Hugging Face's logo

stillerman
/
starcoder-mathematica

PEFT
Safetensors
gpt_bigcode
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
stillerman commited on
Commit
076b539
•
1 Parent(s): b9fd121

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. README.md +164 -0
  2. adapter_config.json +30 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +6 -0
  5. checkpoint-492/README.md +218 -0
  6. checkpoint-492/adapter_config.json +30 -0
  7. checkpoint-492/adapter_model.safetensors +3 -0
  8. checkpoint-492/optimizer.pt +3 -0
  9. checkpoint-492/rng_state.pth +3 -0
  10. checkpoint-492/scheduler.pt +3 -0
  11. checkpoint-492/trainer_state.json +3005 -0
  12. checkpoint-492/training_args.bin +3 -0
  13. config.json +51 -0
  14. merges.txt +0 -0
  15. special_tokens_map.json +51 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +218 -0
  18. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigcode-openrail-m
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: bigcode/starcoder
7
+ model-index:
8
+ - name: lora-out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.3.0`
19
+ ```yaml
20
+ base_model: bigcode/starcoder
21
+ model_type: AutoModelForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+ is_llama_derived_model: false
24
+
25
+ load_in_8bit: true
26
+ load_in_4bit: false
27
+ strict: false
28
+
29
+ datasets:
30
+ - path: /workspace/axolotl-mdel/mathematica.txt
31
+ type: completion
32
+
33
+ lora_modules_to_save:
34
+ - embed_tokens
35
+ - lm_head
36
+
37
+ dataset_prepared_path:
38
+ val_set_size: 0.05
39
+ output_dir: ./lora-out
40
+
41
+ sequence_len: 2048
42
+ sample_packing: true
43
+ pad_to_sequence_len: true
44
+
45
+ adapter: lora
46
+ lora_model_dir:
47
+ lora_r: 32
48
+ lora_alpha: 16
49
+ lora_dropout: 0.05
50
+ lora_target_linear: true
51
+ lora_fan_in_fan_out:
52
+
53
+ wandb_project: starcoder-mathematica
54
+ wandb_entity:
55
+ wandb_watch:
56
+ wandb_name:
57
+ wandb_log_model:
58
+
59
+ gradient_accumulation_steps: 2
60
+ micro_batch_size: 1
61
+ num_epochs: 1
62
+ optimizer: adamw_bnb_8bit
63
+ lr_scheduler: cosine
64
+ learning_rate: 0.0002
65
+
66
+ train_on_inputs: false
67
+ group_by_length: false
68
+ bf16: true
69
+ fp16: false
70
+ tf32: false
71
+
72
+ gradient_checkpointing: true
73
+ early_stopping_patience:
74
+ resume_from_checkpoint:
75
+ local_rank:
76
+ logging_steps: 1
77
+ xformers_attention:
78
+ flash_attention: true
79
+ s2_attention:
80
+
81
+ warmup_steps: 10
82
+ evals_per_epoch: 4
83
+ eval_table_size:
84
+ eval_table_max_new_tokens: 128
85
+ saves_per_epoch: 1
86
+ debug:
87
+ deepspeed:
88
+ weight_decay: 0.0
89
+ fsdp:
90
+ fsdp_config:
91
+ special_tokens:
92
+ pad_token: "[PAD]"
93
+ bos_token: "<s>"
94
+ eos_token: "</s>"
95
+ unk_token: "<unk>"
96
+
97
+ ```
98
+
99
+ </details><br>
100
+
101
+ # lora-out
102
+
103
+ This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on the None dataset.
104
+ It achieves the following results on the evaluation set:
105
+ - Loss: 3.0968
106
+
107
+ ## Model description
108
+
109
+ More information needed
110
+
111
+ ## Intended uses & limitations
112
+
113
+ More information needed
114
+
115
+ ## Training and evaluation data
116
+
117
+ More information needed
118
+
119
+ ## Training procedure
120
+
121
+
122
+ The following `bitsandbytes` quantization config was used during training:
123
+ - quant_method: bitsandbytes
124
+ - load_in_8bit: True
125
+ - load_in_4bit: False
126
+ - llm_int8_threshold: 6.0
127
+ - llm_int8_skip_modules: None
128
+ - llm_int8_enable_fp32_cpu_offload: False
129
+ - llm_int8_has_fp16_weight: False
130
+ - bnb_4bit_quant_type: fp4
131
+ - bnb_4bit_use_double_quant: False
132
+ - bnb_4bit_compute_dtype: float32
133
+
134
+ ### Training hyperparameters
135
+
136
+ The following hyperparameters were used during training:
137
+ - learning_rate: 0.0002
138
+ - train_batch_size: 1
139
+ - eval_batch_size: 1
140
+ - seed: 42
141
+ - gradient_accumulation_steps: 2
142
+ - total_train_batch_size: 2
143
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
144
+ - lr_scheduler_type: cosine
145
+ - lr_scheduler_warmup_steps: 10
146
+ - num_epochs: 1
147
+
148
+ ### Training results
149
+
150
+ | Training Loss | Epoch | Step | Validation Loss |
151
+ |:-------------:|:-----:|:----:|:---------------:|
152
+ | 2.8529 | 0.0 | 1 | 3.1576 |
153
+ | 0.4365 | 0.25 | 127 | 3.1416 |
154
+ | 2.953 | 0.5 | 254 | 3.1146 |
155
+ | 0.35 | 0.75 | 381 | 3.0968 |
156
+
157
+
158
+ ### Framework versions
159
+
160
+ - PEFT 0.7.0
161
+ - Transformers 4.37.0.dev0
162
+ - Pytorch 2.0.1+cu118
163
+ - Datasets 2.16.1
164
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigcode/starcoder",
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": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "embed_tokens",
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 32,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "c_proj",
26
+ "c_fc",
27
+ "c_attn"
28
+ ],
29
+ "task_type": "CAUSAL_LM"
30
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdd5d4e5abc47b7801925fa4319a27dafffe3e26c99c08dec6388e846d06382
3
+ size 1045856081
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 49154,
3
+ "<s>": 49153,
4
+ "<unk>": 49155,
5
+ "[PAD]": 49152
6
+ }
checkpoint-492/README.md ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: bigcode/starcoder
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
+
201
+
202
+ ## Training procedure
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+ - PEFT 0.7.0
checkpoint-492/adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigcode/starcoder",
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": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "embed_tokens",
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 32,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "c_proj",
26
+ "c_fc",
27
+ "c_attn"
28
+ ],
29
+ "task_type": "CAUSAL_LM"
30
+ }
checkpoint-492/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7313054df98f87bd9be10494c1b522b160a13ba59900885414bc4904fca0099
3
+ size 1045783792
checkpoint-492/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999968e8507c4b291fb95454907a11256d5d7a19cd2a0e8ff6f63b25718551bf
3
+ size 826871587
checkpoint-492/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2751b99f5cff795e81a257377695a49576d09777ea32cc6b0169b19e658d9b
3
+ size 14575
checkpoint-492/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a235c7e05aad6920288b6dca5aed5dcfbfbee009cf9d05cf53f56475bacc1288
3
+ size 627
checkpoint-492/trainer_state.json ADDED
@@ -0,0 +1,3005 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9713721618953604,
5
+ "eval_steps": 127,
6
+ "global_step": 492,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 2e-05,
14
+ "loss": 2.8529,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "eval_loss": 3.1576027870178223,
20
+ "eval_runtime": 37.0517,
21
+ "eval_samples_per_second": 1.403,
22
+ "eval_steps_per_second": 1.403,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "learning_rate": 4e-05,
28
+ "loss": 0.7839,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.01,
33
+ "learning_rate": 6e-05,
34
+ "loss": 0.5453,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.01,
39
+ "learning_rate": 8e-05,
40
+ "loss": 0.0492,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.01,
45
+ "learning_rate": 0.0001,
46
+ "loss": 0.766,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.01,
51
+ "learning_rate": 0.00012,
52
+ "loss": 0.8575,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.01,
57
+ "learning_rate": 0.00014,
58
+ "loss": 0.5194,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "learning_rate": 0.00016,
64
+ "loss": 0.2592,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.02,
69
+ "learning_rate": 0.00018,
70
+ "loss": 2.9974,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.02,
75
+ "learning_rate": 0.0002,
76
+ "loss": 0.1871,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.02,
81
+ "learning_rate": 0.00019999799412001546,
82
+ "loss": 0.213,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.02,
87
+ "learning_rate": 0.00019999197656053288,
88
+ "loss": 0.7832,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.03,
93
+ "learning_rate": 0.0001999819475629623,
94
+ "loss": 2.6674,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.03,
99
+ "learning_rate": 0.00019996790752964305,
100
+ "loss": 0.1479,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.03,
105
+ "learning_rate": 0.00019994985702382758,
106
+ "loss": 0.1546,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.03,
111
+ "learning_rate": 0.00019992779676965885,
112
+ "loss": 3.1039,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.03,
117
+ "learning_rate": 0.00019990172765214128,
118
+ "loss": 2.2049,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.04,
123
+ "learning_rate": 0.00019987165071710527,
124
+ "loss": 3.6854,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.04,
129
+ "learning_rate": 0.00019983756717116536,
130
+ "loss": 0.1398,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.04,
135
+ "learning_rate": 0.0001997994783816715,
136
+ "loss": 0.3254,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.04,
141
+ "learning_rate": 0.00019975738587665456,
142
+ "loss": 0.6154,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.04,
147
+ "learning_rate": 0.00019971129134476473,
148
+ "loss": 0.8228,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.05,
153
+ "learning_rate": 0.00019966119663520412,
154
+ "loss": 0.3039,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.05,
159
+ "learning_rate": 0.0001996071037576521,
160
+ "loss": 1.0781,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.05,
165
+ "learning_rate": 0.00019954901488218515,
166
+ "loss": 0.6851,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.05,
171
+ "learning_rate": 0.00019948693233918952,
172
+ "loss": 0.6144,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.05,
177
+ "learning_rate": 0.0001994208586192678,
178
+ "loss": 0.8485,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.06,
183
+ "learning_rate": 0.00019935079637313906,
184
+ "loss": 0.6133,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.06,
189
+ "learning_rate": 0.00019927674841153237,
190
+ "loss": 2.9564,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.06,
195
+ "learning_rate": 0.0001991987177050743,
196
+ "loss": 1.506,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.06,
201
+ "learning_rate": 0.00019911670738416947,
202
+ "loss": 0.168,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.06,
207
+ "learning_rate": 0.00019903072073887507,
208
+ "loss": 0.7176,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.07,
213
+ "learning_rate": 0.000198940761218769,
214
+ "loss": 0.4638,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.07,
219
+ "learning_rate": 0.00019884683243281116,
220
+ "loss": 0.7248,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.07,
225
+ "learning_rate": 0.00019874893814919906,
226
+ "loss": 0.3349,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.07,
231
+ "learning_rate": 0.00019864708229521636,
232
+ "loss": 0.3917,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.07,
237
+ "learning_rate": 0.0001985412689570754,
238
+ "loss": 1.2308,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.08,
243
+ "learning_rate": 0.00019843150237975344,
244
+ "loss": 0.9945,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.08,
249
+ "learning_rate": 0.00019831778696682194,
250
+ "loss": 1.3547,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.08,
255
+ "learning_rate": 0.00019820012728027044,
256
+ "loss": 0.9227,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.08,
261
+ "learning_rate": 0.00019807852804032305,
262
+ "loss": 1.0954,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 0.08,
267
+ "learning_rate": 0.00019795299412524945,
268
+ "loss": 0.6762,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 0.08,
273
+ "learning_rate": 0.000197823530571169,
274
+ "loss": 1.3553,
275
+ "step": 43
276
+ },
277
+ {
278
+ "epoch": 0.09,
279
+ "learning_rate": 0.0001976901425718487,
280
+ "loss": 0.3896,
281
+ "step": 44
282
+ },
283
+ {
284
+ "epoch": 0.09,
285
+ "learning_rate": 0.00019755283547849494,
286
+ "loss": 0.3207,
287
+ "step": 45
288
+ },
289
+ {
290
+ "epoch": 0.09,
291
+ "learning_rate": 0.0001974116147995387,
292
+ "loss": 3.249,
293
+ "step": 46
294
+ },
295
+ {
296
+ "epoch": 0.09,
297
+ "learning_rate": 0.00019726648620041468,
298
+ "loss": 0.9758,
299
+ "step": 47
300
+ },
301
+ {
302
+ "epoch": 0.09,
303
+ "learning_rate": 0.0001971174555033339,
304
+ "loss": 0.5544,
305
+ "step": 48
306
+ },
307
+ {
308
+ "epoch": 0.1,
309
+ "learning_rate": 0.00019696452868705024,
310
+ "loss": 0.332,
311
+ "step": 49
312
+ },
313
+ {
314
+ "epoch": 0.1,
315
+ "learning_rate": 0.00019680771188662044,
316
+ "loss": 0.6672,
317
+ "step": 50
318
+ },
319
+ {
320
+ "epoch": 0.1,
321
+ "learning_rate": 0.0001966470113931582,
322
+ "loss": 0.7634,
323
+ "step": 51
324
+ },
325
+ {
326
+ "epoch": 0.1,
327
+ "learning_rate": 0.00019648243365358146,
328
+ "loss": 0.5081,
329
+ "step": 52
330
+ },
331
+ {
332
+ "epoch": 0.1,
333
+ "learning_rate": 0.00019631398527035422,
334
+ "loss": 0.7995,
335
+ "step": 53
336
+ },
337
+ {
338
+ "epoch": 0.11,
339
+ "learning_rate": 0.00019614167300122126,
340
+ "loss": 1.1439,
341
+ "step": 54
342
+ },
343
+ {
344
+ "epoch": 0.11,
345
+ "learning_rate": 0.0001959655037589372,
346
+ "loss": 0.4855,
347
+ "step": 55
348
+ },
349
+ {
350
+ "epoch": 0.11,
351
+ "learning_rate": 0.00019578548461098914,
352
+ "loss": 5.2893,
353
+ "step": 56
354
+ },
355
+ {
356
+ "epoch": 0.11,
357
+ "learning_rate": 0.00019560162277931325,
358
+ "loss": 0.1765,
359
+ "step": 57
360
+ },
361
+ {
362
+ "epoch": 0.11,
363
+ "learning_rate": 0.00019541392564000488,
364
+ "loss": 0.4805,
365
+ "step": 58
366
+ },
367
+ {
368
+ "epoch": 0.12,
369
+ "learning_rate": 0.00019522240072302274,
370
+ "loss": 1.668,
371
+ "step": 59
372
+ },
373
+ {
374
+ "epoch": 0.12,
375
+ "learning_rate": 0.00019502705571188672,
376
+ "loss": 0.1239,
377
+ "step": 60
378
+ },
379
+ {
380
+ "epoch": 0.12,
381
+ "learning_rate": 0.0001948278984433699,
382
+ "loss": 3.1256,
383
+ "step": 61
384
+ },
385
+ {
386
+ "epoch": 0.12,
387
+ "learning_rate": 0.0001946249369071837,
388
+ "loss": 0.2337,
389
+ "step": 62
390
+ },
391
+ {
392
+ "epoch": 0.12,
393
+ "learning_rate": 0.00019441817924565786,
394
+ "loss": 0.1279,
395
+ "step": 63
396
+ },
397
+ {
398
+ "epoch": 0.13,
399
+ "learning_rate": 0.0001942076337534135,
400
+ "loss": 3.1412,
401
+ "step": 64
402
+ },
403
+ {
404
+ "epoch": 0.13,
405
+ "learning_rate": 0.00019399330887703037,
406
+ "loss": 0.4809,
407
+ "step": 65
408
+ },
409
+ {
410
+ "epoch": 0.13,
411
+ "learning_rate": 0.00019377521321470805,
412
+ "loss": 0.5192,
413
+ "step": 66
414
+ },
415
+ {
416
+ "epoch": 0.13,
417
+ "learning_rate": 0.00019355335551592105,
418
+ "loss": 0.5328,
419
+ "step": 67
420
+ },
421
+ {
422
+ "epoch": 0.13,
423
+ "learning_rate": 0.00019332774468106768,
424
+ "loss": 0.1569,
425
+ "step": 68
426
+ },
427
+ {
428
+ "epoch": 0.14,
429
+ "learning_rate": 0.00019309838976111311,
430
+ "loss": 3.1561,
431
+ "step": 69
432
+ },
433
+ {
434
+ "epoch": 0.14,
435
+ "learning_rate": 0.00019286529995722623,
436
+ "loss": 4.205,
437
+ "step": 70
438
+ },
439
+ {
440
+ "epoch": 0.14,
441
+ "learning_rate": 0.00019262848462041045,
442
+ "loss": 0.0668,
443
+ "step": 71
444
+ },
445
+ {
446
+ "epoch": 0.14,
447
+ "learning_rate": 0.0001923879532511287,
448
+ "loss": 0.4921,
449
+ "step": 72
450
+ },
451
+ {
452
+ "epoch": 0.14,
453
+ "learning_rate": 0.0001921437154989221,
454
+ "loss": 3.1048,
455
+ "step": 73
456
+ },
457
+ {
458
+ "epoch": 0.15,
459
+ "learning_rate": 0.00019189578116202307,
460
+ "loss": 0.2369,
461
+ "step": 74
462
+ },
463
+ {
464
+ "epoch": 0.15,
465
+ "learning_rate": 0.00019164416018696207,
466
+ "loss": 0.7976,
467
+ "step": 75
468
+ },
469
+ {
470
+ "epoch": 0.15,
471
+ "learning_rate": 0.00019138886266816866,
472
+ "loss": 0.4052,
473
+ "step": 76
474
+ },
475
+ {
476
+ "epoch": 0.15,
477
+ "learning_rate": 0.00019112989884756653,
478
+ "loss": 0.3292,
479
+ "step": 77
480
+ },
481
+ {
482
+ "epoch": 0.15,
483
+ "learning_rate": 0.0001908672791141625,
484
+ "loss": 0.4974,
485
+ "step": 78
486
+ },
487
+ {
488
+ "epoch": 0.16,
489
+ "learning_rate": 0.00019060101400362998,
490
+ "loss": 0.1235,
491
+ "step": 79
492
+ },
493
+ {
494
+ "epoch": 0.16,
495
+ "learning_rate": 0.00019033111419788597,
496
+ "loss": 1.8426,
497
+ "step": 80
498
+ },
499
+ {
500
+ "epoch": 0.16,
501
+ "learning_rate": 0.000190057590524663,
502
+ "loss": 1.1387,
503
+ "step": 81
504
+ },
505
+ {
506
+ "epoch": 0.16,
507
+ "learning_rate": 0.00018978045395707418,
508
+ "loss": 0.1255,
509
+ "step": 82
510
+ },
511
+ {
512
+ "epoch": 0.16,
513
+ "learning_rate": 0.0001894997156131734,
514
+ "loss": 0.3632,
515
+ "step": 83
516
+ },
517
+ {
518
+ "epoch": 0.17,
519
+ "learning_rate": 0.0001892153867555092,
520
+ "loss": 0.5894,
521
+ "step": 84
522
+ },
523
+ {
524
+ "epoch": 0.17,
525
+ "learning_rate": 0.00018892747879067286,
526
+ "loss": 0.9053,
527
+ "step": 85
528
+ },
529
+ {
530
+ "epoch": 0.17,
531
+ "learning_rate": 0.00018863600326884082,
532
+ "loss": 0.6213,
533
+ "step": 86
534
+ },
535
+ {
536
+ "epoch": 0.17,
537
+ "learning_rate": 0.00018834097188331143,
538
+ "loss": 0.4491,
539
+ "step": 87
540
+ },
541
+ {
542
+ "epoch": 0.17,
543
+ "learning_rate": 0.00018804239647003573,
544
+ "loss": 0.3181,
545
+ "step": 88
546
+ },
547
+ {
548
+ "epoch": 0.18,
549
+ "learning_rate": 0.00018774028900714256,
550
+ "loss": 0.6545,
551
+ "step": 89
552
+ },
553
+ {
554
+ "epoch": 0.18,
555
+ "learning_rate": 0.00018743466161445823,
556
+ "loss": 0.4294,
557
+ "step": 90
558
+ },
559
+ {
560
+ "epoch": 0.18,
561
+ "learning_rate": 0.0001871255265530201,
562
+ "loss": 2.9904,
563
+ "step": 91
564
+ },
565
+ {
566
+ "epoch": 0.18,
567
+ "learning_rate": 0.00018681289622458485,
568
+ "loss": 0.6953,
569
+ "step": 92
570
+ },
571
+ {
572
+ "epoch": 0.18,
573
+ "learning_rate": 0.00018649678317113084,
574
+ "loss": 3.2506,
575
+ "step": 93
576
+ },
577
+ {
578
+ "epoch": 0.19,
579
+ "learning_rate": 0.00018617720007435497,
580
+ "loss": 0.7977,
581
+ "step": 94
582
+ },
583
+ {
584
+ "epoch": 0.19,
585
+ "learning_rate": 0.000185854159755164,
586
+ "loss": 2.8863,
587
+ "step": 95
588
+ },
589
+ {
590
+ "epoch": 0.19,
591
+ "learning_rate": 0.00018552767517316022,
592
+ "loss": 0.6639,
593
+ "step": 96
594
+ },
595
+ {
596
+ "epoch": 0.19,
597
+ "learning_rate": 0.00018519775942612128,
598
+ "loss": 0.3403,
599
+ "step": 97
600
+ },
601
+ {
602
+ "epoch": 0.19,
603
+ "learning_rate": 0.00018486442574947511,
604
+ "loss": 0.084,
605
+ "step": 98
606
+ },
607
+ {
608
+ "epoch": 0.2,
609
+ "learning_rate": 0.0001845276875157687,
610
+ "loss": 0.8301,
611
+ "step": 99
612
+ },
613
+ {
614
+ "epoch": 0.2,
615
+ "learning_rate": 0.0001841875582341317,
616
+ "loss": 0.3861,
617
+ "step": 100
618
+ },
619
+ {
620
+ "epoch": 0.2,
621
+ "learning_rate": 0.0001838440515497345,
622
+ "loss": 0.9388,
623
+ "step": 101
624
+ },
625
+ {
626
+ "epoch": 0.2,
627
+ "learning_rate": 0.00018349718124324076,
628
+ "loss": 0.4805,
629
+ "step": 102
630
+ },
631
+ {
632
+ "epoch": 0.2,
633
+ "learning_rate": 0.00018314696123025454,
634
+ "loss": 0.9507,
635
+ "step": 103
636
+ },
637
+ {
638
+ "epoch": 0.21,
639
+ "learning_rate": 0.00018279340556076216,
640
+ "loss": 0.9377,
641
+ "step": 104
642
+ },
643
+ {
644
+ "epoch": 0.21,
645
+ "learning_rate": 0.0001824365284185684,
646
+ "loss": 3.8316,
647
+ "step": 105
648
+ },
649
+ {
650
+ "epoch": 0.21,
651
+ "learning_rate": 0.00018207634412072764,
652
+ "loss": 2.9745,
653
+ "step": 106
654
+ },
655
+ {
656
+ "epoch": 0.21,
657
+ "learning_rate": 0.00018171286711696934,
658
+ "loss": 1.9168,
659
+ "step": 107
660
+ },
661
+ {
662
+ "epoch": 0.21,
663
+ "learning_rate": 0.0001813461119891184,
664
+ "loss": 0.9356,
665
+ "step": 108
666
+ },
667
+ {
668
+ "epoch": 0.22,
669
+ "learning_rate": 0.00018097609345051025,
670
+ "loss": 5.7176,
671
+ "step": 109
672
+ },
673
+ {
674
+ "epoch": 0.22,
675
+ "learning_rate": 0.00018060282634540053,
676
+ "loss": 1.141,
677
+ "step": 110
678
+ },
679
+ {
680
+ "epoch": 0.22,
681
+ "learning_rate": 0.00018022632564836948,
682
+ "loss": 0.2181,
683
+ "step": 111
684
+ },
685
+ {
686
+ "epoch": 0.22,
687
+ "learning_rate": 0.0001798466064637214,
688
+ "loss": 0.8319,
689
+ "step": 112
690
+ },
691
+ {
692
+ "epoch": 0.22,
693
+ "learning_rate": 0.00017946368402487845,
694
+ "loss": 0.6727,
695
+ "step": 113
696
+ },
697
+ {
698
+ "epoch": 0.23,
699
+ "learning_rate": 0.00017907757369376985,
700
+ "loss": 1.0776,
701
+ "step": 114
702
+ },
703
+ {
704
+ "epoch": 0.23,
705
+ "learning_rate": 0.00017868829096021527,
706
+ "loss": 0.5182,
707
+ "step": 115
708
+ },
709
+ {
710
+ "epoch": 0.23,
711
+ "learning_rate": 0.00017829585144130356,
712
+ "loss": 0.7924,
713
+ "step": 116
714
+ },
715
+ {
716
+ "epoch": 0.23,
717
+ "learning_rate": 0.0001779002708807662,
718
+ "loss": 0.4007,
719
+ "step": 117
720
+ },
721
+ {
722
+ "epoch": 0.23,
723
+ "learning_rate": 0.0001775015651483459,
724
+ "loss": 0.2954,
725
+ "step": 118
726
+ },
727
+ {
728
+ "epoch": 0.23,
729
+ "learning_rate": 0.00017709975023915949,
730
+ "loss": 1.4825,
731
+ "step": 119
732
+ },
733
+ {
734
+ "epoch": 0.24,
735
+ "learning_rate": 0.0001766948422730567,
736
+ "loss": 0.8667,
737
+ "step": 120
738
+ },
739
+ {
740
+ "epoch": 0.24,
741
+ "learning_rate": 0.0001762868574939732,
742
+ "loss": 0.0204,
743
+ "step": 121
744
+ },
745
+ {
746
+ "epoch": 0.24,
747
+ "learning_rate": 0.0001758758122692791,
748
+ "loss": 0.0491,
749
+ "step": 122
750
+ },
751
+ {
752
+ "epoch": 0.24,
753
+ "learning_rate": 0.00017546172308912213,
754
+ "loss": 3.2544,
755
+ "step": 123
756
+ },
757
+ {
758
+ "epoch": 0.24,
759
+ "learning_rate": 0.00017504460656576627,
760
+ "loss": 0.7571,
761
+ "step": 124
762
+ },
763
+ {
764
+ "epoch": 0.25,
765
+ "learning_rate": 0.0001746244794329252,
766
+ "loss": 3.2652,
767
+ "step": 125
768
+ },
769
+ {
770
+ "epoch": 0.25,
771
+ "learning_rate": 0.0001742013585450911,
772
+ "loss": 0.565,
773
+ "step": 126
774
+ },
775
+ {
776
+ "epoch": 0.25,
777
+ "learning_rate": 0.00017377526087685832,
778
+ "loss": 0.4365,
779
+ "step": 127
780
+ },
781
+ {
782
+ "epoch": 0.25,
783
+ "eval_loss": 3.1416423320770264,
784
+ "eval_runtime": 38.7051,
785
+ "eval_samples_per_second": 1.343,
786
+ "eval_steps_per_second": 1.343,
787
+ "step": 127
788
+ },
789
+ {
790
+ "epoch": 0.25,
791
+ "learning_rate": 0.0001733462035222426,
792
+ "loss": 3.5766,
793
+ "step": 128
794
+ },
795
+ {
796
+ "epoch": 0.25,
797
+ "learning_rate": 0.0001729142036939951,
798
+ "loss": 0.2136,
799
+ "step": 129
800
+ },
801
+ {
802
+ "epoch": 0.26,
803
+ "learning_rate": 0.000172479278722912,
804
+ "loss": 0.8068,
805
+ "step": 130
806
+ },
807
+ {
808
+ "epoch": 0.26,
809
+ "learning_rate": 0.0001720414460571392,
810
+ "loss": 0.3899,
811
+ "step": 131
812
+ },
813
+ {
814
+ "epoch": 0.26,
815
+ "learning_rate": 0.0001716007232614723,
816
+ "loss": 0.5877,
817
+ "step": 132
818
+ },
819
+ {
820
+ "epoch": 0.26,
821
+ "learning_rate": 0.000171157128016652,
822
+ "loss": 0.1575,
823
+ "step": 133
824
+ },
825
+ {
826
+ "epoch": 0.26,
827
+ "learning_rate": 0.00017071067811865476,
828
+ "loss": 3.0165,
829
+ "step": 134
830
+ },
831
+ {
832
+ "epoch": 0.27,
833
+ "learning_rate": 0.0001702613914779789,
834
+ "loss": 3.3047,
835
+ "step": 135
836
+ },
837
+ {
838
+ "epoch": 0.27,
839
+ "learning_rate": 0.0001698092861189259,
840
+ "loss": 0.4127,
841
+ "step": 136
842
+ },
843
+ {
844
+ "epoch": 0.27,
845
+ "learning_rate": 0.00016935438017887772,
846
+ "loss": 0.7031,
847
+ "step": 137
848
+ },
849
+ {
850
+ "epoch": 0.27,
851
+ "learning_rate": 0.00016889669190756868,
852
+ "loss": 2.9221,
853
+ "step": 138
854
+ },
855
+ {
856
+ "epoch": 0.27,
857
+ "learning_rate": 0.00016843623966635366,
858
+ "loss": 0.1674,
859
+ "step": 139
860
+ },
861
+ {
862
+ "epoch": 0.28,
863
+ "learning_rate": 0.0001679730419274713,
864
+ "loss": 0.4934,
865
+ "step": 140
866
+ },
867
+ {
868
+ "epoch": 0.28,
869
+ "learning_rate": 0.0001675071172733031,
870
+ "loss": 0.6168,
871
+ "step": 141
872
+ },
873
+ {
874
+ "epoch": 0.28,
875
+ "learning_rate": 0.00016703848439562785,
876
+ "loss": 0.3576,
877
+ "step": 142
878
+ },
879
+ {
880
+ "epoch": 0.28,
881
+ "learning_rate": 0.00016656716209487174,
882
+ "loss": 0.5786,
883
+ "step": 143
884
+ },
885
+ {
886
+ "epoch": 0.28,
887
+ "learning_rate": 0.0001660931692793541,
888
+ "loss": 1.2878,
889
+ "step": 144
890
+ },
891
+ {
892
+ "epoch": 0.29,
893
+ "learning_rate": 0.000165616524964529,
894
+ "loss": 0.4301,
895
+ "step": 145
896
+ },
897
+ {
898
+ "epoch": 0.29,
899
+ "learning_rate": 0.00016513724827222227,
900
+ "loss": 0.3353,
901
+ "step": 146
902
+ },
903
+ {
904
+ "epoch": 0.29,
905
+ "learning_rate": 0.00016465535842986434,
906
+ "loss": 0.9216,
907
+ "step": 147
908
+ },
909
+ {
910
+ "epoch": 0.29,
911
+ "learning_rate": 0.000164170874769719,
912
+ "loss": 0.4037,
913
+ "step": 148
914
+ },
915
+ {
916
+ "epoch": 0.29,
917
+ "learning_rate": 0.00016368381672810786,
918
+ "loss": 3.7759,
919
+ "step": 149
920
+ },
921
+ {
922
+ "epoch": 0.3,
923
+ "learning_rate": 0.0001631942038446304,
924
+ "loss": 0.3816,
925
+ "step": 150
926
+ },
927
+ {
928
+ "epoch": 0.3,
929
+ "learning_rate": 0.00016270205576138032,
930
+ "loss": 0.167,
931
+ "step": 151
932
+ },
933
+ {
934
+ "epoch": 0.3,
935
+ "learning_rate": 0.00016220739222215738,
936
+ "loss": 2.676,
937
+ "step": 152
938
+ },
939
+ {
940
+ "epoch": 0.3,
941
+ "learning_rate": 0.00016171023307167545,
942
+ "loss": 0.0795,
943
+ "step": 153
944
+ },
945
+ {
946
+ "epoch": 0.3,
947
+ "learning_rate": 0.0001612105982547663,
948
+ "loss": 0.1744,
949
+ "step": 154
950
+ },
951
+ {
952
+ "epoch": 0.31,
953
+ "learning_rate": 0.00016070850781557948,
954
+ "loss": 0.4056,
955
+ "step": 155
956
+ },
957
+ {
958
+ "epoch": 0.31,
959
+ "learning_rate": 0.0001602039818967783,
960
+ "loss": 0.7392,
961
+ "step": 156
962
+ },
963
+ {
964
+ "epoch": 0.31,
965
+ "learning_rate": 0.00015969704073873157,
966
+ "loss": 5.6689,
967
+ "step": 157
968
+ },
969
+ {
970
+ "epoch": 0.31,
971
+ "learning_rate": 0.0001591877046787017,
972
+ "loss": 0.7629,
973
+ "step": 158
974
+ },
975
+ {
976
+ "epoch": 0.31,
977
+ "learning_rate": 0.00015867599415002895,
978
+ "loss": 0.069,
979
+ "step": 159
980
+ },
981
+ {
982
+ "epoch": 0.32,
983
+ "learning_rate": 0.00015816192968131138,
984
+ "loss": 2.9564,
985
+ "step": 160
986
+ },
987
+ {
988
+ "epoch": 0.32,
989
+ "learning_rate": 0.0001576455318955816,
990
+ "loss": 0.3949,
991
+ "step": 161
992
+ },
993
+ {
994
+ "epoch": 0.32,
995
+ "learning_rate": 0.00015712682150947923,
996
+ "loss": 0.4876,
997
+ "step": 162
998
+ },
999
+ {
1000
+ "epoch": 0.32,
1001
+ "learning_rate": 0.00015660581933241993,
1002
+ "loss": 0.9095,
1003
+ "step": 163
1004
+ },
1005
+ {
1006
+ "epoch": 0.32,
1007
+ "learning_rate": 0.00015608254626576048,
1008
+ "loss": 0.1195,
1009
+ "step": 164
1010
+ },
1011
+ {
1012
+ "epoch": 0.33,
1013
+ "learning_rate": 0.00015555702330196023,
1014
+ "loss": 0.182,
1015
+ "step": 165
1016
+ },
1017
+ {
1018
+ "epoch": 0.33,
1019
+ "learning_rate": 0.00015502927152373914,
1020
+ "loss": 0.3554,
1021
+ "step": 166
1022
+ },
1023
+ {
1024
+ "epoch": 0.33,
1025
+ "learning_rate": 0.0001544993121032318,
1026
+ "loss": 0.5072,
1027
+ "step": 167
1028
+ },
1029
+ {
1030
+ "epoch": 0.33,
1031
+ "learning_rate": 0.000153967166301138,
1032
+ "loss": 0.7807,
1033
+ "step": 168
1034
+ },
1035
+ {
1036
+ "epoch": 0.33,
1037
+ "learning_rate": 0.00015343285546587013,
1038
+ "loss": 0.1042,
1039
+ "step": 169
1040
+ },
1041
+ {
1042
+ "epoch": 0.34,
1043
+ "learning_rate": 0.00015289640103269625,
1044
+ "loss": 0.3438,
1045
+ "step": 170
1046
+ },
1047
+ {
1048
+ "epoch": 0.34,
1049
+ "learning_rate": 0.00015235782452288068,
1050
+ "loss": 0.3308,
1051
+ "step": 171
1052
+ },
1053
+ {
1054
+ "epoch": 0.34,
1055
+ "learning_rate": 0.0001518171475428202,
1056
+ "loss": 0.5366,
1057
+ "step": 172
1058
+ },
1059
+ {
1060
+ "epoch": 0.34,
1061
+ "learning_rate": 0.00015127439178317745,
1062
+ "loss": 0.509,
1063
+ "step": 173
1064
+ },
1065
+ {
1066
+ "epoch": 0.34,
1067
+ "learning_rate": 0.00015072957901801076,
1068
+ "loss": 0.4237,
1069
+ "step": 174
1070
+ },
1071
+ {
1072
+ "epoch": 0.35,
1073
+ "learning_rate": 0.0001501827311039005,
1074
+ "loss": 0.2678,
1075
+ "step": 175
1076
+ },
1077
+ {
1078
+ "epoch": 0.35,
1079
+ "learning_rate": 0.0001496338699790724,
1080
+ "loss": 0.5321,
1081
+ "step": 176
1082
+ },
1083
+ {
1084
+ "epoch": 0.35,
1085
+ "learning_rate": 0.00014908301766251739,
1086
+ "loss": 0.1806,
1087
+ "step": 177
1088
+ },
1089
+ {
1090
+ "epoch": 0.35,
1091
+ "learning_rate": 0.00014853019625310813,
1092
+ "loss": 0.469,
1093
+ "step": 178
1094
+ },
1095
+ {
1096
+ "epoch": 0.35,
1097
+ "learning_rate": 0.00014797542792871265,
1098
+ "loss": 0.4509,
1099
+ "step": 179
1100
+ },
1101
+ {
1102
+ "epoch": 0.36,
1103
+ "learning_rate": 0.0001474187349453045,
1104
+ "loss": 0.4466,
1105
+ "step": 180
1106
+ },
1107
+ {
1108
+ "epoch": 0.36,
1109
+ "learning_rate": 0.00014686013963607,
1110
+ "loss": 0.9026,
1111
+ "step": 181
1112
+ },
1113
+ {
1114
+ "epoch": 0.36,
1115
+ "learning_rate": 0.00014629966441051208,
1116
+ "loss": 0.6483,
1117
+ "step": 182
1118
+ },
1119
+ {
1120
+ "epoch": 0.36,
1121
+ "learning_rate": 0.0001457373317535515,
1122
+ "loss": 0.1891,
1123
+ "step": 183
1124
+ },
1125
+ {
1126
+ "epoch": 0.36,
1127
+ "learning_rate": 0.0001451731642246247,
1128
+ "loss": 2.834,
1129
+ "step": 184
1130
+ },
1131
+ {
1132
+ "epoch": 0.37,
1133
+ "learning_rate": 0.00014460718445677876,
1134
+ "loss": 0.3445,
1135
+ "step": 185
1136
+ },
1137
+ {
1138
+ "epoch": 0.37,
1139
+ "learning_rate": 0.00014403941515576344,
1140
+ "loss": 0.3603,
1141
+ "step": 186
1142
+ },
1143
+ {
1144
+ "epoch": 0.37,
1145
+ "learning_rate": 0.00014346987909912023,
1146
+ "loss": 0.388,
1147
+ "step": 187
1148
+ },
1149
+ {
1150
+ "epoch": 0.37,
1151
+ "learning_rate": 0.00014289859913526874,
1152
+ "loss": 0.4124,
1153
+ "step": 188
1154
+ },
1155
+ {
1156
+ "epoch": 0.37,
1157
+ "learning_rate": 0.00014232559818258984,
1158
+ "loss": 1.4459,
1159
+ "step": 189
1160
+ },
1161
+ {
1162
+ "epoch": 0.38,
1163
+ "learning_rate": 0.00014175089922850633,
1164
+ "loss": 0.1114,
1165
+ "step": 190
1166
+ },
1167
+ {
1168
+ "epoch": 0.38,
1169
+ "learning_rate": 0.00014117452532856083,
1170
+ "loss": 3.2592,
1171
+ "step": 191
1172
+ },
1173
+ {
1174
+ "epoch": 0.38,
1175
+ "learning_rate": 0.0001405964996054907,
1176
+ "loss": 0.4387,
1177
+ "step": 192
1178
+ },
1179
+ {
1180
+ "epoch": 0.38,
1181
+ "learning_rate": 0.00014001684524830057,
1182
+ "loss": 3.0681,
1183
+ "step": 193
1184
+ },
1185
+ {
1186
+ "epoch": 0.38,
1187
+ "learning_rate": 0.00013943558551133186,
1188
+ "loss": 2.8873,
1189
+ "step": 194
1190
+ },
1191
+ {
1192
+ "epoch": 0.38,
1193
+ "learning_rate": 0.00013885274371333,
1194
+ "loss": 0.0514,
1195
+ "step": 195
1196
+ },
1197
+ {
1198
+ "epoch": 0.39,
1199
+ "learning_rate": 0.000138268343236509,
1200
+ "loss": 0.2656,
1201
+ "step": 196
1202
+ },
1203
+ {
1204
+ "epoch": 0.39,
1205
+ "learning_rate": 0.00013768240752561314,
1206
+ "loss": 0.5523,
1207
+ "step": 197
1208
+ },
1209
+ {
1210
+ "epoch": 0.39,
1211
+ "learning_rate": 0.0001370949600869768,
1212
+ "loss": 0.3376,
1213
+ "step": 198
1214
+ },
1215
+ {
1216
+ "epoch": 0.39,
1217
+ "learning_rate": 0.00013650602448758112,
1218
+ "loss": 0.397,
1219
+ "step": 199
1220
+ },
1221
+ {
1222
+ "epoch": 0.39,
1223
+ "learning_rate": 0.0001359156243541087,
1224
+ "loss": 0.306,
1225
+ "step": 200
1226
+ },
1227
+ {
1228
+ "epoch": 0.4,
1229
+ "learning_rate": 0.00013532378337199582,
1230
+ "loss": 0.3834,
1231
+ "step": 201
1232
+ },
1233
+ {
1234
+ "epoch": 0.4,
1235
+ "learning_rate": 0.00013473052528448201,
1236
+ "loss": 0.351,
1237
+ "step": 202
1238
+ },
1239
+ {
1240
+ "epoch": 0.4,
1241
+ "learning_rate": 0.00013413587389165784,
1242
+ "loss": 0.3581,
1243
+ "step": 203
1244
+ },
1245
+ {
1246
+ "epoch": 0.4,
1247
+ "learning_rate": 0.00013353985304950973,
1248
+ "loss": 0.3167,
1249
+ "step": 204
1250
+ },
1251
+ {
1252
+ "epoch": 0.4,
1253
+ "learning_rate": 0.00013294248666896328,
1254
+ "loss": 1.2743,
1255
+ "step": 205
1256
+ },
1257
+ {
1258
+ "epoch": 0.41,
1259
+ "learning_rate": 0.0001323437987149238,
1260
+ "loss": 1.1231,
1261
+ "step": 206
1262
+ },
1263
+ {
1264
+ "epoch": 0.41,
1265
+ "learning_rate": 0.00013174381320531505,
1266
+ "loss": 0.2232,
1267
+ "step": 207
1268
+ },
1269
+ {
1270
+ "epoch": 0.41,
1271
+ "learning_rate": 0.0001311425542101154,
1272
+ "loss": 0.2116,
1273
+ "step": 208
1274
+ },
1275
+ {
1276
+ "epoch": 0.41,
1277
+ "learning_rate": 0.00013054004585039258,
1278
+ "loss": 3.3701,
1279
+ "step": 209
1280
+ },
1281
+ {
1282
+ "epoch": 0.41,
1283
+ "learning_rate": 0.00012993631229733582,
1284
+ "loss": 0.1044,
1285
+ "step": 210
1286
+ },
1287
+ {
1288
+ "epoch": 0.42,
1289
+ "learning_rate": 0.00012933137777128607,
1290
+ "loss": 0.8717,
1291
+ "step": 211
1292
+ },
1293
+ {
1294
+ "epoch": 0.42,
1295
+ "learning_rate": 0.0001287252665407645,
1296
+ "loss": 0.1707,
1297
+ "step": 212
1298
+ },
1299
+ {
1300
+ "epoch": 0.42,
1301
+ "learning_rate": 0.0001281180029214988,
1302
+ "loss": 0.3714,
1303
+ "step": 213
1304
+ },
1305
+ {
1306
+ "epoch": 0.42,
1307
+ "learning_rate": 0.0001275096112754478,
1308
+ "loss": 0.5697,
1309
+ "step": 214
1310
+ },
1311
+ {
1312
+ "epoch": 0.42,
1313
+ "learning_rate": 0.000126900116009824,
1314
+ "loss": 0.8001,
1315
+ "step": 215
1316
+ },
1317
+ {
1318
+ "epoch": 0.43,
1319
+ "learning_rate": 0.0001262895415761145,
1320
+ "loss": 0.8647,
1321
+ "step": 216
1322
+ },
1323
+ {
1324
+ "epoch": 0.43,
1325
+ "learning_rate": 0.00012567791246909994,
1326
+ "loss": 0.31,
1327
+ "step": 217
1328
+ },
1329
+ {
1330
+ "epoch": 0.43,
1331
+ "learning_rate": 0.00012506525322587207,
1332
+ "loss": 2.5493,
1333
+ "step": 218
1334
+ },
1335
+ {
1336
+ "epoch": 0.43,
1337
+ "learning_rate": 0.0001244515884248491,
1338
+ "loss": 3.1865,
1339
+ "step": 219
1340
+ },
1341
+ {
1342
+ "epoch": 0.43,
1343
+ "learning_rate": 0.00012383694268478993,
1344
+ "loss": 2.7346,
1345
+ "step": 220
1346
+ },
1347
+ {
1348
+ "epoch": 0.44,
1349
+ "learning_rate": 0.0001232213406638062,
1350
+ "loss": 2.9121,
1351
+ "step": 221
1352
+ },
1353
+ {
1354
+ "epoch": 0.44,
1355
+ "learning_rate": 0.0001226048070583735,
1356
+ "loss": 3.3936,
1357
+ "step": 222
1358
+ },
1359
+ {
1360
+ "epoch": 0.44,
1361
+ "learning_rate": 0.00012198736660234009,
1362
+ "loss": 0.7656,
1363
+ "step": 223
1364
+ },
1365
+ {
1366
+ "epoch": 0.44,
1367
+ "learning_rate": 0.00012136904406593507,
1368
+ "loss": 0.2102,
1369
+ "step": 224
1370
+ },
1371
+ {
1372
+ "epoch": 0.44,
1373
+ "learning_rate": 0.00012074986425477445,
1374
+ "loss": 0.0982,
1375
+ "step": 225
1376
+ },
1377
+ {
1378
+ "epoch": 0.45,
1379
+ "learning_rate": 0.00012012985200886602,
1380
+ "loss": 0.5801,
1381
+ "step": 226
1382
+ },
1383
+ {
1384
+ "epoch": 0.45,
1385
+ "learning_rate": 0.00011950903220161285,
1386
+ "loss": 0.1236,
1387
+ "step": 227
1388
+ },
1389
+ {
1390
+ "epoch": 0.45,
1391
+ "learning_rate": 0.00011888742973881543,
1392
+ "loss": 1.401,
1393
+ "step": 228
1394
+ },
1395
+ {
1396
+ "epoch": 0.45,
1397
+ "learning_rate": 0.00011826506955767258,
1398
+ "loss": 0.5149,
1399
+ "step": 229
1400
+ },
1401
+ {
1402
+ "epoch": 0.45,
1403
+ "learning_rate": 0.00011764197662578086,
1404
+ "loss": 0.6567,
1405
+ "step": 230
1406
+ },
1407
+ {
1408
+ "epoch": 0.46,
1409
+ "learning_rate": 0.00011701817594013312,
1410
+ "loss": 0.1937,
1411
+ "step": 231
1412
+ },
1413
+ {
1414
+ "epoch": 0.46,
1415
+ "learning_rate": 0.00011639369252611552,
1416
+ "loss": 0.1336,
1417
+ "step": 232
1418
+ },
1419
+ {
1420
+ "epoch": 0.46,
1421
+ "learning_rate": 0.00011576855143650371,
1422
+ "loss": 2.8677,
1423
+ "step": 233
1424
+ },
1425
+ {
1426
+ "epoch": 0.46,
1427
+ "learning_rate": 0.00011514277775045768,
1428
+ "loss": 0.3171,
1429
+ "step": 234
1430
+ },
1431
+ {
1432
+ "epoch": 0.46,
1433
+ "learning_rate": 0.00011451639657251563,
1434
+ "loss": 0.7903,
1435
+ "step": 235
1436
+ },
1437
+ {
1438
+ "epoch": 0.47,
1439
+ "learning_rate": 0.00011388943303158693,
1440
+ "loss": 2.6568,
1441
+ "step": 236
1442
+ },
1443
+ {
1444
+ "epoch": 0.47,
1445
+ "learning_rate": 0.00011326191227994391,
1446
+ "loss": 0.2808,
1447
+ "step": 237
1448
+ },
1449
+ {
1450
+ "epoch": 0.47,
1451
+ "learning_rate": 0.00011263385949221295,
1452
+ "loss": 0.1951,
1453
+ "step": 238
1454
+ },
1455
+ {
1456
+ "epoch": 0.47,
1457
+ "learning_rate": 0.0001120052998643643,
1458
+ "loss": 0.0974,
1459
+ "step": 239
1460
+ },
1461
+ {
1462
+ "epoch": 0.47,
1463
+ "learning_rate": 0.00011137625861270151,
1464
+ "loss": 0.1154,
1465
+ "step": 240
1466
+ },
1467
+ {
1468
+ "epoch": 0.48,
1469
+ "learning_rate": 0.00011074676097284973,
1470
+ "loss": 0.2559,
1471
+ "step": 241
1472
+ },
1473
+ {
1474
+ "epoch": 0.48,
1475
+ "learning_rate": 0.00011011683219874323,
1476
+ "loss": 0.6843,
1477
+ "step": 242
1478
+ },
1479
+ {
1480
+ "epoch": 0.48,
1481
+ "learning_rate": 0.00010948649756161246,
1482
+ "loss": 1.8828,
1483
+ "step": 243
1484
+ },
1485
+ {
1486
+ "epoch": 0.48,
1487
+ "learning_rate": 0.00010885578234897003,
1488
+ "loss": 0.0511,
1489
+ "step": 244
1490
+ },
1491
+ {
1492
+ "epoch": 0.48,
1493
+ "learning_rate": 0.00010822471186359639,
1494
+ "loss": 0.4992,
1495
+ "step": 245
1496
+ },
1497
+ {
1498
+ "epoch": 0.49,
1499
+ "learning_rate": 0.00010759331142252462,
1500
+ "loss": 0.1157,
1501
+ "step": 246
1502
+ },
1503
+ {
1504
+ "epoch": 0.49,
1505
+ "learning_rate": 0.00010696160635602487,
1506
+ "loss": 0.937,
1507
+ "step": 247
1508
+ },
1509
+ {
1510
+ "epoch": 0.49,
1511
+ "learning_rate": 0.00010632962200658815,
1512
+ "loss": 0.052,
1513
+ "step": 248
1514
+ },
1515
+ {
1516
+ "epoch": 0.49,
1517
+ "learning_rate": 0.00010569738372790956,
1518
+ "loss": 0.1229,
1519
+ "step": 249
1520
+ },
1521
+ {
1522
+ "epoch": 0.49,
1523
+ "learning_rate": 0.00010506491688387127,
1524
+ "loss": 0.1599,
1525
+ "step": 250
1526
+ },
1527
+ {
1528
+ "epoch": 0.5,
1529
+ "learning_rate": 0.000104432246847525,
1530
+ "loss": 0.7171,
1531
+ "step": 251
1532
+ },
1533
+ {
1534
+ "epoch": 0.5,
1535
+ "learning_rate": 0.00010379939900007393,
1536
+ "loss": 0.0594,
1537
+ "step": 252
1538
+ },
1539
+ {
1540
+ "epoch": 0.5,
1541
+ "learning_rate": 0.00010316639872985472,
1542
+ "loss": 2.7738,
1543
+ "step": 253
1544
+ },
1545
+ {
1546
+ "epoch": 0.5,
1547
+ "learning_rate": 0.00010253327143131879,
1548
+ "loss": 2.953,
1549
+ "step": 254
1550
+ },
1551
+ {
1552
+ "epoch": 0.5,
1553
+ "eval_loss": 3.1145544052124023,
1554
+ "eval_runtime": 38.0064,
1555
+ "eval_samples_per_second": 1.368,
1556
+ "eval_steps_per_second": 1.368,
1557
+ "step": 254
1558
+ },
1559
+ {
1560
+ "epoch": 0.5,
1561
+ "learning_rate": 0.00010190004250401368,
1562
+ "loss": 1.0087,
1563
+ "step": 255
1564
+ },
1565
+ {
1566
+ "epoch": 0.51,
1567
+ "learning_rate": 0.00010126673735156402,
1568
+ "loss": 0.1579,
1569
+ "step": 256
1570
+ },
1571
+ {
1572
+ "epoch": 0.51,
1573
+ "learning_rate": 0.00010063338138065234,
1574
+ "loss": 0.7859,
1575
+ "step": 257
1576
+ },
1577
+ {
1578
+ "epoch": 0.51,
1579
+ "learning_rate": 0.0001,
1580
+ "loss": 3.0133,
1581
+ "step": 258
1582
+ },
1583
+ {
1584
+ "epoch": 0.51,
1585
+ "learning_rate": 9.936661861934765e-05,
1586
+ "loss": 0.2415,
1587
+ "step": 259
1588
+ },
1589
+ {
1590
+ "epoch": 0.51,
1591
+ "learning_rate": 9.8733262648436e-05,
1592
+ "loss": 0.1456,
1593
+ "step": 260
1594
+ },
1595
+ {
1596
+ "epoch": 0.52,
1597
+ "learning_rate": 9.809995749598632e-05,
1598
+ "loss": 0.1532,
1599
+ "step": 261
1600
+ },
1601
+ {
1602
+ "epoch": 0.52,
1603
+ "learning_rate": 9.746672856868123e-05,
1604
+ "loss": 0.407,
1605
+ "step": 262
1606
+ },
1607
+ {
1608
+ "epoch": 0.52,
1609
+ "learning_rate": 9.683360127014529e-05,
1610
+ "loss": 0.3275,
1611
+ "step": 263
1612
+ },
1613
+ {
1614
+ "epoch": 0.52,
1615
+ "learning_rate": 9.620060099992609e-05,
1616
+ "loss": 0.3738,
1617
+ "step": 264
1618
+ },
1619
+ {
1620
+ "epoch": 0.52,
1621
+ "learning_rate": 9.556775315247501e-05,
1622
+ "loss": 0.283,
1623
+ "step": 265
1624
+ },
1625
+ {
1626
+ "epoch": 0.53,
1627
+ "learning_rate": 9.493508311612874e-05,
1628
+ "loss": 0.6886,
1629
+ "step": 266
1630
+ },
1631
+ {
1632
+ "epoch": 0.53,
1633
+ "learning_rate": 9.430261627209044e-05,
1634
+ "loss": 0.2551,
1635
+ "step": 267
1636
+ },
1637
+ {
1638
+ "epoch": 0.53,
1639
+ "learning_rate": 9.367037799341187e-05,
1640
+ "loss": 0.8632,
1641
+ "step": 268
1642
+ },
1643
+ {
1644
+ "epoch": 0.53,
1645
+ "learning_rate": 9.303839364397511e-05,
1646
+ "loss": 0.4109,
1647
+ "step": 269
1648
+ },
1649
+ {
1650
+ "epoch": 0.53,
1651
+ "learning_rate": 9.24066885774754e-05,
1652
+ "loss": 0.122,
1653
+ "step": 270
1654
+ },
1655
+ {
1656
+ "epoch": 0.54,
1657
+ "learning_rate": 9.177528813640362e-05,
1658
+ "loss": 0.1055,
1659
+ "step": 271
1660
+ },
1661
+ {
1662
+ "epoch": 0.54,
1663
+ "learning_rate": 9.114421765102999e-05,
1664
+ "loss": 0.3906,
1665
+ "step": 272
1666
+ },
1667
+ {
1668
+ "epoch": 0.54,
1669
+ "learning_rate": 9.051350243838756e-05,
1670
+ "loss": 0.0687,
1671
+ "step": 273
1672
+ },
1673
+ {
1674
+ "epoch": 0.54,
1675
+ "learning_rate": 8.98831678012568e-05,
1676
+ "loss": 2.9347,
1677
+ "step": 274
1678
+ },
1679
+ {
1680
+ "epoch": 0.54,
1681
+ "learning_rate": 8.925323902715031e-05,
1682
+ "loss": 0.1194,
1683
+ "step": 275
1684
+ },
1685
+ {
1686
+ "epoch": 0.54,
1687
+ "learning_rate": 8.862374138729853e-05,
1688
+ "loss": 0.5719,
1689
+ "step": 276
1690
+ },
1691
+ {
1692
+ "epoch": 0.55,
1693
+ "learning_rate": 8.799470013563573e-05,
1694
+ "loss": 2.7415,
1695
+ "step": 277
1696
+ },
1697
+ {
1698
+ "epoch": 0.55,
1699
+ "learning_rate": 8.73661405077871e-05,
1700
+ "loss": 0.1243,
1701
+ "step": 278
1702
+ },
1703
+ {
1704
+ "epoch": 0.55,
1705
+ "learning_rate": 8.67380877200561e-05,
1706
+ "loss": 2.9093,
1707
+ "step": 279
1708
+ },
1709
+ {
1710
+ "epoch": 0.55,
1711
+ "learning_rate": 8.611056696841312e-05,
1712
+ "loss": 1.2619,
1713
+ "step": 280
1714
+ },
1715
+ {
1716
+ "epoch": 0.55,
1717
+ "learning_rate": 8.54836034274844e-05,
1718
+ "loss": 0.5068,
1719
+ "step": 281
1720
+ },
1721
+ {
1722
+ "epoch": 0.56,
1723
+ "learning_rate": 8.485722224954237e-05,
1724
+ "loss": 2.9148,
1725
+ "step": 282
1726
+ },
1727
+ {
1728
+ "epoch": 0.56,
1729
+ "learning_rate": 8.423144856349631e-05,
1730
+ "loss": 1.1471,
1731
+ "step": 283
1732
+ },
1733
+ {
1734
+ "epoch": 0.56,
1735
+ "learning_rate": 8.36063074738845e-05,
1736
+ "loss": 1.91,
1737
+ "step": 284
1738
+ },
1739
+ {
1740
+ "epoch": 0.56,
1741
+ "learning_rate": 8.298182405986689e-05,
1742
+ "loss": 0.0886,
1743
+ "step": 285
1744
+ },
1745
+ {
1746
+ "epoch": 0.56,
1747
+ "learning_rate": 8.235802337421919e-05,
1748
+ "loss": 0.3945,
1749
+ "step": 286
1750
+ },
1751
+ {
1752
+ "epoch": 0.57,
1753
+ "learning_rate": 8.173493044232745e-05,
1754
+ "loss": 0.4341,
1755
+ "step": 287
1756
+ },
1757
+ {
1758
+ "epoch": 0.57,
1759
+ "learning_rate": 8.11125702611846e-05,
1760
+ "loss": 1.4804,
1761
+ "step": 288
1762
+ },
1763
+ {
1764
+ "epoch": 0.57,
1765
+ "learning_rate": 8.049096779838719e-05,
1766
+ "loss": 2.9338,
1767
+ "step": 289
1768
+ },
1769
+ {
1770
+ "epoch": 0.57,
1771
+ "learning_rate": 7.987014799113397e-05,
1772
+ "loss": 0.4612,
1773
+ "step": 290
1774
+ },
1775
+ {
1776
+ "epoch": 0.57,
1777
+ "learning_rate": 7.925013574522557e-05,
1778
+ "loss": 0.9304,
1779
+ "step": 291
1780
+ },
1781
+ {
1782
+ "epoch": 0.58,
1783
+ "learning_rate": 7.863095593406491e-05,
1784
+ "loss": 2.9119,
1785
+ "step": 292
1786
+ },
1787
+ {
1788
+ "epoch": 0.58,
1789
+ "learning_rate": 7.801263339765994e-05,
1790
+ "loss": 2.8254,
1791
+ "step": 293
1792
+ },
1793
+ {
1794
+ "epoch": 0.58,
1795
+ "learning_rate": 7.739519294162652e-05,
1796
+ "loss": 0.0828,
1797
+ "step": 294
1798
+ },
1799
+ {
1800
+ "epoch": 0.58,
1801
+ "learning_rate": 7.677865933619379e-05,
1802
+ "loss": 2.9986,
1803
+ "step": 295
1804
+ },
1805
+ {
1806
+ "epoch": 0.58,
1807
+ "learning_rate": 7.616305731521008e-05,
1808
+ "loss": 3.1021,
1809
+ "step": 296
1810
+ },
1811
+ {
1812
+ "epoch": 0.59,
1813
+ "learning_rate": 7.554841157515092e-05,
1814
+ "loss": 0.6816,
1815
+ "step": 297
1816
+ },
1817
+ {
1818
+ "epoch": 0.59,
1819
+ "learning_rate": 7.493474677412794e-05,
1820
+ "loss": 0.1559,
1821
+ "step": 298
1822
+ },
1823
+ {
1824
+ "epoch": 0.59,
1825
+ "learning_rate": 7.432208753090009e-05,
1826
+ "loss": 0.0844,
1827
+ "step": 299
1828
+ },
1829
+ {
1830
+ "epoch": 0.59,
1831
+ "learning_rate": 7.371045842388552e-05,
1832
+ "loss": 2.7568,
1833
+ "step": 300
1834
+ },
1835
+ {
1836
+ "epoch": 0.59,
1837
+ "learning_rate": 7.309988399017602e-05,
1838
+ "loss": 1.1267,
1839
+ "step": 301
1840
+ },
1841
+ {
1842
+ "epoch": 0.6,
1843
+ "learning_rate": 7.24903887245522e-05,
1844
+ "loss": 0.2277,
1845
+ "step": 302
1846
+ },
1847
+ {
1848
+ "epoch": 0.6,
1849
+ "learning_rate": 7.188199707850122e-05,
1850
+ "loss": 0.0967,
1851
+ "step": 303
1852
+ },
1853
+ {
1854
+ "epoch": 0.6,
1855
+ "learning_rate": 7.127473345923554e-05,
1856
+ "loss": 3.2755,
1857
+ "step": 304
1858
+ },
1859
+ {
1860
+ "epoch": 0.6,
1861
+ "learning_rate": 7.066862222871397e-05,
1862
+ "loss": 1.1044,
1863
+ "step": 305
1864
+ },
1865
+ {
1866
+ "epoch": 0.6,
1867
+ "learning_rate": 7.006368770266421e-05,
1868
+ "loss": 0.0781,
1869
+ "step": 306
1870
+ },
1871
+ {
1872
+ "epoch": 0.61,
1873
+ "learning_rate": 6.945995414960744e-05,
1874
+ "loss": 0.064,
1875
+ "step": 307
1876
+ },
1877
+ {
1878
+ "epoch": 0.61,
1879
+ "learning_rate": 6.885744578988463e-05,
1880
+ "loss": 0.831,
1881
+ "step": 308
1882
+ },
1883
+ {
1884
+ "epoch": 0.61,
1885
+ "learning_rate": 6.825618679468502e-05,
1886
+ "loss": 0.1206,
1887
+ "step": 309
1888
+ },
1889
+ {
1890
+ "epoch": 0.61,
1891
+ "learning_rate": 6.765620128507619e-05,
1892
+ "loss": 0.6853,
1893
+ "step": 310
1894
+ },
1895
+ {
1896
+ "epoch": 0.61,
1897
+ "learning_rate": 6.705751333103675e-05,
1898
+ "loss": 0.2435,
1899
+ "step": 311
1900
+ },
1901
+ {
1902
+ "epoch": 0.62,
1903
+ "learning_rate": 6.64601469504903e-05,
1904
+ "loss": 0.753,
1905
+ "step": 312
1906
+ },
1907
+ {
1908
+ "epoch": 0.62,
1909
+ "learning_rate": 6.586412610834221e-05,
1910
+ "loss": 0.0688,
1911
+ "step": 313
1912
+ },
1913
+ {
1914
+ "epoch": 0.62,
1915
+ "learning_rate": 6.526947471551798e-05,
1916
+ "loss": 0.2185,
1917
+ "step": 314
1918
+ },
1919
+ {
1920
+ "epoch": 0.62,
1921
+ "learning_rate": 6.46762166280042e-05,
1922
+ "loss": 0.0895,
1923
+ "step": 315
1924
+ },
1925
+ {
1926
+ "epoch": 0.62,
1927
+ "learning_rate": 6.40843756458913e-05,
1928
+ "loss": 2.5166,
1929
+ "step": 316
1930
+ },
1931
+ {
1932
+ "epoch": 0.63,
1933
+ "learning_rate": 6.349397551241894e-05,
1934
+ "loss": 0.7716,
1935
+ "step": 317
1936
+ },
1937
+ {
1938
+ "epoch": 0.63,
1939
+ "learning_rate": 6.290503991302324e-05,
1940
+ "loss": 0.7076,
1941
+ "step": 318
1942
+ },
1943
+ {
1944
+ "epoch": 0.63,
1945
+ "learning_rate": 6.231759247438689e-05,
1946
+ "loss": 0.3317,
1947
+ "step": 319
1948
+ },
1949
+ {
1950
+ "epoch": 0.63,
1951
+ "learning_rate": 6.173165676349103e-05,
1952
+ "loss": 0.3898,
1953
+ "step": 320
1954
+ },
1955
+ {
1956
+ "epoch": 0.63,
1957
+ "learning_rate": 6.114725628666998e-05,
1958
+ "loss": 1.9533,
1959
+ "step": 321
1960
+ },
1961
+ {
1962
+ "epoch": 0.64,
1963
+ "learning_rate": 6.0564414488668165e-05,
1964
+ "loss": 0.646,
1965
+ "step": 322
1966
+ },
1967
+ {
1968
+ "epoch": 0.64,
1969
+ "learning_rate": 5.998315475169942e-05,
1970
+ "loss": 2.9357,
1971
+ "step": 323
1972
+ },
1973
+ {
1974
+ "epoch": 0.64,
1975
+ "learning_rate": 5.94035003945093e-05,
1976
+ "loss": 5.7477,
1977
+ "step": 324
1978
+ },
1979
+ {
1980
+ "epoch": 0.64,
1981
+ "learning_rate": 5.88254746714392e-05,
1982
+ "loss": 1.0008,
1983
+ "step": 325
1984
+ },
1985
+ {
1986
+ "epoch": 0.64,
1987
+ "learning_rate": 5.824910077149371e-05,
1988
+ "loss": 0.3179,
1989
+ "step": 326
1990
+ },
1991
+ {
1992
+ "epoch": 0.65,
1993
+ "learning_rate": 5.767440181741019e-05,
1994
+ "loss": 0.9338,
1995
+ "step": 327
1996
+ },
1997
+ {
1998
+ "epoch": 0.65,
1999
+ "learning_rate": 5.710140086473129e-05,
2000
+ "loss": 0.1536,
2001
+ "step": 328
2002
+ },
2003
+ {
2004
+ "epoch": 0.65,
2005
+ "learning_rate": 5.653012090087977e-05,
2006
+ "loss": 0.61,
2007
+ "step": 329
2008
+ },
2009
+ {
2010
+ "epoch": 0.65,
2011
+ "learning_rate": 5.596058484423656e-05,
2012
+ "loss": 1.2369,
2013
+ "step": 330
2014
+ },
2015
+ {
2016
+ "epoch": 0.65,
2017
+ "learning_rate": 5.5392815543221254e-05,
2018
+ "loss": 0.1902,
2019
+ "step": 331
2020
+ },
2021
+ {
2022
+ "epoch": 0.66,
2023
+ "learning_rate": 5.4826835775375285e-05,
2024
+ "loss": 0.2775,
2025
+ "step": 332
2026
+ },
2027
+ {
2028
+ "epoch": 0.66,
2029
+ "learning_rate": 5.4262668246448475e-05,
2030
+ "loss": 0.2029,
2031
+ "step": 333
2032
+ },
2033
+ {
2034
+ "epoch": 0.66,
2035
+ "learning_rate": 5.3700335589487925e-05,
2036
+ "loss": 0.0906,
2037
+ "step": 334
2038
+ },
2039
+ {
2040
+ "epoch": 0.66,
2041
+ "learning_rate": 5.3139860363929996e-05,
2042
+ "loss": 0.1297,
2043
+ "step": 335
2044
+ },
2045
+ {
2046
+ "epoch": 0.66,
2047
+ "learning_rate": 5.2581265054695494e-05,
2048
+ "loss": 0.3453,
2049
+ "step": 336
2050
+ },
2051
+ {
2052
+ "epoch": 0.67,
2053
+ "learning_rate": 5.202457207128736e-05,
2054
+ "loss": 0.156,
2055
+ "step": 337
2056
+ },
2057
+ {
2058
+ "epoch": 0.67,
2059
+ "learning_rate": 5.146980374689192e-05,
2060
+ "loss": 0.2555,
2061
+ "step": 338
2062
+ },
2063
+ {
2064
+ "epoch": 0.67,
2065
+ "learning_rate": 5.0916982337482644e-05,
2066
+ "loss": 0.3003,
2067
+ "step": 339
2068
+ },
2069
+ {
2070
+ "epoch": 0.67,
2071
+ "learning_rate": 5.0366130020927624e-05,
2072
+ "loss": 0.7925,
2073
+ "step": 340
2074
+ },
2075
+ {
2076
+ "epoch": 0.67,
2077
+ "learning_rate": 4.981726889609952e-05,
2078
+ "loss": 1.2376,
2079
+ "step": 341
2080
+ },
2081
+ {
2082
+ "epoch": 0.68,
2083
+ "learning_rate": 4.9270420981989294e-05,
2084
+ "loss": 2.9298,
2085
+ "step": 342
2086
+ },
2087
+ {
2088
+ "epoch": 0.68,
2089
+ "learning_rate": 4.872560821682256e-05,
2090
+ "loss": 0.1811,
2091
+ "step": 343
2092
+ },
2093
+ {
2094
+ "epoch": 0.68,
2095
+ "learning_rate": 4.818285245717984e-05,
2096
+ "loss": 0.1007,
2097
+ "step": 344
2098
+ },
2099
+ {
2100
+ "epoch": 0.68,
2101
+ "learning_rate": 4.764217547711934e-05,
2102
+ "loss": 5.1643,
2103
+ "step": 345
2104
+ },
2105
+ {
2106
+ "epoch": 0.68,
2107
+ "learning_rate": 4.710359896730379e-05,
2108
+ "loss": 0.6855,
2109
+ "step": 346
2110
+ },
2111
+ {
2112
+ "epoch": 0.69,
2113
+ "learning_rate": 4.656714453412993e-05,
2114
+ "loss": 1.6421,
2115
+ "step": 347
2116
+ },
2117
+ {
2118
+ "epoch": 0.69,
2119
+ "learning_rate": 4.6032833698862044e-05,
2120
+ "loss": 0.0813,
2121
+ "step": 348
2122
+ },
2123
+ {
2124
+ "epoch": 0.69,
2125
+ "learning_rate": 4.5500687896768256e-05,
2126
+ "loss": 2.8098,
2127
+ "step": 349
2128
+ },
2129
+ {
2130
+ "epoch": 0.69,
2131
+ "learning_rate": 4.497072847626087e-05,
2132
+ "loss": 2.9227,
2133
+ "step": 350
2134
+ },
2135
+ {
2136
+ "epoch": 0.69,
2137
+ "learning_rate": 4.444297669803981e-05,
2138
+ "loss": 0.0877,
2139
+ "step": 351
2140
+ },
2141
+ {
2142
+ "epoch": 0.69,
2143
+ "learning_rate": 4.3917453734239566e-05,
2144
+ "loss": 0.1996,
2145
+ "step": 352
2146
+ },
2147
+ {
2148
+ "epoch": 0.7,
2149
+ "learning_rate": 4.339418066758008e-05,
2150
+ "loss": 0.8809,
2151
+ "step": 353
2152
+ },
2153
+ {
2154
+ "epoch": 0.7,
2155
+ "learning_rate": 4.287317849052075e-05,
2156
+ "loss": 2.7009,
2157
+ "step": 354
2158
+ },
2159
+ {
2160
+ "epoch": 0.7,
2161
+ "learning_rate": 4.235446810441841e-05,
2162
+ "loss": 0.067,
2163
+ "step": 355
2164
+ },
2165
+ {
2166
+ "epoch": 0.7,
2167
+ "learning_rate": 4.1838070318688604e-05,
2168
+ "loss": 1.6842,
2169
+ "step": 356
2170
+ },
2171
+ {
2172
+ "epoch": 0.7,
2173
+ "learning_rate": 4.132400584997106e-05,
2174
+ "loss": 0.7324,
2175
+ "step": 357
2176
+ },
2177
+ {
2178
+ "epoch": 0.71,
2179
+ "learning_rate": 4.081229532129827e-05,
2180
+ "loss": 0.1683,
2181
+ "step": 358
2182
+ },
2183
+ {
2184
+ "epoch": 0.71,
2185
+ "learning_rate": 4.030295926126845e-05,
2186
+ "loss": 0.7423,
2187
+ "step": 359
2188
+ },
2189
+ {
2190
+ "epoch": 0.71,
2191
+ "learning_rate": 3.979601810322169e-05,
2192
+ "loss": 0.2521,
2193
+ "step": 360
2194
+ },
2195
+ {
2196
+ "epoch": 0.71,
2197
+ "learning_rate": 3.929149218442052e-05,
2198
+ "loss": 0.3601,
2199
+ "step": 361
2200
+ },
2201
+ {
2202
+ "epoch": 0.71,
2203
+ "learning_rate": 3.878940174523371e-05,
2204
+ "loss": 0.1575,
2205
+ "step": 362
2206
+ },
2207
+ {
2208
+ "epoch": 0.72,
2209
+ "learning_rate": 3.828976692832458e-05,
2210
+ "loss": 0.572,
2211
+ "step": 363
2212
+ },
2213
+ {
2214
+ "epoch": 0.72,
2215
+ "learning_rate": 3.779260777784263e-05,
2216
+ "loss": 2.8984,
2217
+ "step": 364
2218
+ },
2219
+ {
2220
+ "epoch": 0.72,
2221
+ "learning_rate": 3.7297944238619706e-05,
2222
+ "loss": 0.0589,
2223
+ "step": 365
2224
+ },
2225
+ {
2226
+ "epoch": 0.72,
2227
+ "learning_rate": 3.680579615536961e-05,
2228
+ "loss": 0.0536,
2229
+ "step": 366
2230
+ },
2231
+ {
2232
+ "epoch": 0.72,
2233
+ "learning_rate": 3.631618327189218e-05,
2234
+ "loss": 0.0897,
2235
+ "step": 367
2236
+ },
2237
+ {
2238
+ "epoch": 0.73,
2239
+ "learning_rate": 3.582912523028101e-05,
2240
+ "loss": 0.7315,
2241
+ "step": 368
2242
+ },
2243
+ {
2244
+ "epoch": 0.73,
2245
+ "learning_rate": 3.534464157013574e-05,
2246
+ "loss": 0.1946,
2247
+ "step": 369
2248
+ },
2249
+ {
2250
+ "epoch": 0.73,
2251
+ "learning_rate": 3.4862751727777797e-05,
2252
+ "loss": 1.2387,
2253
+ "step": 370
2254
+ },
2255
+ {
2256
+ "epoch": 0.73,
2257
+ "learning_rate": 3.438347503547102e-05,
2258
+ "loss": 0.0964,
2259
+ "step": 371
2260
+ },
2261
+ {
2262
+ "epoch": 0.73,
2263
+ "learning_rate": 3.390683072064594e-05,
2264
+ "loss": 1.1282,
2265
+ "step": 372
2266
+ },
2267
+ {
2268
+ "epoch": 0.74,
2269
+ "learning_rate": 3.343283790512829e-05,
2270
+ "loss": 0.3648,
2271
+ "step": 373
2272
+ },
2273
+ {
2274
+ "epoch": 0.74,
2275
+ "learning_rate": 3.296151560437214e-05,
2276
+ "loss": 0.1887,
2277
+ "step": 374
2278
+ },
2279
+ {
2280
+ "epoch": 0.74,
2281
+ "learning_rate": 3.249288272669691e-05,
2282
+ "loss": 0.1734,
2283
+ "step": 375
2284
+ },
2285
+ {
2286
+ "epoch": 0.74,
2287
+ "learning_rate": 3.202695807252871e-05,
2288
+ "loss": 2.8517,
2289
+ "step": 376
2290
+ },
2291
+ {
2292
+ "epoch": 0.74,
2293
+ "learning_rate": 3.1563760333646395e-05,
2294
+ "loss": 0.1988,
2295
+ "step": 377
2296
+ },
2297
+ {
2298
+ "epoch": 0.75,
2299
+ "learning_rate": 3.110330809243134e-05,
2300
+ "loss": 2.929,
2301
+ "step": 378
2302
+ },
2303
+ {
2304
+ "epoch": 0.75,
2305
+ "learning_rate": 3.064561982112232e-05,
2306
+ "loss": 0.1981,
2307
+ "step": 379
2308
+ },
2309
+ {
2310
+ "epoch": 0.75,
2311
+ "learning_rate": 3.0190713881074105e-05,
2312
+ "loss": 0.0902,
2313
+ "step": 380
2314
+ },
2315
+ {
2316
+ "epoch": 0.75,
2317
+ "learning_rate": 2.9738608522021173e-05,
2318
+ "loss": 0.35,
2319
+ "step": 381
2320
+ },
2321
+ {
2322
+ "epoch": 0.75,
2323
+ "eval_loss": 3.096834897994995,
2324
+ "eval_runtime": 37.8467,
2325
+ "eval_samples_per_second": 1.374,
2326
+ "eval_steps_per_second": 1.374,
2327
+ "step": 381
2328
+ },
2329
+ {
2330
+ "epoch": 0.75,
2331
+ "learning_rate": 2.9289321881345254e-05,
2332
+ "loss": 0.4055,
2333
+ "step": 382
2334
+ },
2335
+ {
2336
+ "epoch": 0.76,
2337
+ "learning_rate": 2.8842871983347998e-05,
2338
+ "loss": 0.0914,
2339
+ "step": 383
2340
+ },
2341
+ {
2342
+ "epoch": 0.76,
2343
+ "learning_rate": 2.8399276738527714e-05,
2344
+ "loss": 0.6584,
2345
+ "step": 384
2346
+ },
2347
+ {
2348
+ "epoch": 0.76,
2349
+ "learning_rate": 2.795855394286081e-05,
2350
+ "loss": 0.1345,
2351
+ "step": 385
2352
+ },
2353
+ {
2354
+ "epoch": 0.76,
2355
+ "learning_rate": 2.7520721277088024e-05,
2356
+ "loss": 0.1762,
2357
+ "step": 386
2358
+ },
2359
+ {
2360
+ "epoch": 0.76,
2361
+ "learning_rate": 2.7085796306004906e-05,
2362
+ "loss": 0.0956,
2363
+ "step": 387
2364
+ },
2365
+ {
2366
+ "epoch": 0.77,
2367
+ "learning_rate": 2.6653796477757432e-05,
2368
+ "loss": 0.0985,
2369
+ "step": 388
2370
+ },
2371
+ {
2372
+ "epoch": 0.77,
2373
+ "learning_rate": 2.6224739123141684e-05,
2374
+ "loss": 0.768,
2375
+ "step": 389
2376
+ },
2377
+ {
2378
+ "epoch": 0.77,
2379
+ "learning_rate": 2.5798641454908944e-05,
2380
+ "loss": 3.141,
2381
+ "step": 390
2382
+ },
2383
+ {
2384
+ "epoch": 0.77,
2385
+ "learning_rate": 2.537552056707483e-05,
2386
+ "loss": 3.1468,
2387
+ "step": 391
2388
+ },
2389
+ {
2390
+ "epoch": 0.77,
2391
+ "learning_rate": 2.4955393434233754e-05,
2392
+ "loss": 2.8864,
2393
+ "step": 392
2394
+ },
2395
+ {
2396
+ "epoch": 0.78,
2397
+ "learning_rate": 2.45382769108779e-05,
2398
+ "loss": 0.774,
2399
+ "step": 393
2400
+ },
2401
+ {
2402
+ "epoch": 0.78,
2403
+ "learning_rate": 2.4124187730720917e-05,
2404
+ "loss": 0.1578,
2405
+ "step": 394
2406
+ },
2407
+ {
2408
+ "epoch": 0.78,
2409
+ "learning_rate": 2.3713142506026786e-05,
2410
+ "loss": 2.4016,
2411
+ "step": 395
2412
+ },
2413
+ {
2414
+ "epoch": 0.78,
2415
+ "learning_rate": 2.3305157726943327e-05,
2416
+ "loss": 3.0549,
2417
+ "step": 396
2418
+ },
2419
+ {
2420
+ "epoch": 0.78,
2421
+ "learning_rate": 2.290024976084052e-05,
2422
+ "loss": 0.3476,
2423
+ "step": 397
2424
+ },
2425
+ {
2426
+ "epoch": 0.79,
2427
+ "learning_rate": 2.2498434851654126e-05,
2428
+ "loss": 1.6223,
2429
+ "step": 398
2430
+ },
2431
+ {
2432
+ "epoch": 0.79,
2433
+ "learning_rate": 2.209972911923377e-05,
2434
+ "loss": 0.139,
2435
+ "step": 399
2436
+ },
2437
+ {
2438
+ "epoch": 0.79,
2439
+ "learning_rate": 2.170414855869647e-05,
2440
+ "loss": 3.1515,
2441
+ "step": 400
2442
+ },
2443
+ {
2444
+ "epoch": 0.79,
2445
+ "learning_rate": 2.1311709039784734e-05,
2446
+ "loss": 1.0012,
2447
+ "step": 401
2448
+ },
2449
+ {
2450
+ "epoch": 0.79,
2451
+ "learning_rate": 2.092242630623016e-05,
2452
+ "loss": 0.4592,
2453
+ "step": 402
2454
+ },
2455
+ {
2456
+ "epoch": 0.8,
2457
+ "learning_rate": 2.0536315975121544e-05,
2458
+ "loss": 0.4305,
2459
+ "step": 403
2460
+ },
2461
+ {
2462
+ "epoch": 0.8,
2463
+ "learning_rate": 2.0153393536278653e-05,
2464
+ "loss": 0.9412,
2465
+ "step": 404
2466
+ },
2467
+ {
2468
+ "epoch": 0.8,
2469
+ "learning_rate": 1.9773674351630545e-05,
2470
+ "loss": 0.1606,
2471
+ "step": 405
2472
+ },
2473
+ {
2474
+ "epoch": 0.8,
2475
+ "learning_rate": 1.939717365459952e-05,
2476
+ "loss": 0.1445,
2477
+ "step": 406
2478
+ },
2479
+ {
2480
+ "epoch": 0.8,
2481
+ "learning_rate": 1.9023906549489767e-05,
2482
+ "loss": 5.7603,
2483
+ "step": 407
2484
+ },
2485
+ {
2486
+ "epoch": 0.81,
2487
+ "learning_rate": 1.8653888010881637e-05,
2488
+ "loss": 0.037,
2489
+ "step": 408
2490
+ },
2491
+ {
2492
+ "epoch": 0.81,
2493
+ "learning_rate": 1.82871328830307e-05,
2494
+ "loss": 0.1551,
2495
+ "step": 409
2496
+ },
2497
+ {
2498
+ "epoch": 0.81,
2499
+ "learning_rate": 1.7923655879272393e-05,
2500
+ "loss": 0.542,
2501
+ "step": 410
2502
+ },
2503
+ {
2504
+ "epoch": 0.81,
2505
+ "learning_rate": 1.7563471581431624e-05,
2506
+ "loss": 0.1888,
2507
+ "step": 411
2508
+ },
2509
+ {
2510
+ "epoch": 0.81,
2511
+ "learning_rate": 1.7206594439237865e-05,
2512
+ "loss": 1.0623,
2513
+ "step": 412
2514
+ },
2515
+ {
2516
+ "epoch": 0.82,
2517
+ "learning_rate": 1.6853038769745467e-05,
2518
+ "loss": 0.0943,
2519
+ "step": 413
2520
+ },
2521
+ {
2522
+ "epoch": 0.82,
2523
+ "learning_rate": 1.6502818756759276e-05,
2524
+ "loss": 0.1562,
2525
+ "step": 414
2526
+ },
2527
+ {
2528
+ "epoch": 0.82,
2529
+ "learning_rate": 1.61559484502655e-05,
2530
+ "loss": 2.9172,
2531
+ "step": 415
2532
+ },
2533
+ {
2534
+ "epoch": 0.82,
2535
+ "learning_rate": 1.5812441765868292e-05,
2536
+ "loss": 0.0865,
2537
+ "step": 416
2538
+ },
2539
+ {
2540
+ "epoch": 0.82,
2541
+ "learning_rate": 1.547231248423132e-05,
2542
+ "loss": 2.3386,
2543
+ "step": 417
2544
+ },
2545
+ {
2546
+ "epoch": 0.83,
2547
+ "learning_rate": 1.5135574250524897e-05,
2548
+ "loss": 2.3205,
2549
+ "step": 418
2550
+ },
2551
+ {
2552
+ "epoch": 0.83,
2553
+ "learning_rate": 1.4802240573878733e-05,
2554
+ "loss": 0.9576,
2555
+ "step": 419
2556
+ },
2557
+ {
2558
+ "epoch": 0.83,
2559
+ "learning_rate": 1.447232482683979e-05,
2560
+ "loss": 0.1757,
2561
+ "step": 420
2562
+ },
2563
+ {
2564
+ "epoch": 0.83,
2565
+ "learning_rate": 1.4145840244835983e-05,
2566
+ "loss": 0.5404,
2567
+ "step": 421
2568
+ },
2569
+ {
2570
+ "epoch": 0.83,
2571
+ "learning_rate": 1.3822799925645036e-05,
2572
+ "loss": 0.8805,
2573
+ "step": 422
2574
+ },
2575
+ {
2576
+ "epoch": 0.84,
2577
+ "learning_rate": 1.3503216828869192e-05,
2578
+ "loss": 0.1249,
2579
+ "step": 423
2580
+ },
2581
+ {
2582
+ "epoch": 0.84,
2583
+ "learning_rate": 1.3187103775415156e-05,
2584
+ "loss": 0.3596,
2585
+ "step": 424
2586
+ },
2587
+ {
2588
+ "epoch": 0.84,
2589
+ "learning_rate": 1.2874473446979918e-05,
2590
+ "loss": 1.6876,
2591
+ "step": 425
2592
+ },
2593
+ {
2594
+ "epoch": 0.84,
2595
+ "learning_rate": 1.2565338385541792e-05,
2596
+ "loss": 0.1585,
2597
+ "step": 426
2598
+ },
2599
+ {
2600
+ "epoch": 0.84,
2601
+ "learning_rate": 1.2259710992857465e-05,
2602
+ "loss": 2.8895,
2603
+ "step": 427
2604
+ },
2605
+ {
2606
+ "epoch": 0.85,
2607
+ "learning_rate": 1.195760352996429e-05,
2608
+ "loss": 2.9701,
2609
+ "step": 428
2610
+ },
2611
+ {
2612
+ "epoch": 0.85,
2613
+ "learning_rate": 1.1659028116688575e-05,
2614
+ "loss": 0.3456,
2615
+ "step": 429
2616
+ },
2617
+ {
2618
+ "epoch": 0.85,
2619
+ "learning_rate": 1.1363996731159188e-05,
2620
+ "loss": 0.3992,
2621
+ "step": 430
2622
+ },
2623
+ {
2624
+ "epoch": 0.85,
2625
+ "learning_rate": 1.107252120932717e-05,
2626
+ "loss": 0.4428,
2627
+ "step": 431
2628
+ },
2629
+ {
2630
+ "epoch": 0.85,
2631
+ "learning_rate": 1.0784613244490816e-05,
2632
+ "loss": 0.0964,
2633
+ "step": 432
2634
+ },
2635
+ {
2636
+ "epoch": 0.85,
2637
+ "learning_rate": 1.0500284386826597e-05,
2638
+ "loss": 0.4612,
2639
+ "step": 433
2640
+ },
2641
+ {
2642
+ "epoch": 0.86,
2643
+ "learning_rate": 1.0219546042925843e-05,
2644
+ "loss": 1.0988,
2645
+ "step": 434
2646
+ },
2647
+ {
2648
+ "epoch": 0.86,
2649
+ "learning_rate": 9.942409475337012e-06,
2650
+ "loss": 0.2646,
2651
+ "step": 435
2652
+ },
2653
+ {
2654
+ "epoch": 0.86,
2655
+ "learning_rate": 9.668885802114003e-06,
2656
+ "loss": 0.1104,
2657
+ "step": 436
2658
+ },
2659
+ {
2660
+ "epoch": 0.86,
2661
+ "learning_rate": 9.398985996370058e-06,
2662
+ "loss": 2.9026,
2663
+ "step": 437
2664
+ },
2665
+ {
2666
+ "epoch": 0.86,
2667
+ "learning_rate": 9.13272088583751e-06,
2668
+ "loss": 2.5969,
2669
+ "step": 438
2670
+ },
2671
+ {
2672
+ "epoch": 0.87,
2673
+ "learning_rate": 8.870101152433497e-06,
2674
+ "loss": 0.204,
2675
+ "step": 439
2676
+ },
2677
+ {
2678
+ "epoch": 0.87,
2679
+ "learning_rate": 8.611137331831331e-06,
2680
+ "loss": 2.8929,
2681
+ "step": 440
2682
+ },
2683
+ {
2684
+ "epoch": 0.87,
2685
+ "learning_rate": 8.355839813037936e-06,
2686
+ "loss": 0.4752,
2687
+ "step": 441
2688
+ },
2689
+ {
2690
+ "epoch": 0.87,
2691
+ "learning_rate": 8.10421883797694e-06,
2692
+ "loss": 0.0708,
2693
+ "step": 442
2694
+ },
2695
+ {
2696
+ "epoch": 0.87,
2697
+ "learning_rate": 7.856284501077926e-06,
2698
+ "loss": 0.2817,
2699
+ "step": 443
2700
+ },
2701
+ {
2702
+ "epoch": 0.88,
2703
+ "learning_rate": 7.612046748871327e-06,
2704
+ "loss": 0.3538,
2705
+ "step": 444
2706
+ },
2707
+ {
2708
+ "epoch": 0.88,
2709
+ "learning_rate": 7.371515379589555e-06,
2710
+ "loss": 3.0355,
2711
+ "step": 445
2712
+ },
2713
+ {
2714
+ "epoch": 0.88,
2715
+ "learning_rate": 7.13470004277379e-06,
2716
+ "loss": 1.7098,
2717
+ "step": 446
2718
+ },
2719
+ {
2720
+ "epoch": 0.88,
2721
+ "learning_rate": 6.901610238886891e-06,
2722
+ "loss": 0.0538,
2723
+ "step": 447
2724
+ },
2725
+ {
2726
+ "epoch": 0.88,
2727
+ "learning_rate": 6.672255318932341e-06,
2728
+ "loss": 0.1649,
2729
+ "step": 448
2730
+ },
2731
+ {
2732
+ "epoch": 0.89,
2733
+ "learning_rate": 6.4466444840789674e-06,
2734
+ "loss": 0.1586,
2735
+ "step": 449
2736
+ },
2737
+ {
2738
+ "epoch": 0.89,
2739
+ "learning_rate": 6.22478678529197e-06,
2740
+ "loss": 3.0296,
2741
+ "step": 450
2742
+ },
2743
+ {
2744
+ "epoch": 0.89,
2745
+ "learning_rate": 6.006691122969643e-06,
2746
+ "loss": 2.9251,
2747
+ "step": 451
2748
+ },
2749
+ {
2750
+ "epoch": 0.89,
2751
+ "learning_rate": 5.792366246586511e-06,
2752
+ "loss": 0.5227,
2753
+ "step": 452
2754
+ },
2755
+ {
2756
+ "epoch": 0.89,
2757
+ "learning_rate": 5.581820754342137e-06,
2758
+ "loss": 0.1688,
2759
+ "step": 453
2760
+ },
2761
+ {
2762
+ "epoch": 0.9,
2763
+ "learning_rate": 5.375063092816313e-06,
2764
+ "loss": 0.6017,
2765
+ "step": 454
2766
+ },
2767
+ {
2768
+ "epoch": 0.9,
2769
+ "learning_rate": 5.172101556630149e-06,
2770
+ "loss": 0.0826,
2771
+ "step": 455
2772
+ },
2773
+ {
2774
+ "epoch": 0.9,
2775
+ "learning_rate": 4.972944288113268e-06,
2776
+ "loss": 0.7591,
2777
+ "step": 456
2778
+ },
2779
+ {
2780
+ "epoch": 0.9,
2781
+ "learning_rate": 4.777599276977263e-06,
2782
+ "loss": 0.1292,
2783
+ "step": 457
2784
+ },
2785
+ {
2786
+ "epoch": 0.9,
2787
+ "learning_rate": 4.586074359995119e-06,
2788
+ "loss": 0.8982,
2789
+ "step": 458
2790
+ },
2791
+ {
2792
+ "epoch": 0.91,
2793
+ "learning_rate": 4.398377220686745e-06,
2794
+ "loss": 2.735,
2795
+ "step": 459
2796
+ },
2797
+ {
2798
+ "epoch": 0.91,
2799
+ "learning_rate": 4.214515389010865e-06,
2800
+ "loss": 0.242,
2801
+ "step": 460
2802
+ },
2803
+ {
2804
+ "epoch": 0.91,
2805
+ "learning_rate": 4.034496241062824e-06,
2806
+ "loss": 0.097,
2807
+ "step": 461
2808
+ },
2809
+ {
2810
+ "epoch": 0.91,
2811
+ "learning_rate": 3.858326998778761e-06,
2812
+ "loss": 0.1028,
2813
+ "step": 462
2814
+ },
2815
+ {
2816
+ "epoch": 0.91,
2817
+ "learning_rate": 3.6860147296457816e-06,
2818
+ "loss": 0.1689,
2819
+ "step": 463
2820
+ },
2821
+ {
2822
+ "epoch": 0.92,
2823
+ "learning_rate": 3.5175663464185436e-06,
2824
+ "loss": 0.1873,
2825
+ "step": 464
2826
+ },
2827
+ {
2828
+ "epoch": 0.92,
2829
+ "learning_rate": 3.3529886068418447e-06,
2830
+ "loss": 3.074,
2831
+ "step": 465
2832
+ },
2833
+ {
2834
+ "epoch": 0.92,
2835
+ "learning_rate": 3.1922881133795825e-06,
2836
+ "loss": 0.2985,
2837
+ "step": 466
2838
+ },
2839
+ {
2840
+ "epoch": 0.92,
2841
+ "learning_rate": 3.035471312949778e-06,
2842
+ "loss": 0.0815,
2843
+ "step": 467
2844
+ },
2845
+ {
2846
+ "epoch": 0.92,
2847
+ "learning_rate": 2.8825444966661063e-06,
2848
+ "loss": 0.1297,
2849
+ "step": 468
2850
+ },
2851
+ {
2852
+ "epoch": 0.93,
2853
+ "learning_rate": 2.7335137995853188e-06,
2854
+ "loss": 1.8928,
2855
+ "step": 469
2856
+ },
2857
+ {
2858
+ "epoch": 0.93,
2859
+ "learning_rate": 2.5883852004613074e-06,
2860
+ "loss": 0.0399,
2861
+ "step": 470
2862
+ },
2863
+ {
2864
+ "epoch": 0.93,
2865
+ "learning_rate": 2.4471645215050743e-06,
2866
+ "loss": 2.4668,
2867
+ "step": 471
2868
+ },
2869
+ {
2870
+ "epoch": 0.93,
2871
+ "learning_rate": 2.3098574281513185e-06,
2872
+ "loss": 1.3717,
2873
+ "step": 472
2874
+ },
2875
+ {
2876
+ "epoch": 0.93,
2877
+ "learning_rate": 2.1764694288310184e-06,
2878
+ "loss": 0.5464,
2879
+ "step": 473
2880
+ },
2881
+ {
2882
+ "epoch": 0.94,
2883
+ "learning_rate": 2.0470058747505516e-06,
2884
+ "loss": 5.7381,
2885
+ "step": 474
2886
+ },
2887
+ {
2888
+ "epoch": 0.94,
2889
+ "learning_rate": 1.921471959676957e-06,
2890
+ "loss": 0.0523,
2891
+ "step": 475
2892
+ },
2893
+ {
2894
+ "epoch": 0.94,
2895
+ "learning_rate": 1.7998727197295784e-06,
2896
+ "loss": 2.0947,
2897
+ "step": 476
2898
+ },
2899
+ {
2900
+ "epoch": 0.94,
2901
+ "learning_rate": 1.6822130331780484e-06,
2902
+ "loss": 0.3609,
2903
+ "step": 477
2904
+ },
2905
+ {
2906
+ "epoch": 0.94,
2907
+ "learning_rate": 1.5684976202465784e-06,
2908
+ "loss": 0.3193,
2909
+ "step": 478
2910
+ },
2911
+ {
2912
+ "epoch": 0.95,
2913
+ "learning_rate": 1.4587310429245882e-06,
2914
+ "loss": 0.5045,
2915
+ "step": 479
2916
+ },
2917
+ {
2918
+ "epoch": 0.95,
2919
+ "learning_rate": 1.3529177047836627e-06,
2920
+ "loss": 0.0842,
2921
+ "step": 480
2922
+ },
2923
+ {
2924
+ "epoch": 0.95,
2925
+ "learning_rate": 1.2510618508009608e-06,
2926
+ "loss": 1.3106,
2927
+ "step": 481
2928
+ },
2929
+ {
2930
+ "epoch": 0.95,
2931
+ "learning_rate": 1.1531675671888619e-06,
2932
+ "loss": 2.8808,
2933
+ "step": 482
2934
+ },
2935
+ {
2936
+ "epoch": 0.95,
2937
+ "learning_rate": 1.0592387812310311e-06,
2938
+ "loss": 2.9172,
2939
+ "step": 483
2940
+ },
2941
+ {
2942
+ "epoch": 0.96,
2943
+ "learning_rate": 9.692792611249224e-07,
2944
+ "loss": 0.6062,
2945
+ "step": 484
2946
+ },
2947
+ {
2948
+ "epoch": 0.96,
2949
+ "learning_rate": 8.832926158305444e-07,
2950
+ "loss": 0.1825,
2951
+ "step": 485
2952
+ },
2953
+ {
2954
+ "epoch": 0.96,
2955
+ "learning_rate": 8.012822949256982e-07,
2956
+ "loss": 0.2575,
2957
+ "step": 486
2958
+ },
2959
+ {
2960
+ "epoch": 0.96,
2961
+ "learning_rate": 7.232515884676328e-07,
2962
+ "loss": 0.1746,
2963
+ "step": 487
2964
+ },
2965
+ {
2966
+ "epoch": 0.96,
2967
+ "learning_rate": 6.492036268609725e-07,
2968
+ "loss": 0.264,
2969
+ "step": 488
2970
+ },
2971
+ {
2972
+ "epoch": 0.97,
2973
+ "learning_rate": 5.791413807322066e-07,
2974
+ "loss": 0.0955,
2975
+ "step": 489
2976
+ },
2977
+ {
2978
+ "epoch": 0.97,
2979
+ "learning_rate": 5.130676608104845e-07,
2980
+ "loss": 0.1896,
2981
+ "step": 490
2982
+ },
2983
+ {
2984
+ "epoch": 0.97,
2985
+ "learning_rate": 4.509851178148505e-07,
2986
+ "loss": 0.402,
2987
+ "step": 491
2988
+ },
2989
+ {
2990
+ "epoch": 0.97,
2991
+ "learning_rate": 3.9289624234790656e-07,
2992
+ "loss": 0.3264,
2993
+ "step": 492
2994
+ }
2995
+ ],
2996
+ "logging_steps": 1,
2997
+ "max_steps": 506,
2998
+ "num_input_tokens_seen": 0,
2999
+ "num_train_epochs": 1,
3000
+ "save_steps": 500,
3001
+ "total_flos": 1.8835459562432102e+17,
3002
+ "train_batch_size": 1,
3003
+ "trial_name": null,
3004
+ "trial_params": null
3005
+ }
checkpoint-492/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bbf07f85ca03d460e0939878b710e57c14395472419b3516802b1c1ba6510a
3
+ size 4795
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigcode/starcoder",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 6144,
20
+ "n_head": 48,
21
+ "n_inner": 24576,
22
+ "n_layer": 40,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "quantization_config": {
27
+ "bnb_4bit_compute_dtype": "float32",
28
+ "bnb_4bit_quant_type": "fp4",
29
+ "bnb_4bit_use_double_quant": false,
30
+ "llm_int8_enable_fp32_cpu_offload": false,
31
+ "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": null,
33
+ "llm_int8_threshold": 6.0,
34
+ "load_in_4bit": false,
35
+ "load_in_8bit": true,
36
+ "quant_method": "bitsandbytes"
37
+ },
38
+ "resid_pdrop": 0.1,
39
+ "scale_attention_softmax_in_fp32": true,
40
+ "scale_attn_weights": true,
41
+ "summary_activation": null,
42
+ "summary_first_dropout": 0.1,
43
+ "summary_proj_to_labels": true,
44
+ "summary_type": "cls_index",
45
+ "summary_use_proj": true,
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.37.0.dev0",
48
+ "use_cache": false,
49
+ "validate_runner_input": true,
50
+ "vocab_size": 49156
51
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<s>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": {
38
+ "content": "[PAD]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<filename>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49152": {
157
+ "content": "[PAD]",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49153": {
165
+ "content": "<s>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49154": {
173
+ "content": "</s>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49155": {
181
+ "content": "<unk>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ }
188
+ },
189
+ "additional_special_tokens": [
190
+ "<|endoftext|>",
191
+ "<fim_prefix>",
192
+ "<fim_middle>",
193
+ "<fim_suffix>",
194
+ "<fim_pad>",
195
+ "<filename>",
196
+ "<gh_stars>",
197
+ "<issue_start>",
198
+ "<issue_comment>",
199
+ "<issue_closed>",
200
+ "<jupyter_start>",
201
+ "<jupyter_text>",
202
+ "<jupyter_code>",
203
+ "<jupyter_output>",
204
+ "<empty_output>",
205
+ "<commit_before>",
206
+ "<commit_msg>",
207
+ "<commit_after>",
208
+ "<reponame>"
209
+ ],
210
+ "bos_token": "<s>",
211
+ "clean_up_tokenization_spaces": true,
212
+ "eos_token": "</s>",
213
+ "model_max_length": 1000000000000000019884624838656,
214
+ "pad_token": "[PAD]",
215
+ "tokenizer_class": "GPT2Tokenizer",
216
+ "unk_token": "<unk>",
217
+ "vocab_size": 49152
218
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff