Hugging Face's logo

dyang415
/
mixtral-fc-w-resp-new-format-4e-no-negative

PEFT
Safetensors
mixtral
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
dyang415 commited on
Commit
2557733
•
1 Parent(s): 7206b2d

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. checkpoint-192/README.md +216 -0
  2. checkpoint-192/adapter_config.json +28 -0
  3. checkpoint-192/adapter_model.safetensors +3 -0
  4. checkpoint-192/optimizer.pt +3 -0
  5. checkpoint-192/rng_state_0.pth +3 -0
  6. checkpoint-192/rng_state_1.pth +3 -0
  7. checkpoint-192/scheduler.pt +3 -0
  8. checkpoint-192/trainer_state.json +1173 -0
  9. checkpoint-192/training_args.bin +3 -0
  10. checkpoint-288/README.md +216 -0
  11. checkpoint-288/adapter_config.json +28 -0
  12. checkpoint-288/adapter_model.safetensors +3 -0
  13. checkpoint-288/optimizer.pt +3 -0
  14. checkpoint-288/rng_state_0.pth +3 -0
  15. checkpoint-288/rng_state_1.pth +3 -0
  16. checkpoint-288/scheduler.pt +3 -0
  17. checkpoint-288/trainer_state.json +1749 -0
  18. checkpoint-288/training_args.bin +3 -0
  19. checkpoint-384/README.md +216 -0
  20. checkpoint-384/adapter_config.json +28 -0
  21. checkpoint-384/adapter_model.safetensors +3 -0
  22. checkpoint-384/optimizer.pt +3 -0
  23. checkpoint-384/rng_state_0.pth +3 -0
  24. checkpoint-384/rng_state_1.pth +3 -0
  25. checkpoint-384/scheduler.pt +3 -0
  26. checkpoint-384/trainer_state.json +2325 -0
  27. checkpoint-384/training_args.bin +3 -0
  28. checkpoint-96/README.md +216 -0
  29. checkpoint-96/adapter_config.json +28 -0
  30. checkpoint-96/adapter_model.safetensors +3 -0
  31. checkpoint-96/optimizer.pt +3 -0
  32. checkpoint-96/rng_state_0.pth +3 -0
  33. checkpoint-96/rng_state_1.pth +3 -0
  34. checkpoint-96/scheduler.pt +3 -0
  35. checkpoint-96/trainer_state.json +597 -0
  36. checkpoint-96/training_args.bin +3 -0
checkpoint-192/README.md ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ## Training procedure
201
+
202
+ The following `bitsandbytes` quantization config was used during training:
203
+ - quant_method: QuantizationMethod.BITS_AND_BYTES
204
+ - load_in_8bit: False
205
+ - load_in_4bit: True
206
+ - llm_int8_threshold: 6.0
207
+ - llm_int8_skip_modules: None
208
+ - llm_int8_enable_fp32_cpu_offload: False
209
+ - llm_int8_has_fp16_weight: False
210
+ - bnb_4bit_quant_type: nf4
211
+ - bnb_4bit_use_double_quant: True
212
+ - bnb_4bit_compute_dtype: bfloat16
213
+
214
+ ### Framework versions
215
+
216
+ - PEFT 0.7.0
checkpoint-192/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj",
24
+ "o_proj",
25
+ "k_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-192/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b43e19ac8f53943fe358dcf838b1406b6797242ec5279f3789bff8bccc4ef39
3
+ size 109086416
checkpoint-192/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf81335e1b497b6ff1791c9210543a0613df426cec6f783e7fbcb38f8d4daa87
3
+ size 54936735
checkpoint-192/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:534fa79523c0ccf10ecfacbca7fc7552642f2c512a4a72e38a1f05031bd9752c
3
+ size 15607
checkpoint-192/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a07ac4554e6b85be2b8bc1655c478164d6a5a7bac789d6ed65dbc7e59dfbff
3
+ size 15607
checkpoint-192/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b80b4052e3d6d8a77f4a95b8ccc29b78bf92b6e3837f6d89db4a2ce535366a1a
3
+ size 627
checkpoint-192/trainer_state.json ADDED
@@ -0,0 +1,1173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.981818181818182,
5
+ "eval_steps": 500,
6
+ "global_step": 192,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2e-05,
14
+ "loss": 2.1617,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.1579,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "learning_rate": 6e-05,
26
+ "loss": 2.0917,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.04,
31
+ "learning_rate": 8e-05,
32
+ "loss": 1.8765,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.05,
37
+ "learning_rate": 0.0001,
38
+ "loss": 1.3302,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.06,
43
+ "learning_rate": 0.00012,
44
+ "loss": 0.9737,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.07,
49
+ "learning_rate": 0.00014,
50
+ "loss": 0.7302,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.08,
55
+ "learning_rate": 0.00016,
56
+ "loss": 0.534,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.09,
61
+ "learning_rate": 0.00018,
62
+ "loss": 0.4094,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.1,
67
+ "learning_rate": 0.0002,
68
+ "loss": 0.35,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.11,
73
+ "learning_rate": 0.00019999647203724434,
74
+ "loss": 0.3007,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.12,
79
+ "learning_rate": 0.00019998588839790777,
80
+ "loss": 0.2644,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.14,
85
+ "learning_rate": 0.000199968249828764,
86
+ "loss": 0.2454,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.15,
91
+ "learning_rate": 0.00019994355757437738,
92
+ "loss": 0.2029,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.16,
97
+ "learning_rate": 0.0001999118133770149,
98
+ "loss": 0.204,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.17,
103
+ "learning_rate": 0.00019987301947652352,
104
+ "loss": 0.1925,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.18,
109
+ "learning_rate": 0.00019982717861017198,
110
+ "loss": 0.184,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.19,
115
+ "learning_rate": 0.0001997742940124576,
116
+ "loss": 0.1639,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.2,
121
+ "learning_rate": 0.00019971436941487833,
122
+ "loss": 0.1655,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.21,
127
+ "learning_rate": 0.000199647409045669,
128
+ "loss": 0.1566,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.22,
133
+ "learning_rate": 0.00019957341762950344,
134
+ "loss": 0.1571,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.23,
139
+ "learning_rate": 0.0001994924003871609,
140
+ "loss": 0.1477,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.24,
145
+ "learning_rate": 0.0001994043630351576,
146
+ "loss": 0.1495,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.25,
151
+ "learning_rate": 0.0001993093117853435,
152
+ "loss": 0.1388,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.26,
157
+ "learning_rate": 0.00019920725334446405,
158
+ "loss": 0.1466,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.27,
163
+ "learning_rate": 0.00019909819491368676,
164
+ "loss": 0.141,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.28,
169
+ "learning_rate": 0.0001989821441880933,
170
+ "loss": 0.1315,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.29,
175
+ "learning_rate": 0.0001988591093561364,
176
+ "loss": 0.1354,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.3,
181
+ "learning_rate": 0.00019872909909906215,
182
+ "loss": 0.129,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.31,
187
+ "learning_rate": 0.00019859212259029752,
188
+ "loss": 0.1266,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.32,
193
+ "learning_rate": 0.00019844818949480285,
194
+ "loss": 0.1233,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.33,
199
+ "learning_rate": 0.0001982973099683902,
200
+ "loss": 0.121,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.34,
205
+ "learning_rate": 0.00019813949465700653,
206
+ "loss": 0.1284,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.35,
211
+ "learning_rate": 0.00019797475469598267,
212
+ "loss": 0.1266,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.36,
217
+ "learning_rate": 0.00019780310170924753,
218
+ "loss": 0.1218,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.37,
223
+ "learning_rate": 0.00019762454780850806,
224
+ "loss": 0.1264,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.38,
229
+ "learning_rate": 0.0001974391055923944,
230
+ "loss": 0.1191,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.39,
235
+ "learning_rate": 0.00019724678814557128,
236
+ "loss": 0.1173,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.41,
241
+ "learning_rate": 0.00019704760903781446,
242
+ "loss": 0.1128,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.42,
247
+ "learning_rate": 0.0001968415823230534,
248
+ "loss": 0.1113,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.43,
253
+ "learning_rate": 0.0001966287225383796,
254
+ "loss": 0.1087,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.44,
259
+ "learning_rate": 0.00019640904470302097,
260
+ "loss": 0.1163,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.45,
265
+ "learning_rate": 0.00019618256431728194,
266
+ "loss": 0.1084,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.46,
271
+ "learning_rate": 0.00019594929736144976,
272
+ "loss": 0.105,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.47,
277
+ "learning_rate": 0.0001957092602946671,
278
+ "loss": 0.1124,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.48,
283
+ "learning_rate": 0.00019546247005377065,
284
+ "loss": 0.1086,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.49,
289
+ "learning_rate": 0.0001952089440520959,
290
+ "loss": 0.111,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.5,
295
+ "learning_rate": 0.00019494870017824876,
296
+ "loss": 0.1109,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.51,
301
+ "learning_rate": 0.00019468175679484304,
302
+ "loss": 0.106,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.52,
307
+ "learning_rate": 0.00019440813273720504,
308
+ "loss": 0.1087,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.53,
313
+ "learning_rate": 0.0001941278473120445,
314
+ "loss": 0.1065,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.54,
319
+ "learning_rate": 0.0001938409202960922,
320
+ "loss": 0.1079,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.55,
325
+ "learning_rate": 0.00019354737193470466,
326
+ "loss": 0.1055,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.56,
331
+ "learning_rate": 0.00019324722294043558,
332
+ "loss": 0.1072,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.57,
337
+ "learning_rate": 0.00019294049449157448,
338
+ "loss": 0.1056,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.58,
343
+ "learning_rate": 0.00019262720823065216,
344
+ "loss": 0.1073,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.59,
349
+ "learning_rate": 0.0001923073862629139,
350
+ "loss": 0.1075,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.6,
355
+ "learning_rate": 0.00019198105115475947,
356
+ "loss": 0.0995,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.61,
361
+ "learning_rate": 0.000191648225932151,
362
+ "loss": 0.0973,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.62,
367
+ "learning_rate": 0.00019130893407898834,
368
+ "loss": 0.1021,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.63,
373
+ "learning_rate": 0.00019096319953545185,
374
+ "loss": 0.1096,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.64,
379
+ "learning_rate": 0.0001906110466963134,
380
+ "loss": 0.1007,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.65,
385
+ "learning_rate": 0.00019025250040921506,
386
+ "loss": 0.1003,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.66,
391
+ "learning_rate": 0.00018988758597291577,
392
+ "loss": 0.0959,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.68,
397
+ "learning_rate": 0.00018951632913550626,
398
+ "loss": 0.0996,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.69,
403
+ "learning_rate": 0.00018913875609259247,
404
+ "loss": 0.0965,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.7,
409
+ "learning_rate": 0.00018875489348544705,
410
+ "loss": 0.1011,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.71,
415
+ "learning_rate": 0.00018836476839912967,
416
+ "loss": 0.0966,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.72,
421
+ "learning_rate": 0.00018796840836057577,
422
+ "loss": 0.0967,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.73,
427
+ "learning_rate": 0.00018756584133665448,
428
+ "loss": 0.1003,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.74,
433
+ "learning_rate": 0.00018715709573219506,
434
+ "loss": 0.1006,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.75,
439
+ "learning_rate": 0.00018674220038798298,
440
+ "loss": 0.0962,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.76,
445
+ "learning_rate": 0.00018632118457872463,
446
+ "loss": 0.0996,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.77,
451
+ "learning_rate": 0.0001858940780109819,
452
+ "loss": 0.101,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.78,
457
+ "learning_rate": 0.0001854609108210761,
458
+ "loss": 0.1049,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.79,
463
+ "learning_rate": 0.00018502171357296144,
464
+ "loss": 0.1,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.8,
469
+ "learning_rate": 0.00018457651725606861,
470
+ "loss": 0.0975,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.81,
475
+ "learning_rate": 0.00018412535328311814,
476
+ "loss": 0.0959,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.82,
481
+ "learning_rate": 0.00018366825348790388,
482
+ "loss": 0.0936,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.83,
487
+ "learning_rate": 0.00018320525012304685,
488
+ "loss": 0.0956,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.84,
493
+ "learning_rate": 0.00018273637585771964,
494
+ "loss": 0.1004,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.85,
499
+ "learning_rate": 0.00018226166377534114,
500
+ "loss": 0.0964,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.86,
505
+ "learning_rate": 0.00018178114737124224,
506
+ "loss": 0.0974,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.87,
511
+ "learning_rate": 0.00018129486055030257,
512
+ "loss": 0.0963,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.88,
517
+ "learning_rate": 0.0001808028376245579,
518
+ "loss": 0.0973,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.89,
523
+ "learning_rate": 0.00018030511331077945,
524
+ "loss": 0.0959,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.9,
529
+ "learning_rate": 0.000179801722728024,
530
+ "loss": 0.0941,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.91,
535
+ "learning_rate": 0.00017929270139515604,
536
+ "loss": 0.095,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.92,
541
+ "learning_rate": 0.00017877808522834173,
542
+ "loss": 0.0992,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.94,
547
+ "learning_rate": 0.0001782579105385145,
548
+ "loss": 0.0912,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.95,
553
+ "learning_rate": 0.00017773221402881295,
554
+ "loss": 0.0943,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.96,
559
+ "learning_rate": 0.0001772010327919912,
560
+ "loss": 0.0959,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.97,
565
+ "learning_rate": 0.0001766644043078017,
566
+ "loss": 0.0972,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.98,
571
+ "learning_rate": 0.0001761223664403505,
572
+ "loss": 0.0933,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.99,
577
+ "learning_rate": 0.00017557495743542585,
578
+ "loss": 0.0947,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 1.0,
583
+ "learning_rate": 0.0001750222159177993,
584
+ "loss": 0.0958,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 1.01,
589
+ "learning_rate": 0.00017446418088850067,
590
+ "loss": 0.0981,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 1.01,
595
+ "learning_rate": 0.00017390089172206592,
596
+ "loss": 0.0952,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 1.02,
601
+ "learning_rate": 0.00017333238816375906,
602
+ "loss": 0.0894,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 1.03,
607
+ "learning_rate": 0.0001727587103267677,
608
+ "loss": 0.092,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 1.04,
613
+ "learning_rate": 0.00017217989868937265,
614
+ "loss": 0.0908,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 1.05,
619
+ "learning_rate": 0.00017159599409209193,
620
+ "loss": 0.0902,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 1.06,
625
+ "learning_rate": 0.000171007037734799,
626
+ "loss": 0.0903,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 1.07,
631
+ "learning_rate": 0.0001704130711738157,
632
+ "loss": 0.0844,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 1.08,
637
+ "learning_rate": 0.00016981413631898012,
638
+ "loss": 0.0901,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 1.09,
643
+ "learning_rate": 0.0001692102754306895,
644
+ "loss": 0.0923,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 1.1,
649
+ "learning_rate": 0.00016860153111691832,
650
+ "loss": 0.0893,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 1.11,
655
+ "learning_rate": 0.00016798794633021192,
656
+ "loss": 0.0946,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 1.12,
661
+ "learning_rate": 0.00016736956436465573,
662
+ "loss": 0.0911,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 1.13,
667
+ "learning_rate": 0.0001667464288528207,
668
+ "loss": 0.0919,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 1.14,
673
+ "learning_rate": 0.0001661185837626843,
674
+ "loss": 0.0921,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 1.15,
679
+ "learning_rate": 0.00016548607339452853,
680
+ "loss": 0.0897,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 1.16,
685
+ "learning_rate": 0.00016484894237781371,
686
+ "loss": 0.0938,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 1.17,
691
+ "learning_rate": 0.00016420723566802983,
692
+ "loss": 0.0883,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 1.18,
697
+ "learning_rate": 0.00016356099854352433,
698
+ "loss": 0.0937,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 1.19,
703
+ "learning_rate": 0.00016291027660230733,
704
+ "loss": 0.0939,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 1.2,
709
+ "learning_rate": 0.00016225511575883433,
710
+ "loss": 0.0912,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 1.21,
715
+ "learning_rate": 0.00016159556224076637,
716
+ "loss": 0.0894,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 1.22,
721
+ "learning_rate": 0.00016093166258570845,
722
+ "loss": 0.0858,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 1.23,
727
+ "learning_rate": 0.00016026346363792567,
728
+ "loss": 0.0875,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 1.24,
733
+ "learning_rate": 0.000159591012545038,
734
+ "loss": 0.0917,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 1.25,
739
+ "learning_rate": 0.00015891435675469376,
740
+ "loss": 0.0932,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 1.26,
745
+ "learning_rate": 0.0001582335440112214,
746
+ "loss": 0.0908,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 1.28,
751
+ "learning_rate": 0.000157548622352261,
752
+ "loss": 0.0913,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 1.29,
757
+ "learning_rate": 0.00015685964010537465,
758
+ "loss": 0.0875,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 1.3,
763
+ "learning_rate": 0.00015616664588463647,
764
+ "loss": 0.0863,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 1.31,
769
+ "learning_rate": 0.00015546968858720246,
770
+ "loss": 0.0896,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 1.32,
775
+ "learning_rate": 0.00015476881738986037,
776
+ "loss": 0.0853,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 1.33,
781
+ "learning_rate": 0.00015406408174555976,
782
+ "loss": 0.0894,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 1.34,
787
+ "learning_rate": 0.00015335553137992285,
788
+ "loss": 0.0855,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 1.35,
793
+ "learning_rate": 0.0001526432162877356,
794
+ "loss": 0.0867,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 1.36,
799
+ "learning_rate": 0.0001519271867294203,
800
+ "loss": 0.0895,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 1.37,
805
+ "learning_rate": 0.00015120749322748925,
806
+ "loss": 0.0873,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 1.38,
811
+ "learning_rate": 0.0001504841865629799,
812
+ "loss": 0.0898,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 1.39,
817
+ "learning_rate": 0.0001497573177718716,
818
+ "loss": 0.09,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 1.4,
823
+ "learning_rate": 0.0001490269381414849,
824
+ "loss": 0.086,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 1.41,
829
+ "learning_rate": 0.00014829309920686245,
830
+ "loss": 0.0878,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 1.42,
835
+ "learning_rate": 0.0001475558527471329,
836
+ "loss": 0.088,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 1.43,
841
+ "learning_rate": 0.00014681525078185715,
842
+ "loss": 0.0832,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 1.44,
847
+ "learning_rate": 0.00014607134556735834,
848
+ "loss": 0.0925,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 1.45,
853
+ "learning_rate": 0.00014532418959303423,
854
+ "loss": 0.0909,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 1.46,
859
+ "learning_rate": 0.00014457383557765386,
860
+ "loss": 0.0909,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 1.47,
865
+ "learning_rate": 0.00014382033646563754,
866
+ "loss": 0.0915,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 1.48,
871
+ "learning_rate": 0.00014306374542332143,
872
+ "loss": 0.0911,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 1.49,
877
+ "learning_rate": 0.0001423041158352058,
878
+ "loss": 0.0845,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 1.5,
883
+ "learning_rate": 0.00014154150130018866,
884
+ "loss": 0.0863,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 1.51,
889
+ "learning_rate": 0.00014077595562778347,
890
+ "loss": 0.0882,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 1.52,
895
+ "learning_rate": 0.00014000753283432266,
896
+ "loss": 0.0874,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 1.54,
901
+ "learning_rate": 0.00013923628713914617,
902
+ "loss": 0.0864,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 1.55,
907
+ "learning_rate": 0.00013846227296077568,
908
+ "loss": 0.092,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 1.56,
913
+ "learning_rate": 0.00013768554491307516,
914
+ "loss": 0.0887,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 1.57,
919
+ "learning_rate": 0.000136906157801397,
920
+ "loss": 0.0889,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 1.58,
925
+ "learning_rate": 0.00013612416661871533,
926
+ "loss": 0.0865,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 1.59,
931
+ "learning_rate": 0.0001353396265417454,
932
+ "loss": 0.0865,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 1.6,
937
+ "learning_rate": 0.00013455259292705071,
938
+ "loss": 0.0845,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 1.61,
943
+ "learning_rate": 0.00013376312130713687,
944
+ "loss": 0.0908,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 1.62,
949
+ "learning_rate": 0.0001329712673865333,
950
+ "loss": 0.0902,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 1.63,
955
+ "learning_rate": 0.0001321770870378628,
956
+ "loss": 0.0867,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 1.64,
961
+ "learning_rate": 0.00013138063629789922,
962
+ "loss": 0.0899,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 1.65,
967
+ "learning_rate": 0.00013058197136361343,
968
+ "loss": 0.0893,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 1.66,
973
+ "learning_rate": 0.00012978114858820834,
974
+ "loss": 0.086,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 1.67,
979
+ "learning_rate": 0.00012897822447714247,
980
+ "loss": 0.0853,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 1.68,
985
+ "learning_rate": 0.00012817325568414297,
986
+ "loss": 0.0844,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 1.69,
991
+ "learning_rate": 0.0001273662990072083,
992
+ "loss": 0.0905,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 1.7,
997
+ "learning_rate": 0.00012655741138460045,
998
+ "loss": 0.0856,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 1.71,
1003
+ "learning_rate": 0.00012574664989082758,
1004
+ "loss": 0.0896,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 1.72,
1009
+ "learning_rate": 0.00012493407173261675,
1010
+ "loss": 0.0843,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 1.73,
1015
+ "learning_rate": 0.0001241197342448775,
1016
+ "loss": 0.0869,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 1.74,
1021
+ "learning_rate": 0.00012330369488665647,
1022
+ "loss": 0.0889,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 1.75,
1027
+ "learning_rate": 0.0001224860112370828,
1028
+ "loss": 0.089,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 1.76,
1033
+ "learning_rate": 0.00012166674099130577,
1034
+ "loss": 0.0901,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 1.77,
1039
+ "learning_rate": 0.00012084594195642367,
1040
+ "loss": 0.0882,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 1.78,
1045
+ "learning_rate": 0.00012002367204740496,
1046
+ "loss": 0.085,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.79,
1051
+ "learning_rate": 0.00011919998928300203,
1052
+ "loss": 0.0865,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.81,
1057
+ "learning_rate": 0.00011837495178165706,
1058
+ "loss": 0.083,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.82,
1063
+ "learning_rate": 0.00011754861775740162,
1064
+ "loss": 0.0919,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.83,
1069
+ "learning_rate": 0.00011672104551574896,
1070
+ "loss": 0.0853,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.84,
1075
+ "learning_rate": 0.00011589229344957999,
1076
+ "loss": 0.0898,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.85,
1081
+ "learning_rate": 0.0001150624200350232,
1082
+ "loss": 0.085,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.86,
1087
+ "learning_rate": 0.00011423148382732853,
1088
+ "loss": 0.0881,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.87,
1093
+ "learning_rate": 0.00011339954345673582,
1094
+ "loss": 0.0909,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.88,
1099
+ "learning_rate": 0.00011256665762433798,
1100
+ "loss": 0.0815,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.89,
1105
+ "learning_rate": 0.00011173288509793889,
1106
+ "loss": 0.0858,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.9,
1111
+ "learning_rate": 0.00011089828470790693,
1112
+ "loss": 0.0825,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.91,
1117
+ "learning_rate": 0.00011006291534302402,
1118
+ "loss": 0.0838,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.92,
1123
+ "learning_rate": 0.00010922683594633021,
1124
+ "loss": 0.0863,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.93,
1129
+ "learning_rate": 0.00010839010551096498,
1130
+ "loss": 0.0871,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.94,
1135
+ "learning_rate": 0.00010755278307600458,
1136
+ "loss": 0.0825,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.95,
1141
+ "learning_rate": 0.00010671492772229628,
1142
+ "loss": 0.0886,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.96,
1147
+ "learning_rate": 0.0001058765985682898,
1148
+ "loss": 0.0851,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.97,
1153
+ "learning_rate": 0.00010503785476586569,
1154
+ "loss": 0.087,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.98,
1159
+ "learning_rate": 0.00010419875549616196,
1160
+ "loss": 0.0863,
1161
+ "step": 192
1162
+ }
1163
+ ],
1164
+ "logging_steps": 1,
1165
+ "max_steps": 384,
1166
+ "num_input_tokens_seen": 0,
1167
+ "num_train_epochs": 4,
1168
+ "save_steps": 96,
1169
+ "total_flos": 1.4072422274753888e+19,
1170
+ "train_batch_size": 2,
1171
+ "trial_name": null,
1172
+ "trial_params": null
1173
+ }
checkpoint-192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12beba6580debef350132c689cb747c91282ee11c5990b44305f48ba18424e41
3
+ size 4923
checkpoint-288/README.md ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ## Training procedure
201
+
202
+ The following `bitsandbytes` quantization config was used during training:
203
+ - quant_method: QuantizationMethod.BITS_AND_BYTES
204
+ - load_in_8bit: False
205
+ - load_in_4bit: True
206
+ - llm_int8_threshold: 6.0
207
+ - llm_int8_skip_modules: None
208
+ - llm_int8_enable_fp32_cpu_offload: False
209
+ - llm_int8_has_fp16_weight: False
210
+ - bnb_4bit_quant_type: nf4
211
+ - bnb_4bit_use_double_quant: True
212
+ - bnb_4bit_compute_dtype: bfloat16
213
+
214
+ ### Framework versions
215
+
216
+ - PEFT 0.7.0
checkpoint-288/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj",
24
+ "o_proj",
25
+ "k_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-288/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa64e9769784239b4af961418f101e01b73816a849d9f03c450221a9ab301bc
3
+ size 109086416
checkpoint-288/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33a7f810eedc7a7c9d37d078a616a8ca680aeff4d3b742096aca24a0a14ce41
3
+ size 54936991
checkpoint-288/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0952915ac057bdebcf6ae1dfd309f32d5c0ab07191f146dc93d7e32f5c9e1fc
3
+ size 15607
checkpoint-288/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5e1d7594993d5b1ec11cbdb28e37f07bbbd05377ac7cf6f389b933acd2350b9
3
+ size 15607
checkpoint-288/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:569f3ee41813133b057ea64a1fa5b6d7131f6766867a738d304298958acac150
3
+ size 627
checkpoint-288/trainer_state.json ADDED
@@ -0,0 +1,1749 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.966233766233766,
5
+ "eval_steps": 500,
6
+ "global_step": 288,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2e-05,
14
+ "loss": 2.1617,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.1579,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "learning_rate": 6e-05,
26
+ "loss": 2.0917,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.04,
31
+ "learning_rate": 8e-05,
32
+ "loss": 1.8765,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.05,
37
+ "learning_rate": 0.0001,
38
+ "loss": 1.3302,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.06,
43
+ "learning_rate": 0.00012,
44
+ "loss": 0.9737,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.07,
49
+ "learning_rate": 0.00014,
50
+ "loss": 0.7302,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.08,
55
+ "learning_rate": 0.00016,
56
+ "loss": 0.534,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.09,
61
+ "learning_rate": 0.00018,
62
+ "loss": 0.4094,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.1,
67
+ "learning_rate": 0.0002,
68
+ "loss": 0.35,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.11,
73
+ "learning_rate": 0.00019999647203724434,
74
+ "loss": 0.3007,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.12,
79
+ "learning_rate": 0.00019998588839790777,
80
+ "loss": 0.2644,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.14,
85
+ "learning_rate": 0.000199968249828764,
86
+ "loss": 0.2454,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.15,
91
+ "learning_rate": 0.00019994355757437738,
92
+ "loss": 0.2029,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.16,
97
+ "learning_rate": 0.0001999118133770149,
98
+ "loss": 0.204,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.17,
103
+ "learning_rate": 0.00019987301947652352,
104
+ "loss": 0.1925,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.18,
109
+ "learning_rate": 0.00019982717861017198,
110
+ "loss": 0.184,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.19,
115
+ "learning_rate": 0.0001997742940124576,
116
+ "loss": 0.1639,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.2,
121
+ "learning_rate": 0.00019971436941487833,
122
+ "loss": 0.1655,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.21,
127
+ "learning_rate": 0.000199647409045669,
128
+ "loss": 0.1566,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.22,
133
+ "learning_rate": 0.00019957341762950344,
134
+ "loss": 0.1571,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.23,
139
+ "learning_rate": 0.0001994924003871609,
140
+ "loss": 0.1477,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.24,
145
+ "learning_rate": 0.0001994043630351576,
146
+ "loss": 0.1495,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.25,
151
+ "learning_rate": 0.0001993093117853435,
152
+ "loss": 0.1388,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.26,
157
+ "learning_rate": 0.00019920725334446405,
158
+ "loss": 0.1466,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.27,
163
+ "learning_rate": 0.00019909819491368676,
164
+ "loss": 0.141,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.28,
169
+ "learning_rate": 0.0001989821441880933,
170
+ "loss": 0.1315,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.29,
175
+ "learning_rate": 0.0001988591093561364,
176
+ "loss": 0.1354,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.3,
181
+ "learning_rate": 0.00019872909909906215,
182
+ "loss": 0.129,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.31,
187
+ "learning_rate": 0.00019859212259029752,
188
+ "loss": 0.1266,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.32,
193
+ "learning_rate": 0.00019844818949480285,
194
+ "loss": 0.1233,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.33,
199
+ "learning_rate": 0.0001982973099683902,
200
+ "loss": 0.121,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.34,
205
+ "learning_rate": 0.00019813949465700653,
206
+ "loss": 0.1284,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.35,
211
+ "learning_rate": 0.00019797475469598267,
212
+ "loss": 0.1266,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.36,
217
+ "learning_rate": 0.00019780310170924753,
218
+ "loss": 0.1218,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.37,
223
+ "learning_rate": 0.00019762454780850806,
224
+ "loss": 0.1264,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.38,
229
+ "learning_rate": 0.0001974391055923944,
230
+ "loss": 0.1191,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.39,
235
+ "learning_rate": 0.00019724678814557128,
236
+ "loss": 0.1173,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.41,
241
+ "learning_rate": 0.00019704760903781446,
242
+ "loss": 0.1128,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.42,
247
+ "learning_rate": 0.0001968415823230534,
248
+ "loss": 0.1113,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.43,
253
+ "learning_rate": 0.0001966287225383796,
254
+ "loss": 0.1087,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.44,
259
+ "learning_rate": 0.00019640904470302097,
260
+ "loss": 0.1163,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.45,
265
+ "learning_rate": 0.00019618256431728194,
266
+ "loss": 0.1084,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.46,
271
+ "learning_rate": 0.00019594929736144976,
272
+ "loss": 0.105,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.47,
277
+ "learning_rate": 0.0001957092602946671,
278
+ "loss": 0.1124,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.48,
283
+ "learning_rate": 0.00019546247005377065,
284
+ "loss": 0.1086,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.49,
289
+ "learning_rate": 0.0001952089440520959,
290
+ "loss": 0.111,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.5,
295
+ "learning_rate": 0.00019494870017824876,
296
+ "loss": 0.1109,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.51,
301
+ "learning_rate": 0.00019468175679484304,
302
+ "loss": 0.106,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.52,
307
+ "learning_rate": 0.00019440813273720504,
308
+ "loss": 0.1087,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.53,
313
+ "learning_rate": 0.0001941278473120445,
314
+ "loss": 0.1065,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.54,
319
+ "learning_rate": 0.0001938409202960922,
320
+ "loss": 0.1079,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.55,
325
+ "learning_rate": 0.00019354737193470466,
326
+ "loss": 0.1055,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.56,
331
+ "learning_rate": 0.00019324722294043558,
332
+ "loss": 0.1072,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.57,
337
+ "learning_rate": 0.00019294049449157448,
338
+ "loss": 0.1056,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.58,
343
+ "learning_rate": 0.00019262720823065216,
344
+ "loss": 0.1073,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.59,
349
+ "learning_rate": 0.0001923073862629139,
350
+ "loss": 0.1075,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.6,
355
+ "learning_rate": 0.00019198105115475947,
356
+ "loss": 0.0995,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.61,
361
+ "learning_rate": 0.000191648225932151,
362
+ "loss": 0.0973,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.62,
367
+ "learning_rate": 0.00019130893407898834,
368
+ "loss": 0.1021,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.63,
373
+ "learning_rate": 0.00019096319953545185,
374
+ "loss": 0.1096,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.64,
379
+ "learning_rate": 0.0001906110466963134,
380
+ "loss": 0.1007,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.65,
385
+ "learning_rate": 0.00019025250040921506,
386
+ "loss": 0.1003,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.66,
391
+ "learning_rate": 0.00018988758597291577,
392
+ "loss": 0.0959,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.68,
397
+ "learning_rate": 0.00018951632913550626,
398
+ "loss": 0.0996,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.69,
403
+ "learning_rate": 0.00018913875609259247,
404
+ "loss": 0.0965,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.7,
409
+ "learning_rate": 0.00018875489348544705,
410
+ "loss": 0.1011,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.71,
415
+ "learning_rate": 0.00018836476839912967,
416
+ "loss": 0.0966,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.72,
421
+ "learning_rate": 0.00018796840836057577,
422
+ "loss": 0.0967,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.73,
427
+ "learning_rate": 0.00018756584133665448,
428
+ "loss": 0.1003,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.74,
433
+ "learning_rate": 0.00018715709573219506,
434
+ "loss": 0.1006,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.75,
439
+ "learning_rate": 0.00018674220038798298,
440
+ "loss": 0.0962,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.76,
445
+ "learning_rate": 0.00018632118457872463,
446
+ "loss": 0.0996,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.77,
451
+ "learning_rate": 0.0001858940780109819,
452
+ "loss": 0.101,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.78,
457
+ "learning_rate": 0.0001854609108210761,
458
+ "loss": 0.1049,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.79,
463
+ "learning_rate": 0.00018502171357296144,
464
+ "loss": 0.1,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.8,
469
+ "learning_rate": 0.00018457651725606861,
470
+ "loss": 0.0975,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.81,
475
+ "learning_rate": 0.00018412535328311814,
476
+ "loss": 0.0959,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.82,
481
+ "learning_rate": 0.00018366825348790388,
482
+ "loss": 0.0936,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.83,
487
+ "learning_rate": 0.00018320525012304685,
488
+ "loss": 0.0956,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.84,
493
+ "learning_rate": 0.00018273637585771964,
494
+ "loss": 0.1004,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.85,
499
+ "learning_rate": 0.00018226166377534114,
500
+ "loss": 0.0964,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.86,
505
+ "learning_rate": 0.00018178114737124224,
506
+ "loss": 0.0974,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.87,
511
+ "learning_rate": 0.00018129486055030257,
512
+ "loss": 0.0963,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.88,
517
+ "learning_rate": 0.0001808028376245579,
518
+ "loss": 0.0973,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.89,
523
+ "learning_rate": 0.00018030511331077945,
524
+ "loss": 0.0959,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.9,
529
+ "learning_rate": 0.000179801722728024,
530
+ "loss": 0.0941,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.91,
535
+ "learning_rate": 0.00017929270139515604,
536
+ "loss": 0.095,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.92,
541
+ "learning_rate": 0.00017877808522834173,
542
+ "loss": 0.0992,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.94,
547
+ "learning_rate": 0.0001782579105385145,
548
+ "loss": 0.0912,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.95,
553
+ "learning_rate": 0.00017773221402881295,
554
+ "loss": 0.0943,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.96,
559
+ "learning_rate": 0.0001772010327919912,
560
+ "loss": 0.0959,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.97,
565
+ "learning_rate": 0.0001766644043078017,
566
+ "loss": 0.0972,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.98,
571
+ "learning_rate": 0.0001761223664403505,
572
+ "loss": 0.0933,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.99,
577
+ "learning_rate": 0.00017557495743542585,
578
+ "loss": 0.0947,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 1.0,
583
+ "learning_rate": 0.0001750222159177993,
584
+ "loss": 0.0958,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 1.01,
589
+ "learning_rate": 0.00017446418088850067,
590
+ "loss": 0.0981,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 1.01,
595
+ "learning_rate": 0.00017390089172206592,
596
+ "loss": 0.0952,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 1.02,
601
+ "learning_rate": 0.00017333238816375906,
602
+ "loss": 0.0894,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 1.03,
607
+ "learning_rate": 0.0001727587103267677,
608
+ "loss": 0.092,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 1.04,
613
+ "learning_rate": 0.00017217989868937265,
614
+ "loss": 0.0908,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 1.05,
619
+ "learning_rate": 0.00017159599409209193,
620
+ "loss": 0.0902,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 1.06,
625
+ "learning_rate": 0.000171007037734799,
626
+ "loss": 0.0903,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 1.07,
631
+ "learning_rate": 0.0001704130711738157,
632
+ "loss": 0.0844,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 1.08,
637
+ "learning_rate": 0.00016981413631898012,
638
+ "loss": 0.0901,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 1.09,
643
+ "learning_rate": 0.0001692102754306895,
644
+ "loss": 0.0923,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 1.1,
649
+ "learning_rate": 0.00016860153111691832,
650
+ "loss": 0.0893,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 1.11,
655
+ "learning_rate": 0.00016798794633021192,
656
+ "loss": 0.0946,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 1.12,
661
+ "learning_rate": 0.00016736956436465573,
662
+ "loss": 0.0911,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 1.13,
667
+ "learning_rate": 0.0001667464288528207,
668
+ "loss": 0.0919,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 1.14,
673
+ "learning_rate": 0.0001661185837626843,
674
+ "loss": 0.0921,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 1.15,
679
+ "learning_rate": 0.00016548607339452853,
680
+ "loss": 0.0897,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 1.16,
685
+ "learning_rate": 0.00016484894237781371,
686
+ "loss": 0.0938,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 1.17,
691
+ "learning_rate": 0.00016420723566802983,
692
+ "loss": 0.0883,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 1.18,
697
+ "learning_rate": 0.00016356099854352433,
698
+ "loss": 0.0937,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 1.19,
703
+ "learning_rate": 0.00016291027660230733,
704
+ "loss": 0.0939,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 1.2,
709
+ "learning_rate": 0.00016225511575883433,
710
+ "loss": 0.0912,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 1.21,
715
+ "learning_rate": 0.00016159556224076637,
716
+ "loss": 0.0894,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 1.22,
721
+ "learning_rate": 0.00016093166258570845,
722
+ "loss": 0.0858,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 1.23,
727
+ "learning_rate": 0.00016026346363792567,
728
+ "loss": 0.0875,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 1.24,
733
+ "learning_rate": 0.000159591012545038,
734
+ "loss": 0.0917,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 1.25,
739
+ "learning_rate": 0.00015891435675469376,
740
+ "loss": 0.0932,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 1.26,
745
+ "learning_rate": 0.0001582335440112214,
746
+ "loss": 0.0908,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 1.28,
751
+ "learning_rate": 0.000157548622352261,
752
+ "loss": 0.0913,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 1.29,
757
+ "learning_rate": 0.00015685964010537465,
758
+ "loss": 0.0875,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 1.3,
763
+ "learning_rate": 0.00015616664588463647,
764
+ "loss": 0.0863,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 1.31,
769
+ "learning_rate": 0.00015546968858720246,
770
+ "loss": 0.0896,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 1.32,
775
+ "learning_rate": 0.00015476881738986037,
776
+ "loss": 0.0853,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 1.33,
781
+ "learning_rate": 0.00015406408174555976,
782
+ "loss": 0.0894,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 1.34,
787
+ "learning_rate": 0.00015335553137992285,
788
+ "loss": 0.0855,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 1.35,
793
+ "learning_rate": 0.0001526432162877356,
794
+ "loss": 0.0867,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 1.36,
799
+ "learning_rate": 0.0001519271867294203,
800
+ "loss": 0.0895,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 1.37,
805
+ "learning_rate": 0.00015120749322748925,
806
+ "loss": 0.0873,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 1.38,
811
+ "learning_rate": 0.0001504841865629799,
812
+ "loss": 0.0898,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 1.39,
817
+ "learning_rate": 0.0001497573177718716,
818
+ "loss": 0.09,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 1.4,
823
+ "learning_rate": 0.0001490269381414849,
824
+ "loss": 0.086,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 1.41,
829
+ "learning_rate": 0.00014829309920686245,
830
+ "loss": 0.0878,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 1.42,
835
+ "learning_rate": 0.0001475558527471329,
836
+ "loss": 0.088,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 1.43,
841
+ "learning_rate": 0.00014681525078185715,
842
+ "loss": 0.0832,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 1.44,
847
+ "learning_rate": 0.00014607134556735834,
848
+ "loss": 0.0925,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 1.45,
853
+ "learning_rate": 0.00014532418959303423,
854
+ "loss": 0.0909,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 1.46,
859
+ "learning_rate": 0.00014457383557765386,
860
+ "loss": 0.0909,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 1.47,
865
+ "learning_rate": 0.00014382033646563754,
866
+ "loss": 0.0915,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 1.48,
871
+ "learning_rate": 0.00014306374542332143,
872
+ "loss": 0.0911,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 1.49,
877
+ "learning_rate": 0.0001423041158352058,
878
+ "loss": 0.0845,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 1.5,
883
+ "learning_rate": 0.00014154150130018866,
884
+ "loss": 0.0863,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 1.51,
889
+ "learning_rate": 0.00014077595562778347,
890
+ "loss": 0.0882,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 1.52,
895
+ "learning_rate": 0.00014000753283432266,
896
+ "loss": 0.0874,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 1.54,
901
+ "learning_rate": 0.00013923628713914617,
902
+ "loss": 0.0864,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 1.55,
907
+ "learning_rate": 0.00013846227296077568,
908
+ "loss": 0.092,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 1.56,
913
+ "learning_rate": 0.00013768554491307516,
914
+ "loss": 0.0887,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 1.57,
919
+ "learning_rate": 0.000136906157801397,
920
+ "loss": 0.0889,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 1.58,
925
+ "learning_rate": 0.00013612416661871533,
926
+ "loss": 0.0865,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 1.59,
931
+ "learning_rate": 0.0001353396265417454,
932
+ "loss": 0.0865,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 1.6,
937
+ "learning_rate": 0.00013455259292705071,
938
+ "loss": 0.0845,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 1.61,
943
+ "learning_rate": 0.00013376312130713687,
944
+ "loss": 0.0908,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 1.62,
949
+ "learning_rate": 0.0001329712673865333,
950
+ "loss": 0.0902,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 1.63,
955
+ "learning_rate": 0.0001321770870378628,
956
+ "loss": 0.0867,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 1.64,
961
+ "learning_rate": 0.00013138063629789922,
962
+ "loss": 0.0899,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 1.65,
967
+ "learning_rate": 0.00013058197136361343,
968
+ "loss": 0.0893,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 1.66,
973
+ "learning_rate": 0.00012978114858820834,
974
+ "loss": 0.086,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 1.67,
979
+ "learning_rate": 0.00012897822447714247,
980
+ "loss": 0.0853,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 1.68,
985
+ "learning_rate": 0.00012817325568414297,
986
+ "loss": 0.0844,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 1.69,
991
+ "learning_rate": 0.0001273662990072083,
992
+ "loss": 0.0905,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 1.7,
997
+ "learning_rate": 0.00012655741138460045,
998
+ "loss": 0.0856,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 1.71,
1003
+ "learning_rate": 0.00012574664989082758,
1004
+ "loss": 0.0896,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 1.72,
1009
+ "learning_rate": 0.00012493407173261675,
1010
+ "loss": 0.0843,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 1.73,
1015
+ "learning_rate": 0.0001241197342448775,
1016
+ "loss": 0.0869,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 1.74,
1021
+ "learning_rate": 0.00012330369488665647,
1022
+ "loss": 0.0889,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 1.75,
1027
+ "learning_rate": 0.0001224860112370828,
1028
+ "loss": 0.089,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 1.76,
1033
+ "learning_rate": 0.00012166674099130577,
1034
+ "loss": 0.0901,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 1.77,
1039
+ "learning_rate": 0.00012084594195642367,
1040
+ "loss": 0.0882,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 1.78,
1045
+ "learning_rate": 0.00012002367204740496,
1046
+ "loss": 0.085,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.79,
1051
+ "learning_rate": 0.00011919998928300203,
1052
+ "loss": 0.0865,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.81,
1057
+ "learning_rate": 0.00011837495178165706,
1058
+ "loss": 0.083,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.82,
1063
+ "learning_rate": 0.00011754861775740162,
1064
+ "loss": 0.0919,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.83,
1069
+ "learning_rate": 0.00011672104551574896,
1070
+ "loss": 0.0853,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.84,
1075
+ "learning_rate": 0.00011589229344957999,
1076
+ "loss": 0.0898,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.85,
1081
+ "learning_rate": 0.0001150624200350232,
1082
+ "loss": 0.085,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.86,
1087
+ "learning_rate": 0.00011423148382732853,
1088
+ "loss": 0.0881,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.87,
1093
+ "learning_rate": 0.00011339954345673582,
1094
+ "loss": 0.0909,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.88,
1099
+ "learning_rate": 0.00011256665762433798,
1100
+ "loss": 0.0815,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.89,
1105
+ "learning_rate": 0.00011173288509793889,
1106
+ "loss": 0.0858,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.9,
1111
+ "learning_rate": 0.00011089828470790693,
1112
+ "loss": 0.0825,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.91,
1117
+ "learning_rate": 0.00011006291534302402,
1118
+ "loss": 0.0838,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.92,
1123
+ "learning_rate": 0.00010922683594633021,
1124
+ "loss": 0.0863,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.93,
1129
+ "learning_rate": 0.00010839010551096498,
1130
+ "loss": 0.0871,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.94,
1135
+ "learning_rate": 0.00010755278307600458,
1136
+ "loss": 0.0825,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.95,
1141
+ "learning_rate": 0.00010671492772229628,
1142
+ "loss": 0.0886,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.96,
1147
+ "learning_rate": 0.0001058765985682898,
1148
+ "loss": 0.0851,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.97,
1153
+ "learning_rate": 0.00010503785476586569,
1154
+ "loss": 0.087,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.98,
1159
+ "learning_rate": 0.00010419875549616196,
1160
+ "loss": 0.0863,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.99,
1165
+ "learning_rate": 0.00010335935996539802,
1166
+ "loss": 0.0833,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 2.0,
1171
+ "learning_rate": 0.00010251972740069724,
1172
+ "loss": 0.0884,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 2.01,
1177
+ "learning_rate": 0.00010167991704590803,
1178
+ "loss": 0.0871,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 2.01,
1183
+ "learning_rate": 0.00010083998815742335,
1184
+ "loss": 0.083,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 2.02,
1189
+ "learning_rate": 0.0001,
1190
+ "loss": 0.0843,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 2.03,
1195
+ "learning_rate": 9.916001184257668e-05,
1196
+ "loss": 0.0812,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 2.04,
1201
+ "learning_rate": 9.8320082954092e-05,
1202
+ "loss": 0.0861,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 2.05,
1207
+ "learning_rate": 9.748027259930276e-05,
1208
+ "loss": 0.0803,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 2.06,
1213
+ "learning_rate": 9.6640640034602e-05,
1214
+ "loss": 0.0833,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 2.07,
1219
+ "learning_rate": 9.580124450383803e-05,
1220
+ "loss": 0.0819,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 2.08,
1225
+ "learning_rate": 9.496214523413432e-05,
1226
+ "loss": 0.0833,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 2.09,
1231
+ "learning_rate": 9.412340143171024e-05,
1232
+ "loss": 0.0803,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 2.1,
1237
+ "learning_rate": 9.328507227770375e-05,
1238
+ "loss": 0.0816,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 2.11,
1243
+ "learning_rate": 9.244721692399545e-05,
1244
+ "loss": 0.085,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 2.12,
1249
+ "learning_rate": 9.160989448903504e-05,
1250
+ "loss": 0.0806,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 2.14,
1255
+ "learning_rate": 9.077316405366981e-05,
1256
+ "loss": 0.0843,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 2.15,
1261
+ "learning_rate": 8.993708465697599e-05,
1262
+ "loss": 0.0817,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 2.16,
1267
+ "learning_rate": 8.910171529209305e-05,
1268
+ "loss": 0.0866,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 2.17,
1273
+ "learning_rate": 8.826711490206113e-05,
1274
+ "loss": 0.0806,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 2.18,
1279
+ "learning_rate": 8.743334237566202e-05,
1280
+ "loss": 0.0818,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 2.19,
1285
+ "learning_rate": 8.66004565432642e-05,
1286
+ "loss": 0.0847,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 2.2,
1291
+ "learning_rate": 8.57685161726715e-05,
1292
+ "loss": 0.0813,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 2.21,
1297
+ "learning_rate": 8.493757996497683e-05,
1298
+ "loss": 0.0817,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 2.22,
1303
+ "learning_rate": 8.410770655042003e-05,
1304
+ "loss": 0.0838,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 2.23,
1309
+ "learning_rate": 8.327895448425105e-05,
1310
+ "loss": 0.0845,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 2.24,
1315
+ "learning_rate": 8.245138224259841e-05,
1316
+ "loss": 0.0816,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 2.25,
1321
+ "learning_rate": 8.162504821834295e-05,
1322
+ "loss": 0.0823,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 2.26,
1327
+ "learning_rate": 8.0800010716998e-05,
1328
+ "loss": 0.0847,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 2.27,
1333
+ "learning_rate": 7.997632795259503e-05,
1334
+ "loss": 0.0808,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 2.28,
1339
+ "learning_rate": 7.915405804357633e-05,
1340
+ "loss": 0.0844,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 2.29,
1345
+ "learning_rate": 7.833325900869428e-05,
1346
+ "loss": 0.0838,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 2.3,
1351
+ "learning_rate": 7.751398876291725e-05,
1352
+ "loss": 0.0855,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 2.31,
1357
+ "learning_rate": 7.669630511334358e-05,
1358
+ "loss": 0.0813,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 2.32,
1363
+ "learning_rate": 7.588026575512251e-05,
1364
+ "loss": 0.0825,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 2.33,
1369
+ "learning_rate": 7.506592826738326e-05,
1370
+ "loss": 0.078,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 2.34,
1375
+ "learning_rate": 7.425335010917244e-05,
1376
+ "loss": 0.0823,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 2.35,
1381
+ "learning_rate": 7.344258861539956e-05,
1382
+ "loss": 0.0816,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 2.36,
1387
+ "learning_rate": 7.263370099279172e-05,
1388
+ "loss": 0.0823,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 2.37,
1393
+ "learning_rate": 7.182674431585704e-05,
1394
+ "loss": 0.08,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 2.38,
1399
+ "learning_rate": 7.102177552285753e-05,
1400
+ "loss": 0.0831,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 2.39,
1405
+ "learning_rate": 7.021885141179165e-05,
1406
+ "loss": 0.0856,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 2.41,
1411
+ "learning_rate": 6.941802863638659e-05,
1412
+ "loss": 0.079,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 2.42,
1417
+ "learning_rate": 6.861936370210083e-05,
1418
+ "loss": 0.0809,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 2.43,
1423
+ "learning_rate": 6.782291296213722e-05,
1424
+ "loss": 0.0803,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 2.44,
1429
+ "learning_rate": 6.70287326134667e-05,
1430
+ "loss": 0.0829,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 2.45,
1435
+ "learning_rate": 6.623687869286313e-05,
1436
+ "loss": 0.0808,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 2.46,
1441
+ "learning_rate": 6.54474070729493e-05,
1442
+ "loss": 0.0835,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 2.47,
1447
+ "learning_rate": 6.466037345825462e-05,
1448
+ "loss": 0.0845,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 2.48,
1453
+ "learning_rate": 6.387583338128471e-05,
1454
+ "loss": 0.076,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 2.49,
1459
+ "learning_rate": 6.309384219860301e-05,
1460
+ "loss": 0.0863,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 2.5,
1465
+ "learning_rate": 6.231445508692485e-05,
1466
+ "loss": 0.0817,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 2.51,
1471
+ "learning_rate": 6.153772703922433e-05,
1472
+ "loss": 0.0786,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 2.52,
1477
+ "learning_rate": 6.076371286085387e-05,
1478
+ "loss": 0.0838,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 2.53,
1483
+ "learning_rate": 5.999246716567737e-05,
1484
+ "loss": 0.0845,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 2.54,
1489
+ "learning_rate": 5.9224044372216534e-05,
1490
+ "loss": 0.0805,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 2.55,
1495
+ "learning_rate": 5.845849869981137e-05,
1496
+ "loss": 0.0859,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 2.56,
1501
+ "learning_rate": 5.7695884164794225e-05,
1502
+ "loss": 0.0842,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 2.57,
1507
+ "learning_rate": 5.693625457667862e-05,
1508
+ "loss": 0.0803,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 2.58,
1513
+ "learning_rate": 5.6179663534362504e-05,
1514
+ "loss": 0.0785,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 2.59,
1519
+ "learning_rate": 5.542616442234618e-05,
1520
+ "loss": 0.0833,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 2.6,
1525
+ "learning_rate": 5.4675810406965765e-05,
1526
+ "loss": 0.0801,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 2.61,
1531
+ "learning_rate": 5.392865443264163e-05,
1532
+ "loss": 0.0867,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 2.62,
1537
+ "learning_rate": 5.318474921814289e-05,
1538
+ "loss": 0.0798,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 2.63,
1543
+ "learning_rate": 5.244414725286717e-05,
1544
+ "loss": 0.0819,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 2.64,
1549
+ "learning_rate": 5.170690079313756e-05,
1550
+ "loss": 0.0822,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 2.65,
1555
+ "learning_rate": 5.0973061858515145e-05,
1556
+ "loss": 0.0815,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 2.66,
1561
+ "learning_rate": 5.024268222812843e-05,
1562
+ "loss": 0.083,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 2.68,
1567
+ "learning_rate": 4.9515813437020144e-05,
1568
+ "loss": 0.0814,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 2.69,
1573
+ "learning_rate": 4.879250677251077e-05,
1574
+ "loss": 0.0795,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 2.7,
1579
+ "learning_rate": 4.807281327057972e-05,
1580
+ "loss": 0.0806,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 2.71,
1585
+ "learning_rate": 4.735678371226441e-05,
1586
+ "loss": 0.0825,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 2.72,
1591
+ "learning_rate": 4.6644468620077174e-05,
1592
+ "loss": 0.0783,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 2.73,
1597
+ "learning_rate": 4.593591825444028e-05,
1598
+ "loss": 0.0787,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 2.74,
1603
+ "learning_rate": 4.523118261013969e-05,
1604
+ "loss": 0.0798,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 2.75,
1609
+ "learning_rate": 4.4530311412797576e-05,
1610
+ "loss": 0.0857,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 2.76,
1615
+ "learning_rate": 4.383335411536357e-05,
1616
+ "loss": 0.0834,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 2.77,
1621
+ "learning_rate": 4.314035989462535e-05,
1622
+ "loss": 0.0858,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 2.78,
1627
+ "learning_rate": 4.2451377647738985e-05,
1628
+ "loss": 0.0791,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 2.79,
1633
+ "learning_rate": 4.1766455988778616e-05,
1634
+ "loss": 0.0806,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 2.8,
1639
+ "learning_rate": 4.108564324530626e-05,
1640
+ "loss": 0.0777,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 2.81,
1645
+ "learning_rate": 4.0408987454961986e-05,
1646
+ "loss": 0.0812,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 2.82,
1651
+ "learning_rate": 3.973653636207437e-05,
1652
+ "loss": 0.0776,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 2.83,
1657
+ "learning_rate": 3.90683374142916e-05,
1658
+ "loss": 0.0779,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 2.84,
1663
+ "learning_rate": 3.840443775923365e-05,
1664
+ "loss": 0.0801,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 2.85,
1669
+ "learning_rate": 3.774488424116569e-05,
1670
+ "loss": 0.081,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 2.86,
1675
+ "learning_rate": 3.70897233976927e-05,
1676
+ "loss": 0.0794,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 2.87,
1681
+ "learning_rate": 3.6439001456475695e-05,
1682
+ "loss": 0.0801,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 2.88,
1687
+ "learning_rate": 3.5792764331970185e-05,
1688
+ "loss": 0.0789,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 2.89,
1693
+ "learning_rate": 3.5151057622186336e-05,
1694
+ "loss": 0.0801,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 2.9,
1699
+ "learning_rate": 3.45139266054715e-05,
1700
+ "loss": 0.0769,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 2.91,
1705
+ "learning_rate": 3.3881416237315675e-05,
1706
+ "loss": 0.0794,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 2.92,
1711
+ "learning_rate": 3.325357114717933e-05,
1712
+ "loss": 0.0819,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 2.94,
1717
+ "learning_rate": 3.263043563534428e-05,
1718
+ "loss": 0.0761,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 2.95,
1723
+ "learning_rate": 3.2012053669788135e-05,
1724
+ "loss": 0.0796,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 2.96,
1729
+ "learning_rate": 3.139846888308169e-05,
1730
+ "loss": 0.0799,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 2.97,
1735
+ "learning_rate": 3.078972456931053e-05,
1736
+ "loss": 0.0787,
1737
+ "step": 288
1738
+ }
1739
+ ],
1740
+ "logging_steps": 1,
1741
+ "max_steps": 384,
1742
+ "num_input_tokens_seen": 0,
1743
+ "num_train_epochs": 4,
1744
+ "save_steps": 96,
1745
+ "total_flos": 2.1108633412130832e+19,
1746
+ "train_batch_size": 2,
1747
+ "trial_name": null,
1748
+ "trial_params": null
1749
+ }
checkpoint-288/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12beba6580debef350132c689cb747c91282ee11c5990b44305f48ba18424e41
3
+ size 4923
checkpoint-384/README.md ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ## Training procedure
201
+
202
+ The following `bitsandbytes` quantization config was used during training:
203
+ - quant_method: QuantizationMethod.BITS_AND_BYTES
204
+ - load_in_8bit: False
205
+ - load_in_4bit: True
206
+ - llm_int8_threshold: 6.0
207
+ - llm_int8_skip_modules: None
208
+ - llm_int8_enable_fp32_cpu_offload: False
209
+ - llm_int8_has_fp16_weight: False
210
+ - bnb_4bit_quant_type: nf4
211
+ - bnb_4bit_use_double_quant: True
212
+ - bnb_4bit_compute_dtype: bfloat16
213
+
214
+ ### Framework versions
215
+
216
+ - PEFT 0.7.0
checkpoint-384/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj",
24
+ "o_proj",
25
+ "k_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-384/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd661e04d867e2fc8e9cc38d6536b36db7e0018c2a3d375139650562128fdc23
3
+ size 109086416
checkpoint-384/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d6fd977aeb50dfda7e4f2ca3c889b739677d2725f95792c715045d39309ff9
3
+ size 54936991
checkpoint-384/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a346c6db1f1ddc16105c8089f0ed66c2f0f4a8a4c5b5b57b7dcc0c030c2643
3
+ size 15607
checkpoint-384/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85d06ce774ae3266f0edb6edffbeeedfa53d8691663d064da627590be89a921
3
+ size 15607
checkpoint-384/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c7fa95dbeb9787811a8c75ae4c1bdf2108bd55824797b12a6c8d4b92d1b609
3
+ size 627
checkpoint-384/trainer_state.json ADDED
@@ -0,0 +1,2325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9506493506493507,
5
+ "eval_steps": 500,
6
+ "global_step": 384,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2e-05,
14
+ "loss": 2.1617,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.1579,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "learning_rate": 6e-05,
26
+ "loss": 2.0917,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.04,
31
+ "learning_rate": 8e-05,
32
+ "loss": 1.8765,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.05,
37
+ "learning_rate": 0.0001,
38
+ "loss": 1.3302,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.06,
43
+ "learning_rate": 0.00012,
44
+ "loss": 0.9737,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.07,
49
+ "learning_rate": 0.00014,
50
+ "loss": 0.7302,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.08,
55
+ "learning_rate": 0.00016,
56
+ "loss": 0.534,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.09,
61
+ "learning_rate": 0.00018,
62
+ "loss": 0.4094,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.1,
67
+ "learning_rate": 0.0002,
68
+ "loss": 0.35,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.11,
73
+ "learning_rate": 0.00019999647203724434,
74
+ "loss": 0.3007,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.12,
79
+ "learning_rate": 0.00019998588839790777,
80
+ "loss": 0.2644,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.14,
85
+ "learning_rate": 0.000199968249828764,
86
+ "loss": 0.2454,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.15,
91
+ "learning_rate": 0.00019994355757437738,
92
+ "loss": 0.2029,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.16,
97
+ "learning_rate": 0.0001999118133770149,
98
+ "loss": 0.204,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.17,
103
+ "learning_rate": 0.00019987301947652352,
104
+ "loss": 0.1925,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.18,
109
+ "learning_rate": 0.00019982717861017198,
110
+ "loss": 0.184,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.19,
115
+ "learning_rate": 0.0001997742940124576,
116
+ "loss": 0.1639,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.2,
121
+ "learning_rate": 0.00019971436941487833,
122
+ "loss": 0.1655,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.21,
127
+ "learning_rate": 0.000199647409045669,
128
+ "loss": 0.1566,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.22,
133
+ "learning_rate": 0.00019957341762950344,
134
+ "loss": 0.1571,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.23,
139
+ "learning_rate": 0.0001994924003871609,
140
+ "loss": 0.1477,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.24,
145
+ "learning_rate": 0.0001994043630351576,
146
+ "loss": 0.1495,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.25,
151
+ "learning_rate": 0.0001993093117853435,
152
+ "loss": 0.1388,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.26,
157
+ "learning_rate": 0.00019920725334446405,
158
+ "loss": 0.1466,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.27,
163
+ "learning_rate": 0.00019909819491368676,
164
+ "loss": 0.141,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.28,
169
+ "learning_rate": 0.0001989821441880933,
170
+ "loss": 0.1315,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.29,
175
+ "learning_rate": 0.0001988591093561364,
176
+ "loss": 0.1354,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.3,
181
+ "learning_rate": 0.00019872909909906215,
182
+ "loss": 0.129,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.31,
187
+ "learning_rate": 0.00019859212259029752,
188
+ "loss": 0.1266,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.32,
193
+ "learning_rate": 0.00019844818949480285,
194
+ "loss": 0.1233,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.33,
199
+ "learning_rate": 0.0001982973099683902,
200
+ "loss": 0.121,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.34,
205
+ "learning_rate": 0.00019813949465700653,
206
+ "loss": 0.1284,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.35,
211
+ "learning_rate": 0.00019797475469598267,
212
+ "loss": 0.1266,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.36,
217
+ "learning_rate": 0.00019780310170924753,
218
+ "loss": 0.1218,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.37,
223
+ "learning_rate": 0.00019762454780850806,
224
+ "loss": 0.1264,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.38,
229
+ "learning_rate": 0.0001974391055923944,
230
+ "loss": 0.1191,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.39,
235
+ "learning_rate": 0.00019724678814557128,
236
+ "loss": 0.1173,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.41,
241
+ "learning_rate": 0.00019704760903781446,
242
+ "loss": 0.1128,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.42,
247
+ "learning_rate": 0.0001968415823230534,
248
+ "loss": 0.1113,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.43,
253
+ "learning_rate": 0.0001966287225383796,
254
+ "loss": 0.1087,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.44,
259
+ "learning_rate": 0.00019640904470302097,
260
+ "loss": 0.1163,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.45,
265
+ "learning_rate": 0.00019618256431728194,
266
+ "loss": 0.1084,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.46,
271
+ "learning_rate": 0.00019594929736144976,
272
+ "loss": 0.105,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.47,
277
+ "learning_rate": 0.0001957092602946671,
278
+ "loss": 0.1124,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.48,
283
+ "learning_rate": 0.00019546247005377065,
284
+ "loss": 0.1086,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.49,
289
+ "learning_rate": 0.0001952089440520959,
290
+ "loss": 0.111,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.5,
295
+ "learning_rate": 0.00019494870017824876,
296
+ "loss": 0.1109,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.51,
301
+ "learning_rate": 0.00019468175679484304,
302
+ "loss": 0.106,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.52,
307
+ "learning_rate": 0.00019440813273720504,
308
+ "loss": 0.1087,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.53,
313
+ "learning_rate": 0.0001941278473120445,
314
+ "loss": 0.1065,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.54,
319
+ "learning_rate": 0.0001938409202960922,
320
+ "loss": 0.1079,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.55,
325
+ "learning_rate": 0.00019354737193470466,
326
+ "loss": 0.1055,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.56,
331
+ "learning_rate": 0.00019324722294043558,
332
+ "loss": 0.1072,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.57,
337
+ "learning_rate": 0.00019294049449157448,
338
+ "loss": 0.1056,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.58,
343
+ "learning_rate": 0.00019262720823065216,
344
+ "loss": 0.1073,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.59,
349
+ "learning_rate": 0.0001923073862629139,
350
+ "loss": 0.1075,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.6,
355
+ "learning_rate": 0.00019198105115475947,
356
+ "loss": 0.0995,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.61,
361
+ "learning_rate": 0.000191648225932151,
362
+ "loss": 0.0973,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.62,
367
+ "learning_rate": 0.00019130893407898834,
368
+ "loss": 0.1021,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.63,
373
+ "learning_rate": 0.00019096319953545185,
374
+ "loss": 0.1096,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.64,
379
+ "learning_rate": 0.0001906110466963134,
380
+ "loss": 0.1007,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.65,
385
+ "learning_rate": 0.00019025250040921506,
386
+ "loss": 0.1003,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.66,
391
+ "learning_rate": 0.00018988758597291577,
392
+ "loss": 0.0959,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.68,
397
+ "learning_rate": 0.00018951632913550626,
398
+ "loss": 0.0996,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.69,
403
+ "learning_rate": 0.00018913875609259247,
404
+ "loss": 0.0965,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.7,
409
+ "learning_rate": 0.00018875489348544705,
410
+ "loss": 0.1011,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.71,
415
+ "learning_rate": 0.00018836476839912967,
416
+ "loss": 0.0966,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.72,
421
+ "learning_rate": 0.00018796840836057577,
422
+ "loss": 0.0967,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.73,
427
+ "learning_rate": 0.00018756584133665448,
428
+ "loss": 0.1003,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.74,
433
+ "learning_rate": 0.00018715709573219506,
434
+ "loss": 0.1006,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.75,
439
+ "learning_rate": 0.00018674220038798298,
440
+ "loss": 0.0962,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.76,
445
+ "learning_rate": 0.00018632118457872463,
446
+ "loss": 0.0996,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.77,
451
+ "learning_rate": 0.0001858940780109819,
452
+ "loss": 0.101,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.78,
457
+ "learning_rate": 0.0001854609108210761,
458
+ "loss": 0.1049,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.79,
463
+ "learning_rate": 0.00018502171357296144,
464
+ "loss": 0.1,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.8,
469
+ "learning_rate": 0.00018457651725606861,
470
+ "loss": 0.0975,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.81,
475
+ "learning_rate": 0.00018412535328311814,
476
+ "loss": 0.0959,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.82,
481
+ "learning_rate": 0.00018366825348790388,
482
+ "loss": 0.0936,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.83,
487
+ "learning_rate": 0.00018320525012304685,
488
+ "loss": 0.0956,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.84,
493
+ "learning_rate": 0.00018273637585771964,
494
+ "loss": 0.1004,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.85,
499
+ "learning_rate": 0.00018226166377534114,
500
+ "loss": 0.0964,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.86,
505
+ "learning_rate": 0.00018178114737124224,
506
+ "loss": 0.0974,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.87,
511
+ "learning_rate": 0.00018129486055030257,
512
+ "loss": 0.0963,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.88,
517
+ "learning_rate": 0.0001808028376245579,
518
+ "loss": 0.0973,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.89,
523
+ "learning_rate": 0.00018030511331077945,
524
+ "loss": 0.0959,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.9,
529
+ "learning_rate": 0.000179801722728024,
530
+ "loss": 0.0941,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.91,
535
+ "learning_rate": 0.00017929270139515604,
536
+ "loss": 0.095,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.92,
541
+ "learning_rate": 0.00017877808522834173,
542
+ "loss": 0.0992,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.94,
547
+ "learning_rate": 0.0001782579105385145,
548
+ "loss": 0.0912,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.95,
553
+ "learning_rate": 0.00017773221402881295,
554
+ "loss": 0.0943,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.96,
559
+ "learning_rate": 0.0001772010327919912,
560
+ "loss": 0.0959,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.97,
565
+ "learning_rate": 0.0001766644043078017,
566
+ "loss": 0.0972,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.98,
571
+ "learning_rate": 0.0001761223664403505,
572
+ "loss": 0.0933,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.99,
577
+ "learning_rate": 0.00017557495743542585,
578
+ "loss": 0.0947,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 1.0,
583
+ "learning_rate": 0.0001750222159177993,
584
+ "loss": 0.0958,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 1.01,
589
+ "learning_rate": 0.00017446418088850067,
590
+ "loss": 0.0981,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 1.01,
595
+ "learning_rate": 0.00017390089172206592,
596
+ "loss": 0.0952,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 1.02,
601
+ "learning_rate": 0.00017333238816375906,
602
+ "loss": 0.0894,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 1.03,
607
+ "learning_rate": 0.0001727587103267677,
608
+ "loss": 0.092,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 1.04,
613
+ "learning_rate": 0.00017217989868937265,
614
+ "loss": 0.0908,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 1.05,
619
+ "learning_rate": 0.00017159599409209193,
620
+ "loss": 0.0902,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 1.06,
625
+ "learning_rate": 0.000171007037734799,
626
+ "loss": 0.0903,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 1.07,
631
+ "learning_rate": 0.0001704130711738157,
632
+ "loss": 0.0844,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 1.08,
637
+ "learning_rate": 0.00016981413631898012,
638
+ "loss": 0.0901,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 1.09,
643
+ "learning_rate": 0.0001692102754306895,
644
+ "loss": 0.0923,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 1.1,
649
+ "learning_rate": 0.00016860153111691832,
650
+ "loss": 0.0893,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 1.11,
655
+ "learning_rate": 0.00016798794633021192,
656
+ "loss": 0.0946,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 1.12,
661
+ "learning_rate": 0.00016736956436465573,
662
+ "loss": 0.0911,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 1.13,
667
+ "learning_rate": 0.0001667464288528207,
668
+ "loss": 0.0919,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 1.14,
673
+ "learning_rate": 0.0001661185837626843,
674
+ "loss": 0.0921,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 1.15,
679
+ "learning_rate": 0.00016548607339452853,
680
+ "loss": 0.0897,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 1.16,
685
+ "learning_rate": 0.00016484894237781371,
686
+ "loss": 0.0938,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 1.17,
691
+ "learning_rate": 0.00016420723566802983,
692
+ "loss": 0.0883,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 1.18,
697
+ "learning_rate": 0.00016356099854352433,
698
+ "loss": 0.0937,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 1.19,
703
+ "learning_rate": 0.00016291027660230733,
704
+ "loss": 0.0939,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 1.2,
709
+ "learning_rate": 0.00016225511575883433,
710
+ "loss": 0.0912,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 1.21,
715
+ "learning_rate": 0.00016159556224076637,
716
+ "loss": 0.0894,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 1.22,
721
+ "learning_rate": 0.00016093166258570845,
722
+ "loss": 0.0858,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 1.23,
727
+ "learning_rate": 0.00016026346363792567,
728
+ "loss": 0.0875,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 1.24,
733
+ "learning_rate": 0.000159591012545038,
734
+ "loss": 0.0917,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 1.25,
739
+ "learning_rate": 0.00015891435675469376,
740
+ "loss": 0.0932,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 1.26,
745
+ "learning_rate": 0.0001582335440112214,
746
+ "loss": 0.0908,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 1.28,
751
+ "learning_rate": 0.000157548622352261,
752
+ "loss": 0.0913,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 1.29,
757
+ "learning_rate": 0.00015685964010537465,
758
+ "loss": 0.0875,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 1.3,
763
+ "learning_rate": 0.00015616664588463647,
764
+ "loss": 0.0863,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 1.31,
769
+ "learning_rate": 0.00015546968858720246,
770
+ "loss": 0.0896,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 1.32,
775
+ "learning_rate": 0.00015476881738986037,
776
+ "loss": 0.0853,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 1.33,
781
+ "learning_rate": 0.00015406408174555976,
782
+ "loss": 0.0894,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 1.34,
787
+ "learning_rate": 0.00015335553137992285,
788
+ "loss": 0.0855,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 1.35,
793
+ "learning_rate": 0.0001526432162877356,
794
+ "loss": 0.0867,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 1.36,
799
+ "learning_rate": 0.0001519271867294203,
800
+ "loss": 0.0895,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 1.37,
805
+ "learning_rate": 0.00015120749322748925,
806
+ "loss": 0.0873,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 1.38,
811
+ "learning_rate": 0.0001504841865629799,
812
+ "loss": 0.0898,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 1.39,
817
+ "learning_rate": 0.0001497573177718716,
818
+ "loss": 0.09,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 1.4,
823
+ "learning_rate": 0.0001490269381414849,
824
+ "loss": 0.086,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 1.41,
829
+ "learning_rate": 0.00014829309920686245,
830
+ "loss": 0.0878,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 1.42,
835
+ "learning_rate": 0.0001475558527471329,
836
+ "loss": 0.088,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 1.43,
841
+ "learning_rate": 0.00014681525078185715,
842
+ "loss": 0.0832,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 1.44,
847
+ "learning_rate": 0.00014607134556735834,
848
+ "loss": 0.0925,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 1.45,
853
+ "learning_rate": 0.00014532418959303423,
854
+ "loss": 0.0909,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 1.46,
859
+ "learning_rate": 0.00014457383557765386,
860
+ "loss": 0.0909,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 1.47,
865
+ "learning_rate": 0.00014382033646563754,
866
+ "loss": 0.0915,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 1.48,
871
+ "learning_rate": 0.00014306374542332143,
872
+ "loss": 0.0911,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 1.49,
877
+ "learning_rate": 0.0001423041158352058,
878
+ "loss": 0.0845,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 1.5,
883
+ "learning_rate": 0.00014154150130018866,
884
+ "loss": 0.0863,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 1.51,
889
+ "learning_rate": 0.00014077595562778347,
890
+ "loss": 0.0882,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 1.52,
895
+ "learning_rate": 0.00014000753283432266,
896
+ "loss": 0.0874,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 1.54,
901
+ "learning_rate": 0.00013923628713914617,
902
+ "loss": 0.0864,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 1.55,
907
+ "learning_rate": 0.00013846227296077568,
908
+ "loss": 0.092,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 1.56,
913
+ "learning_rate": 0.00013768554491307516,
914
+ "loss": 0.0887,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 1.57,
919
+ "learning_rate": 0.000136906157801397,
920
+ "loss": 0.0889,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 1.58,
925
+ "learning_rate": 0.00013612416661871533,
926
+ "loss": 0.0865,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 1.59,
931
+ "learning_rate": 0.0001353396265417454,
932
+ "loss": 0.0865,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 1.6,
937
+ "learning_rate": 0.00013455259292705071,
938
+ "loss": 0.0845,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 1.61,
943
+ "learning_rate": 0.00013376312130713687,
944
+ "loss": 0.0908,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 1.62,
949
+ "learning_rate": 0.0001329712673865333,
950
+ "loss": 0.0902,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 1.63,
955
+ "learning_rate": 0.0001321770870378628,
956
+ "loss": 0.0867,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 1.64,
961
+ "learning_rate": 0.00013138063629789922,
962
+ "loss": 0.0899,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 1.65,
967
+ "learning_rate": 0.00013058197136361343,
968
+ "loss": 0.0893,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 1.66,
973
+ "learning_rate": 0.00012978114858820834,
974
+ "loss": 0.086,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 1.67,
979
+ "learning_rate": 0.00012897822447714247,
980
+ "loss": 0.0853,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 1.68,
985
+ "learning_rate": 0.00012817325568414297,
986
+ "loss": 0.0844,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 1.69,
991
+ "learning_rate": 0.0001273662990072083,
992
+ "loss": 0.0905,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 1.7,
997
+ "learning_rate": 0.00012655741138460045,
998
+ "loss": 0.0856,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 1.71,
1003
+ "learning_rate": 0.00012574664989082758,
1004
+ "loss": 0.0896,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 1.72,
1009
+ "learning_rate": 0.00012493407173261675,
1010
+ "loss": 0.0843,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 1.73,
1015
+ "learning_rate": 0.0001241197342448775,
1016
+ "loss": 0.0869,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 1.74,
1021
+ "learning_rate": 0.00012330369488665647,
1022
+ "loss": 0.0889,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 1.75,
1027
+ "learning_rate": 0.0001224860112370828,
1028
+ "loss": 0.089,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 1.76,
1033
+ "learning_rate": 0.00012166674099130577,
1034
+ "loss": 0.0901,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 1.77,
1039
+ "learning_rate": 0.00012084594195642367,
1040
+ "loss": 0.0882,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 1.78,
1045
+ "learning_rate": 0.00012002367204740496,
1046
+ "loss": 0.085,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.79,
1051
+ "learning_rate": 0.00011919998928300203,
1052
+ "loss": 0.0865,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.81,
1057
+ "learning_rate": 0.00011837495178165706,
1058
+ "loss": 0.083,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.82,
1063
+ "learning_rate": 0.00011754861775740162,
1064
+ "loss": 0.0919,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.83,
1069
+ "learning_rate": 0.00011672104551574896,
1070
+ "loss": 0.0853,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.84,
1075
+ "learning_rate": 0.00011589229344957999,
1076
+ "loss": 0.0898,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.85,
1081
+ "learning_rate": 0.0001150624200350232,
1082
+ "loss": 0.085,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.86,
1087
+ "learning_rate": 0.00011423148382732853,
1088
+ "loss": 0.0881,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.87,
1093
+ "learning_rate": 0.00011339954345673582,
1094
+ "loss": 0.0909,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.88,
1099
+ "learning_rate": 0.00011256665762433798,
1100
+ "loss": 0.0815,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.89,
1105
+ "learning_rate": 0.00011173288509793889,
1106
+ "loss": 0.0858,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.9,
1111
+ "learning_rate": 0.00011089828470790693,
1112
+ "loss": 0.0825,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.91,
1117
+ "learning_rate": 0.00011006291534302402,
1118
+ "loss": 0.0838,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.92,
1123
+ "learning_rate": 0.00010922683594633021,
1124
+ "loss": 0.0863,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.93,
1129
+ "learning_rate": 0.00010839010551096498,
1130
+ "loss": 0.0871,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.94,
1135
+ "learning_rate": 0.00010755278307600458,
1136
+ "loss": 0.0825,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.95,
1141
+ "learning_rate": 0.00010671492772229628,
1142
+ "loss": 0.0886,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.96,
1147
+ "learning_rate": 0.0001058765985682898,
1148
+ "loss": 0.0851,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.97,
1153
+ "learning_rate": 0.00010503785476586569,
1154
+ "loss": 0.087,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.98,
1159
+ "learning_rate": 0.00010419875549616196,
1160
+ "loss": 0.0863,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.99,
1165
+ "learning_rate": 0.00010335935996539802,
1166
+ "loss": 0.0833,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 2.0,
1171
+ "learning_rate": 0.00010251972740069724,
1172
+ "loss": 0.0884,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 2.01,
1177
+ "learning_rate": 0.00010167991704590803,
1178
+ "loss": 0.0871,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 2.01,
1183
+ "learning_rate": 0.00010083998815742335,
1184
+ "loss": 0.083,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 2.02,
1189
+ "learning_rate": 0.0001,
1190
+ "loss": 0.0843,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 2.03,
1195
+ "learning_rate": 9.916001184257668e-05,
1196
+ "loss": 0.0812,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 2.04,
1201
+ "learning_rate": 9.8320082954092e-05,
1202
+ "loss": 0.0861,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 2.05,
1207
+ "learning_rate": 9.748027259930276e-05,
1208
+ "loss": 0.0803,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 2.06,
1213
+ "learning_rate": 9.6640640034602e-05,
1214
+ "loss": 0.0833,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 2.07,
1219
+ "learning_rate": 9.580124450383803e-05,
1220
+ "loss": 0.0819,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 2.08,
1225
+ "learning_rate": 9.496214523413432e-05,
1226
+ "loss": 0.0833,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 2.09,
1231
+ "learning_rate": 9.412340143171024e-05,
1232
+ "loss": 0.0803,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 2.1,
1237
+ "learning_rate": 9.328507227770375e-05,
1238
+ "loss": 0.0816,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 2.11,
1243
+ "learning_rate": 9.244721692399545e-05,
1244
+ "loss": 0.085,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 2.12,
1249
+ "learning_rate": 9.160989448903504e-05,
1250
+ "loss": 0.0806,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 2.14,
1255
+ "learning_rate": 9.077316405366981e-05,
1256
+ "loss": 0.0843,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 2.15,
1261
+ "learning_rate": 8.993708465697599e-05,
1262
+ "loss": 0.0817,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 2.16,
1267
+ "learning_rate": 8.910171529209305e-05,
1268
+ "loss": 0.0866,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 2.17,
1273
+ "learning_rate": 8.826711490206113e-05,
1274
+ "loss": 0.0806,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 2.18,
1279
+ "learning_rate": 8.743334237566202e-05,
1280
+ "loss": 0.0818,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 2.19,
1285
+ "learning_rate": 8.66004565432642e-05,
1286
+ "loss": 0.0847,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 2.2,
1291
+ "learning_rate": 8.57685161726715e-05,
1292
+ "loss": 0.0813,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 2.21,
1297
+ "learning_rate": 8.493757996497683e-05,
1298
+ "loss": 0.0817,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 2.22,
1303
+ "learning_rate": 8.410770655042003e-05,
1304
+ "loss": 0.0838,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 2.23,
1309
+ "learning_rate": 8.327895448425105e-05,
1310
+ "loss": 0.0845,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 2.24,
1315
+ "learning_rate": 8.245138224259841e-05,
1316
+ "loss": 0.0816,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 2.25,
1321
+ "learning_rate": 8.162504821834295e-05,
1322
+ "loss": 0.0823,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 2.26,
1327
+ "learning_rate": 8.0800010716998e-05,
1328
+ "loss": 0.0847,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 2.27,
1333
+ "learning_rate": 7.997632795259503e-05,
1334
+ "loss": 0.0808,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 2.28,
1339
+ "learning_rate": 7.915405804357633e-05,
1340
+ "loss": 0.0844,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 2.29,
1345
+ "learning_rate": 7.833325900869428e-05,
1346
+ "loss": 0.0838,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 2.3,
1351
+ "learning_rate": 7.751398876291725e-05,
1352
+ "loss": 0.0855,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 2.31,
1357
+ "learning_rate": 7.669630511334358e-05,
1358
+ "loss": 0.0813,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 2.32,
1363
+ "learning_rate": 7.588026575512251e-05,
1364
+ "loss": 0.0825,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 2.33,
1369
+ "learning_rate": 7.506592826738326e-05,
1370
+ "loss": 0.078,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 2.34,
1375
+ "learning_rate": 7.425335010917244e-05,
1376
+ "loss": 0.0823,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 2.35,
1381
+ "learning_rate": 7.344258861539956e-05,
1382
+ "loss": 0.0816,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 2.36,
1387
+ "learning_rate": 7.263370099279172e-05,
1388
+ "loss": 0.0823,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 2.37,
1393
+ "learning_rate": 7.182674431585704e-05,
1394
+ "loss": 0.08,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 2.38,
1399
+ "learning_rate": 7.102177552285753e-05,
1400
+ "loss": 0.0831,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 2.39,
1405
+ "learning_rate": 7.021885141179165e-05,
1406
+ "loss": 0.0856,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 2.41,
1411
+ "learning_rate": 6.941802863638659e-05,
1412
+ "loss": 0.079,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 2.42,
1417
+ "learning_rate": 6.861936370210083e-05,
1418
+ "loss": 0.0809,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 2.43,
1423
+ "learning_rate": 6.782291296213722e-05,
1424
+ "loss": 0.0803,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 2.44,
1429
+ "learning_rate": 6.70287326134667e-05,
1430
+ "loss": 0.0829,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 2.45,
1435
+ "learning_rate": 6.623687869286313e-05,
1436
+ "loss": 0.0808,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 2.46,
1441
+ "learning_rate": 6.54474070729493e-05,
1442
+ "loss": 0.0835,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 2.47,
1447
+ "learning_rate": 6.466037345825462e-05,
1448
+ "loss": 0.0845,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 2.48,
1453
+ "learning_rate": 6.387583338128471e-05,
1454
+ "loss": 0.076,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 2.49,
1459
+ "learning_rate": 6.309384219860301e-05,
1460
+ "loss": 0.0863,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 2.5,
1465
+ "learning_rate": 6.231445508692485e-05,
1466
+ "loss": 0.0817,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 2.51,
1471
+ "learning_rate": 6.153772703922433e-05,
1472
+ "loss": 0.0786,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 2.52,
1477
+ "learning_rate": 6.076371286085387e-05,
1478
+ "loss": 0.0838,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 2.53,
1483
+ "learning_rate": 5.999246716567737e-05,
1484
+ "loss": 0.0845,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 2.54,
1489
+ "learning_rate": 5.9224044372216534e-05,
1490
+ "loss": 0.0805,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 2.55,
1495
+ "learning_rate": 5.845849869981137e-05,
1496
+ "loss": 0.0859,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 2.56,
1501
+ "learning_rate": 5.7695884164794225e-05,
1502
+ "loss": 0.0842,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 2.57,
1507
+ "learning_rate": 5.693625457667862e-05,
1508
+ "loss": 0.0803,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 2.58,
1513
+ "learning_rate": 5.6179663534362504e-05,
1514
+ "loss": 0.0785,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 2.59,
1519
+ "learning_rate": 5.542616442234618e-05,
1520
+ "loss": 0.0833,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 2.6,
1525
+ "learning_rate": 5.4675810406965765e-05,
1526
+ "loss": 0.0801,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 2.61,
1531
+ "learning_rate": 5.392865443264163e-05,
1532
+ "loss": 0.0867,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 2.62,
1537
+ "learning_rate": 5.318474921814289e-05,
1538
+ "loss": 0.0798,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 2.63,
1543
+ "learning_rate": 5.244414725286717e-05,
1544
+ "loss": 0.0819,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 2.64,
1549
+ "learning_rate": 5.170690079313756e-05,
1550
+ "loss": 0.0822,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 2.65,
1555
+ "learning_rate": 5.0973061858515145e-05,
1556
+ "loss": 0.0815,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 2.66,
1561
+ "learning_rate": 5.024268222812843e-05,
1562
+ "loss": 0.083,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 2.68,
1567
+ "learning_rate": 4.9515813437020144e-05,
1568
+ "loss": 0.0814,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 2.69,
1573
+ "learning_rate": 4.879250677251077e-05,
1574
+ "loss": 0.0795,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 2.7,
1579
+ "learning_rate": 4.807281327057972e-05,
1580
+ "loss": 0.0806,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 2.71,
1585
+ "learning_rate": 4.735678371226441e-05,
1586
+ "loss": 0.0825,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 2.72,
1591
+ "learning_rate": 4.6644468620077174e-05,
1592
+ "loss": 0.0783,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 2.73,
1597
+ "learning_rate": 4.593591825444028e-05,
1598
+ "loss": 0.0787,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 2.74,
1603
+ "learning_rate": 4.523118261013969e-05,
1604
+ "loss": 0.0798,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 2.75,
1609
+ "learning_rate": 4.4530311412797576e-05,
1610
+ "loss": 0.0857,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 2.76,
1615
+ "learning_rate": 4.383335411536357e-05,
1616
+ "loss": 0.0834,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 2.77,
1621
+ "learning_rate": 4.314035989462535e-05,
1622
+ "loss": 0.0858,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 2.78,
1627
+ "learning_rate": 4.2451377647738985e-05,
1628
+ "loss": 0.0791,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 2.79,
1633
+ "learning_rate": 4.1766455988778616e-05,
1634
+ "loss": 0.0806,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 2.8,
1639
+ "learning_rate": 4.108564324530626e-05,
1640
+ "loss": 0.0777,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 2.81,
1645
+ "learning_rate": 4.0408987454961986e-05,
1646
+ "loss": 0.0812,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 2.82,
1651
+ "learning_rate": 3.973653636207437e-05,
1652
+ "loss": 0.0776,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 2.83,
1657
+ "learning_rate": 3.90683374142916e-05,
1658
+ "loss": 0.0779,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 2.84,
1663
+ "learning_rate": 3.840443775923365e-05,
1664
+ "loss": 0.0801,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 2.85,
1669
+ "learning_rate": 3.774488424116569e-05,
1670
+ "loss": 0.081,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 2.86,
1675
+ "learning_rate": 3.70897233976927e-05,
1676
+ "loss": 0.0794,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 2.87,
1681
+ "learning_rate": 3.6439001456475695e-05,
1682
+ "loss": 0.0801,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 2.88,
1687
+ "learning_rate": 3.5792764331970185e-05,
1688
+ "loss": 0.0789,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 2.89,
1693
+ "learning_rate": 3.5151057622186336e-05,
1694
+ "loss": 0.0801,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 2.9,
1699
+ "learning_rate": 3.45139266054715e-05,
1700
+ "loss": 0.0769,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 2.91,
1705
+ "learning_rate": 3.3881416237315675e-05,
1706
+ "loss": 0.0794,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 2.92,
1711
+ "learning_rate": 3.325357114717933e-05,
1712
+ "loss": 0.0819,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 2.94,
1717
+ "learning_rate": 3.263043563534428e-05,
1718
+ "loss": 0.0761,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 2.95,
1723
+ "learning_rate": 3.2012053669788135e-05,
1724
+ "loss": 0.0796,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 2.96,
1729
+ "learning_rate": 3.139846888308169e-05,
1730
+ "loss": 0.0799,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 2.97,
1735
+ "learning_rate": 3.078972456931053e-05,
1736
+ "loss": 0.0787,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 2.98,
1741
+ "learning_rate": 3.0185863681019898e-05,
1742
+ "loss": 0.0784,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 2.99,
1747
+ "learning_rate": 2.9586928826184325e-05,
1748
+ "loss": 0.0812,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 3.0,
1753
+ "learning_rate": 2.899296226520103e-05,
1754
+ "loss": 0.0797,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 3.01,
1759
+ "learning_rate": 2.8404005907908082e-05,
1760
+ "loss": 0.0807,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 3.01,
1765
+ "learning_rate": 2.7820101310627356e-05,
1766
+ "loss": 0.0774,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 3.02,
1771
+ "learning_rate": 2.724128967323234e-05,
1772
+ "loss": 0.0775,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 3.03,
1777
+ "learning_rate": 2.6667611836240947e-05,
1778
+ "loss": 0.0748,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 3.04,
1783
+ "learning_rate": 2.6099108277934103e-05,
1784
+ "loss": 0.0768,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 3.05,
1789
+ "learning_rate": 2.5535819111499347e-05,
1790
+ "loss": 0.0833,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 3.06,
1795
+ "learning_rate": 2.497778408220073e-05,
1796
+ "loss": 0.0767,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 3.07,
1801
+ "learning_rate": 2.4425042564574184e-05,
1802
+ "loss": 0.0738,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 3.08,
1807
+ "learning_rate": 2.3877633559649505e-05,
1808
+ "loss": 0.0791,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 3.09,
1813
+ "learning_rate": 2.3335595692198344e-05,
1814
+ "loss": 0.0813,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 3.1,
1819
+ "learning_rate": 2.2798967208008804e-05,
1820
+ "loss": 0.0805,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 3.11,
1825
+ "learning_rate": 2.2267785971187062e-05,
1826
+ "loss": 0.0794,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 3.12,
1831
+ "learning_rate": 2.1742089461485504e-05,
1832
+ "loss": 0.0818,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 3.13,
1837
+ "learning_rate": 2.122191477165826e-05,
1838
+ "loss": 0.0771,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 3.14,
1843
+ "learning_rate": 2.070729860484396e-05,
1844
+ "loss": 0.0778,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 3.15,
1849
+ "learning_rate": 2.0198277271976052e-05,
1850
+ "loss": 0.0812,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 3.16,
1855
+ "learning_rate": 1.9694886689220594e-05,
1856
+ "loss": 0.0796,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 3.17,
1861
+ "learning_rate": 1.91971623754421e-05,
1862
+ "loss": 0.0823,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 3.18,
1867
+ "learning_rate": 1.870513944969743e-05,
1868
+ "loss": 0.0803,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 3.19,
1873
+ "learning_rate": 1.8218852628757756e-05,
1874
+ "loss": 0.074,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 3.2,
1879
+ "learning_rate": 1.7738336224658882e-05,
1880
+ "loss": 0.0751,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 3.21,
1885
+ "learning_rate": 1.7263624142280377e-05,
1886
+ "loss": 0.0759,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 3.22,
1891
+ "learning_rate": 1.6794749876953188e-05,
1892
+ "loss": 0.0784,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 3.23,
1897
+ "learning_rate": 1.6331746512096158e-05,
1898
+ "loss": 0.0794,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 3.24,
1903
+ "learning_rate": 1.587464671688187e-05,
1904
+ "loss": 0.0738,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 3.25,
1909
+ "learning_rate": 1.5423482743931405e-05,
1910
+ "loss": 0.077,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 3.26,
1915
+ "learning_rate": 1.4978286427038601e-05,
1916
+ "loss": 0.077,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 3.28,
1921
+ "learning_rate": 1.4539089178923937e-05,
1922
+ "loss": 0.0798,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 3.29,
1927
+ "learning_rate": 1.4105921989018111e-05,
1928
+ "loss": 0.0748,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 3.3,
1933
+ "learning_rate": 1.3678815421275393e-05,
1934
+ "loss": 0.0757,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 3.31,
1939
+ "learning_rate": 1.325779961201703e-05,
1940
+ "loss": 0.0794,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 3.32,
1945
+ "learning_rate": 1.2842904267804934e-05,
1946
+ "loss": 0.0815,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 3.33,
1951
+ "learning_rate": 1.2434158663345552e-05,
1952
+ "loss": 0.0771,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 3.34,
1957
+ "learning_rate": 1.2031591639424234e-05,
1958
+ "loss": 0.0778,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 3.35,
1963
+ "learning_rate": 1.1635231600870333e-05,
1964
+ "loss": 0.0747,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 3.36,
1969
+ "learning_rate": 1.1245106514552973e-05,
1970
+ "loss": 0.0766,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 3.37,
1975
+ "learning_rate": 1.086124390740757e-05,
1976
+ "loss": 0.0773,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 3.38,
1981
+ "learning_rate": 1.0483670864493778e-05,
1982
+ "loss": 0.0801,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 3.39,
1987
+ "learning_rate": 1.0112414027084261e-05,
1988
+ "loss": 0.0767,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 3.4,
1993
+ "learning_rate": 9.747499590784937e-06,
1994
+ "loss": 0.0773,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 3.41,
1999
+ "learning_rate": 9.388953303686588e-06,
2000
+ "loss": 0.0782,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 3.42,
2005
+ "learning_rate": 9.036800464548157e-06,
2006
+ "loss": 0.0754,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 3.43,
2011
+ "learning_rate": 8.691065921011687e-06,
2012
+ "loss": 0.0787,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 3.44,
2017
+ "learning_rate": 8.351774067849005e-06,
2018
+ "loss": 0.0777,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 3.45,
2023
+ "learning_rate": 8.018948845240538e-06,
2024
+ "loss": 0.0786,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 3.46,
2029
+ "learning_rate": 7.692613737086108e-06,
2030
+ "loss": 0.0791,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 3.47,
2035
+ "learning_rate": 7.372791769347842e-06,
2036
+ "loss": 0.0802,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 3.48,
2041
+ "learning_rate": 7.059505508425535e-06,
2042
+ "loss": 0.0774,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 3.49,
2047
+ "learning_rate": 6.75277705956443e-06,
2048
+ "loss": 0.079,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 3.5,
2053
+ "learning_rate": 6.452628065295374e-06,
2054
+ "loss": 0.0749,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 3.51,
2059
+ "learning_rate": 6.159079703907822e-06,
2060
+ "loss": 0.0767,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 3.52,
2065
+ "learning_rate": 5.872152687955523e-06,
2066
+ "loss": 0.0806,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 3.54,
2071
+ "learning_rate": 5.59186726279497e-06,
2072
+ "loss": 0.0803,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 3.55,
2077
+ "learning_rate": 5.318243205156981e-06,
2078
+ "loss": 0.0761,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 3.56,
2083
+ "learning_rate": 5.051299821751254e-06,
2084
+ "loss": 0.0784,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 3.57,
2089
+ "learning_rate": 4.791055947904099e-06,
2090
+ "loss": 0.0782,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 3.58,
2095
+ "learning_rate": 4.537529946229368e-06,
2096
+ "loss": 0.0813,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 3.59,
2101
+ "learning_rate": 4.290739705332902e-06,
2102
+ "loss": 0.0783,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 3.6,
2107
+ "learning_rate": 4.050702638550275e-06,
2108
+ "loss": 0.0745,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 3.61,
2113
+ "learning_rate": 3.817435682718096e-06,
2114
+ "loss": 0.0802,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 3.62,
2119
+ "learning_rate": 3.590955296979037e-06,
2120
+ "loss": 0.0805,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 3.63,
2125
+ "learning_rate": 3.3712774616204145e-06,
2126
+ "loss": 0.0799,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 3.64,
2131
+ "learning_rate": 3.1584176769466346e-06,
2132
+ "loss": 0.0769,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 3.65,
2137
+ "learning_rate": 2.952390962185558e-06,
2138
+ "loss": 0.0766,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 3.66,
2143
+ "learning_rate": 2.7532118544287276e-06,
2144
+ "loss": 0.0758,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 3.67,
2149
+ "learning_rate": 2.5608944076055964e-06,
2150
+ "loss": 0.0764,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 3.68,
2155
+ "learning_rate": 2.3754521914919668e-06,
2156
+ "loss": 0.0786,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 3.69,
2161
+ "learning_rate": 2.1968982907524804e-06,
2162
+ "loss": 0.0743,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 3.7,
2167
+ "learning_rate": 2.0252453040173647e-06,
2168
+ "loss": 0.0792,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 3.71,
2173
+ "learning_rate": 1.8605053429935016e-06,
2174
+ "loss": 0.0771,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 3.72,
2179
+ "learning_rate": 1.7026900316098215e-06,
2180
+ "loss": 0.0746,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 3.73,
2185
+ "learning_rate": 1.5518105051971598e-06,
2186
+ "loss": 0.0746,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 3.74,
2191
+ "learning_rate": 1.407877409702496e-06,
2192
+ "loss": 0.0768,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 3.75,
2197
+ "learning_rate": 1.2709009009378436e-06,
2198
+ "loss": 0.0769,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 3.76,
2203
+ "learning_rate": 1.1408906438636236e-06,
2204
+ "loss": 0.0739,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 3.77,
2209
+ "learning_rate": 1.0178558119067315e-06,
2210
+ "loss": 0.076,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 3.78,
2215
+ "learning_rate": 9.018050863132565e-07,
2216
+ "loss": 0.081,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 3.79,
2221
+ "learning_rate": 7.927466555359808e-07,
2222
+ "loss": 0.0778,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 3.81,
2227
+ "learning_rate": 6.906882146565096e-07,
2228
+ "loss": 0.0734,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 3.82,
2233
+ "learning_rate": 5.956369648424276e-07,
2234
+ "loss": 0.0801,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 3.83,
2239
+ "learning_rate": 5.075996128391158e-07,
2240
+ "loss": 0.0802,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 3.84,
2245
+ "learning_rate": 4.2658237049655323e-07,
2246
+ "loss": 0.0786,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 3.85,
2251
+ "learning_rate": 3.525909543310002e-07,
2252
+ "loss": 0.0822,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 3.86,
2257
+ "learning_rate": 2.856305851216878e-07,
2258
+ "loss": 0.0755,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 3.87,
2263
+ "learning_rate": 2.2570598754237947e-07,
2264
+ "loss": 0.0779,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 3.88,
2269
+ "learning_rate": 1.728213898280373e-07,
2270
+ "loss": 0.0778,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 3.89,
2275
+ "learning_rate": 1.2698052347649426e-07,
2276
+ "loss": 0.0772,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 3.9,
2281
+ "learning_rate": 8.818662298512025e-08,
2282
+ "loss": 0.0826,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 3.91,
2287
+ "learning_rate": 5.644242562264923e-08,
2288
+ "loss": 0.0769,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 3.92,
2293
+ "learning_rate": 3.175017123598911e-08,
2294
+ "loss": 0.0774,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 3.93,
2299
+ "learning_rate": 1.4111602092226062e-08,
2300
+ "loss": 0.0768,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 3.94,
2305
+ "learning_rate": 3.5279627556672467e-09,
2306
+ "loss": 0.0787,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 3.95,
2311
+ "learning_rate": 0.0,
2312
+ "loss": 0.0787,
2313
+ "step": 384
2314
+ }
2315
+ ],
2316
+ "logging_steps": 1,
2317
+ "max_steps": 384,
2318
+ "num_input_tokens_seen": 0,
2319
+ "num_train_epochs": 4,
2320
+ "save_steps": 96,
2321
+ "total_flos": 2.8144844549507777e+19,
2322
+ "train_batch_size": 2,
2323
+ "trial_name": null,
2324
+ "trial_params": null
2325
+ }
checkpoint-384/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12beba6580debef350132c689cb747c91282ee11c5990b44305f48ba18424e41
3
+ size 4923
checkpoint-96/README.md ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ## Training procedure
201
+
202
+ The following `bitsandbytes` quantization config was used during training:
203
+ - quant_method: QuantizationMethod.BITS_AND_BYTES
204
+ - load_in_8bit: False
205
+ - load_in_4bit: True
206
+ - llm_int8_threshold: 6.0
207
+ - llm_int8_skip_modules: None
208
+ - llm_int8_enable_fp32_cpu_offload: False
209
+ - llm_int8_has_fp16_weight: False
210
+ - bnb_4bit_quant_type: nf4
211
+ - bnb_4bit_use_double_quant: True
212
+ - bnb_4bit_compute_dtype: bfloat16
213
+
214
+ ### Framework versions
215
+
216
+ - PEFT 0.7.0
checkpoint-96/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj",
24
+ "o_proj",
25
+ "k_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-96/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a779a058867d30264897505af99a1d2bf96af9066f64dd7c18c723813417b77
3
+ size 109086416
checkpoint-96/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4646b80030637ebb0c7bdde9a9db993856a5486137ded8267f71780885c06f
3
+ size 54936735
checkpoint-96/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a1e1d8689b57956b9c7f5094b312132a145315e482ceea699ac077604a9556c
3
+ size 15607
checkpoint-96/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e6d4db71f4be77e69c37c28139138ee2dda70ca66ec56dc33f869e0ecb4028
3
+ size 15607
checkpoint-96/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8027a0bb23c3c448a938d16463c2a0d39e6f707ead75bdf23fa0c42c60fd6e
3
+ size 627
checkpoint-96/trainer_state.json ADDED
@@ -0,0 +1,597 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9974025974025974,
5
+ "eval_steps": 500,
6
+ "global_step": 96,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2e-05,
14
+ "loss": 2.1617,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.1579,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "learning_rate": 6e-05,
26
+ "loss": 2.0917,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.04,
31
+ "learning_rate": 8e-05,
32
+ "loss": 1.8765,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.05,
37
+ "learning_rate": 0.0001,
38
+ "loss": 1.3302,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.06,
43
+ "learning_rate": 0.00012,
44
+ "loss": 0.9737,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.07,
49
+ "learning_rate": 0.00014,
50
+ "loss": 0.7302,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.08,
55
+ "learning_rate": 0.00016,
56
+ "loss": 0.534,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.09,
61
+ "learning_rate": 0.00018,
62
+ "loss": 0.4094,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.1,
67
+ "learning_rate": 0.0002,
68
+ "loss": 0.35,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.11,
73
+ "learning_rate": 0.00019999647203724434,
74
+ "loss": 0.3007,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.12,
79
+ "learning_rate": 0.00019998588839790777,
80
+ "loss": 0.2644,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.14,
85
+ "learning_rate": 0.000199968249828764,
86
+ "loss": 0.2454,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.15,
91
+ "learning_rate": 0.00019994355757437738,
92
+ "loss": 0.2029,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.16,
97
+ "learning_rate": 0.0001999118133770149,
98
+ "loss": 0.204,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.17,
103
+ "learning_rate": 0.00019987301947652352,
104
+ "loss": 0.1925,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.18,
109
+ "learning_rate": 0.00019982717861017198,
110
+ "loss": 0.184,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.19,
115
+ "learning_rate": 0.0001997742940124576,
116
+ "loss": 0.1639,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.2,
121
+ "learning_rate": 0.00019971436941487833,
122
+ "loss": 0.1655,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.21,
127
+ "learning_rate": 0.000199647409045669,
128
+ "loss": 0.1566,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.22,
133
+ "learning_rate": 0.00019957341762950344,
134
+ "loss": 0.1571,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.23,
139
+ "learning_rate": 0.0001994924003871609,
140
+ "loss": 0.1477,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.24,
145
+ "learning_rate": 0.0001994043630351576,
146
+ "loss": 0.1495,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.25,
151
+ "learning_rate": 0.0001993093117853435,
152
+ "loss": 0.1388,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.26,
157
+ "learning_rate": 0.00019920725334446405,
158
+ "loss": 0.1466,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.27,
163
+ "learning_rate": 0.00019909819491368676,
164
+ "loss": 0.141,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.28,
169
+ "learning_rate": 0.0001989821441880933,
170
+ "loss": 0.1315,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.29,
175
+ "learning_rate": 0.0001988591093561364,
176
+ "loss": 0.1354,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.3,
181
+ "learning_rate": 0.00019872909909906215,
182
+ "loss": 0.129,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.31,
187
+ "learning_rate": 0.00019859212259029752,
188
+ "loss": 0.1266,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.32,
193
+ "learning_rate": 0.00019844818949480285,
194
+ "loss": 0.1233,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.33,
199
+ "learning_rate": 0.0001982973099683902,
200
+ "loss": 0.121,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.34,
205
+ "learning_rate": 0.00019813949465700653,
206
+ "loss": 0.1284,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.35,
211
+ "learning_rate": 0.00019797475469598267,
212
+ "loss": 0.1266,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.36,
217
+ "learning_rate": 0.00019780310170924753,
218
+ "loss": 0.1218,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.37,
223
+ "learning_rate": 0.00019762454780850806,
224
+ "loss": 0.1264,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.38,
229
+ "learning_rate": 0.0001974391055923944,
230
+ "loss": 0.1191,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.39,
235
+ "learning_rate": 0.00019724678814557128,
236
+ "loss": 0.1173,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.41,
241
+ "learning_rate": 0.00019704760903781446,
242
+ "loss": 0.1128,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.42,
247
+ "learning_rate": 0.0001968415823230534,
248
+ "loss": 0.1113,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.43,
253
+ "learning_rate": 0.0001966287225383796,
254
+ "loss": 0.1087,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.44,
259
+ "learning_rate": 0.00019640904470302097,
260
+ "loss": 0.1163,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.45,
265
+ "learning_rate": 0.00019618256431728194,
266
+ "loss": 0.1084,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.46,
271
+ "learning_rate": 0.00019594929736144976,
272
+ "loss": 0.105,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.47,
277
+ "learning_rate": 0.0001957092602946671,
278
+ "loss": 0.1124,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.48,
283
+ "learning_rate": 0.00019546247005377065,
284
+ "loss": 0.1086,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.49,
289
+ "learning_rate": 0.0001952089440520959,
290
+ "loss": 0.111,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.5,
295
+ "learning_rate": 0.00019494870017824876,
296
+ "loss": 0.1109,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.51,
301
+ "learning_rate": 0.00019468175679484304,
302
+ "loss": 0.106,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.52,
307
+ "learning_rate": 0.00019440813273720504,
308
+ "loss": 0.1087,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.53,
313
+ "learning_rate": 0.0001941278473120445,
314
+ "loss": 0.1065,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.54,
319
+ "learning_rate": 0.0001938409202960922,
320
+ "loss": 0.1079,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.55,
325
+ "learning_rate": 0.00019354737193470466,
326
+ "loss": 0.1055,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.56,
331
+ "learning_rate": 0.00019324722294043558,
332
+ "loss": 0.1072,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.57,
337
+ "learning_rate": 0.00019294049449157448,
338
+ "loss": 0.1056,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.58,
343
+ "learning_rate": 0.00019262720823065216,
344
+ "loss": 0.1073,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.59,
349
+ "learning_rate": 0.0001923073862629139,
350
+ "loss": 0.1075,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.6,
355
+ "learning_rate": 0.00019198105115475947,
356
+ "loss": 0.0995,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.61,
361
+ "learning_rate": 0.000191648225932151,
362
+ "loss": 0.0973,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.62,
367
+ "learning_rate": 0.00019130893407898834,
368
+ "loss": 0.1021,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.63,
373
+ "learning_rate": 0.00019096319953545185,
374
+ "loss": 0.1096,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.64,
379
+ "learning_rate": 0.0001906110466963134,
380
+ "loss": 0.1007,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.65,
385
+ "learning_rate": 0.00019025250040921506,
386
+ "loss": 0.1003,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.66,
391
+ "learning_rate": 0.00018988758597291577,
392
+ "loss": 0.0959,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.68,
397
+ "learning_rate": 0.00018951632913550626,
398
+ "loss": 0.0996,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.69,
403
+ "learning_rate": 0.00018913875609259247,
404
+ "loss": 0.0965,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.7,
409
+ "learning_rate": 0.00018875489348544705,
410
+ "loss": 0.1011,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.71,
415
+ "learning_rate": 0.00018836476839912967,
416
+ "loss": 0.0966,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.72,
421
+ "learning_rate": 0.00018796840836057577,
422
+ "loss": 0.0967,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.73,
427
+ "learning_rate": 0.00018756584133665448,
428
+ "loss": 0.1003,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.74,
433
+ "learning_rate": 0.00018715709573219506,
434
+ "loss": 0.1006,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.75,
439
+ "learning_rate": 0.00018674220038798298,
440
+ "loss": 0.0962,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.76,
445
+ "learning_rate": 0.00018632118457872463,
446
+ "loss": 0.0996,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.77,
451
+ "learning_rate": 0.0001858940780109819,
452
+ "loss": 0.101,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.78,
457
+ "learning_rate": 0.0001854609108210761,
458
+ "loss": 0.1049,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.79,
463
+ "learning_rate": 0.00018502171357296144,
464
+ "loss": 0.1,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.8,
469
+ "learning_rate": 0.00018457651725606861,
470
+ "loss": 0.0975,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.81,
475
+ "learning_rate": 0.00018412535328311814,
476
+ "loss": 0.0959,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.82,
481
+ "learning_rate": 0.00018366825348790388,
482
+ "loss": 0.0936,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.83,
487
+ "learning_rate": 0.00018320525012304685,
488
+ "loss": 0.0956,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.84,
493
+ "learning_rate": 0.00018273637585771964,
494
+ "loss": 0.1004,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.85,
499
+ "learning_rate": 0.00018226166377534114,
500
+ "loss": 0.0964,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.86,
505
+ "learning_rate": 0.00018178114737124224,
506
+ "loss": 0.0974,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.87,
511
+ "learning_rate": 0.00018129486055030257,
512
+ "loss": 0.0963,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.88,
517
+ "learning_rate": 0.0001808028376245579,
518
+ "loss": 0.0973,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.89,
523
+ "learning_rate": 0.00018030511331077945,
524
+ "loss": 0.0959,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.9,
529
+ "learning_rate": 0.000179801722728024,
530
+ "loss": 0.0941,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.91,
535
+ "learning_rate": 0.00017929270139515604,
536
+ "loss": 0.095,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.92,
541
+ "learning_rate": 0.00017877808522834173,
542
+ "loss": 0.0992,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.94,
547
+ "learning_rate": 0.0001782579105385145,
548
+ "loss": 0.0912,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.95,
553
+ "learning_rate": 0.00017773221402881295,
554
+ "loss": 0.0943,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.96,
559
+ "learning_rate": 0.0001772010327919912,
560
+ "loss": 0.0959,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.97,
565
+ "learning_rate": 0.0001766644043078017,
566
+ "loss": 0.0972,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.98,
571
+ "learning_rate": 0.0001761223664403505,
572
+ "loss": 0.0933,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.99,
577
+ "learning_rate": 0.00017557495743542585,
578
+ "loss": 0.0947,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 1.0,
583
+ "learning_rate": 0.0001750222159177993,
584
+ "loss": 0.0958,
585
+ "step": 96
586
+ }
587
+ ],
588
+ "logging_steps": 1,
589
+ "max_steps": 384,
590
+ "num_input_tokens_seen": 0,
591
+ "num_train_epochs": 4,
592
+ "save_steps": 96,
593
+ "total_flos": 7.036211137376944e+18,
594
+ "train_batch_size": 2,
595
+ "trial_name": null,
596
+ "trial_params": null
597
+ }
checkpoint-96/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12beba6580debef350132c689cb747c91282ee11c5990b44305f48ba18424e41
3
+ size 4923