mob2711 commited on
Commit
32a4c06
1 Parent(s): d701328

Upload 14 files

Browse files
README.md CHANGED
@@ -1,3 +1,202 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2-1.5B
3
+ library_name: peft
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
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-1.5B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "lm_head",
25
+ "k_proj",
26
+ "up_proj",
27
+ "v_proj",
28
+ "o_proj",
29
+ "down_proj",
30
+ "q_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a00964968e6d0a5dff2413128626581089973918056ec3d6a35bc4c3de30ffc
3
+ size 1017229528
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f78d23e80b412492bb23e7f77c42dc58a5421d56d226af3bfb96ded4984901c
3
+ size 167693808
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e37e1ce471c56982fb53ecc021031588a46b2ad8c358491def6bf222b39b2c
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82bae41031bb9a3e20f8500051e9b275b0c0fa328ed27a9d8750a01556e2e224
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "max_length": 512,
39
+ "model_max_length": 32768,
40
+ "pad_to_multiple_of": null,
41
+ "pad_token": "<|endoftext|>",
42
+ "pad_token_type_id": 0,
43
+ "padding_side": "right",
44
+ "split_special_tokens": false,
45
+ "stride": 0,
46
+ "tokenizer_class": "Qwen2Tokenizer",
47
+ "truncation_side": "right",
48
+ "truncation_strategy": "longest_first",
49
+ "unk_token": null
50
+ }
trainer_state.json ADDED
@@ -0,0 +1,828 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8609164953231812,
3
+ "best_model_checkpoint": "/home/coder/qwen2/checkpoint-15900",
4
+ "epoch": 0.9999803783832573,
5
+ "eval_steps": 300,
6
+ "global_step": 15926,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.018836752073023807,
13
+ "grad_norm": 0.2832883298397064,
14
+ "learning_rate": 0.00019629420262546324,
15
+ "loss": 1.1403,
16
+ "step": 300
17
+ },
18
+ {
19
+ "epoch": 0.018836752073023807,
20
+ "eval_loss": 1.0671226978302002,
21
+ "eval_runtime": 300.1436,
22
+ "eval_samples_per_second": 17.155,
23
+ "eval_steps_per_second": 2.146,
24
+ "step": 300
25
+ },
26
+ {
27
+ "epoch": 0.037673504146047615,
28
+ "grad_norm": 0.33913707733154297,
29
+ "learning_rate": 0.00019252559512593432,
30
+ "loss": 1.0551,
31
+ "step": 600
32
+ },
33
+ {
34
+ "epoch": 0.037673504146047615,
35
+ "eval_loss": 1.0309056043624878,
36
+ "eval_runtime": 300.0852,
37
+ "eval_samples_per_second": 17.158,
38
+ "eval_steps_per_second": 2.146,
39
+ "step": 600
40
+ },
41
+ {
42
+ "epoch": 0.05651025621907143,
43
+ "grad_norm": 0.30800801515579224,
44
+ "learning_rate": 0.0001887569876264054,
45
+ "loss": 1.0185,
46
+ "step": 900
47
+ },
48
+ {
49
+ "epoch": 0.05651025621907143,
50
+ "eval_loss": 1.0096280574798584,
51
+ "eval_runtime": 299.931,
52
+ "eval_samples_per_second": 17.167,
53
+ "eval_steps_per_second": 2.147,
54
+ "step": 900
55
+ },
56
+ {
57
+ "epoch": 0.07534700829209523,
58
+ "grad_norm": 0.317748099565506,
59
+ "learning_rate": 0.00018498838012687648,
60
+ "loss": 0.9952,
61
+ "step": 1200
62
+ },
63
+ {
64
+ "epoch": 0.07534700829209523,
65
+ "eval_loss": 0.9937332272529602,
66
+ "eval_runtime": 299.9997,
67
+ "eval_samples_per_second": 17.163,
68
+ "eval_steps_per_second": 2.147,
69
+ "step": 1200
70
+ },
71
+ {
72
+ "epoch": 0.09418376036511904,
73
+ "grad_norm": 0.36215266585350037,
74
+ "learning_rate": 0.00018121977262734753,
75
+ "loss": 0.9931,
76
+ "step": 1500
77
+ },
78
+ {
79
+ "epoch": 0.09418376036511904,
80
+ "eval_loss": 0.9828254580497742,
81
+ "eval_runtime": 299.9242,
82
+ "eval_samples_per_second": 17.168,
83
+ "eval_steps_per_second": 2.147,
84
+ "step": 1500
85
+ },
86
+ {
87
+ "epoch": 0.11302051243814286,
88
+ "grad_norm": 0.3347627520561218,
89
+ "learning_rate": 0.0001774511651278186,
90
+ "loss": 0.9763,
91
+ "step": 1800
92
+ },
93
+ {
94
+ "epoch": 0.11302051243814286,
95
+ "eval_loss": 0.972442626953125,
96
+ "eval_runtime": 299.8563,
97
+ "eval_samples_per_second": 17.172,
98
+ "eval_steps_per_second": 2.148,
99
+ "step": 1800
100
+ },
101
+ {
102
+ "epoch": 0.13185726451116667,
103
+ "grad_norm": 0.319148451089859,
104
+ "learning_rate": 0.0001736825576282897,
105
+ "loss": 0.9727,
106
+ "step": 2100
107
+ },
108
+ {
109
+ "epoch": 0.13185726451116667,
110
+ "eval_loss": 0.965033769607544,
111
+ "eval_runtime": 299.797,
112
+ "eval_samples_per_second": 17.175,
113
+ "eval_steps_per_second": 2.148,
114
+ "step": 2100
115
+ },
116
+ {
117
+ "epoch": 0.15069401658419046,
118
+ "grad_norm": 0.2830144166946411,
119
+ "learning_rate": 0.00016991395012876077,
120
+ "loss": 0.9674,
121
+ "step": 2400
122
+ },
123
+ {
124
+ "epoch": 0.15069401658419046,
125
+ "eval_loss": 0.9570498466491699,
126
+ "eval_runtime": 300.0087,
127
+ "eval_samples_per_second": 17.163,
128
+ "eval_steps_per_second": 2.147,
129
+ "step": 2400
130
+ },
131
+ {
132
+ "epoch": 0.16953076865721428,
133
+ "grad_norm": 0.30889859795570374,
134
+ "learning_rate": 0.00016614534262923185,
135
+ "loss": 0.9601,
136
+ "step": 2700
137
+ },
138
+ {
139
+ "epoch": 0.16953076865721428,
140
+ "eval_loss": 0.9515209197998047,
141
+ "eval_runtime": 299.9801,
142
+ "eval_samples_per_second": 17.164,
143
+ "eval_steps_per_second": 2.147,
144
+ "step": 2700
145
+ },
146
+ {
147
+ "epoch": 0.18836752073023807,
148
+ "grad_norm": 0.33287131786346436,
149
+ "learning_rate": 0.0001623767351297029,
150
+ "loss": 0.944,
151
+ "step": 3000
152
+ },
153
+ {
154
+ "epoch": 0.18836752073023807,
155
+ "eval_loss": 0.9454107284545898,
156
+ "eval_runtime": 299.9554,
157
+ "eval_samples_per_second": 17.166,
158
+ "eval_steps_per_second": 2.147,
159
+ "step": 3000
160
+ },
161
+ {
162
+ "epoch": 0.2072042728032619,
163
+ "grad_norm": 0.31519943475723267,
164
+ "learning_rate": 0.00015860812763017398,
165
+ "loss": 0.9462,
166
+ "step": 3300
167
+ },
168
+ {
169
+ "epoch": 0.2072042728032619,
170
+ "eval_loss": 0.9404099583625793,
171
+ "eval_runtime": 299.9447,
172
+ "eval_samples_per_second": 17.166,
173
+ "eval_steps_per_second": 2.147,
174
+ "step": 3300
175
+ },
176
+ {
177
+ "epoch": 0.22604102487628572,
178
+ "grad_norm": 0.315909743309021,
179
+ "learning_rate": 0.00015483952013064506,
180
+ "loss": 0.9326,
181
+ "step": 3600
182
+ },
183
+ {
184
+ "epoch": 0.22604102487628572,
185
+ "eval_loss": 0.9352145195007324,
186
+ "eval_runtime": 299.9991,
187
+ "eval_samples_per_second": 17.163,
188
+ "eval_steps_per_second": 2.147,
189
+ "step": 3600
190
+ },
191
+ {
192
+ "epoch": 0.2448777769493095,
193
+ "grad_norm": 0.2997918128967285,
194
+ "learning_rate": 0.00015107091263111613,
195
+ "loss": 0.9298,
196
+ "step": 3900
197
+ },
198
+ {
199
+ "epoch": 0.2448777769493095,
200
+ "eval_loss": 0.9315630793571472,
201
+ "eval_runtime": 299.95,
202
+ "eval_samples_per_second": 17.166,
203
+ "eval_steps_per_second": 2.147,
204
+ "step": 3900
205
+ },
206
+ {
207
+ "epoch": 0.26371452902233333,
208
+ "grad_norm": 0.2730711102485657,
209
+ "learning_rate": 0.0001473023051315872,
210
+ "loss": 0.9345,
211
+ "step": 4200
212
+ },
213
+ {
214
+ "epoch": 0.26371452902233333,
215
+ "eval_loss": 0.9274590015411377,
216
+ "eval_runtime": 300.1027,
217
+ "eval_samples_per_second": 17.157,
218
+ "eval_steps_per_second": 2.146,
219
+ "step": 4200
220
+ },
221
+ {
222
+ "epoch": 0.28255128109535715,
223
+ "grad_norm": 0.27338674664497375,
224
+ "learning_rate": 0.0001435336976320583,
225
+ "loss": 0.9378,
226
+ "step": 4500
227
+ },
228
+ {
229
+ "epoch": 0.28255128109535715,
230
+ "eval_loss": 0.9236754775047302,
231
+ "eval_runtime": 299.988,
232
+ "eval_samples_per_second": 17.164,
233
+ "eval_steps_per_second": 2.147,
234
+ "step": 4500
235
+ },
236
+ {
237
+ "epoch": 0.3013880331683809,
238
+ "grad_norm": 0.3145460784435272,
239
+ "learning_rate": 0.00013976509013252937,
240
+ "loss": 0.9235,
241
+ "step": 4800
242
+ },
243
+ {
244
+ "epoch": 0.3013880331683809,
245
+ "eval_loss": 0.9199886322021484,
246
+ "eval_runtime": 299.9923,
247
+ "eval_samples_per_second": 17.164,
248
+ "eval_steps_per_second": 2.147,
249
+ "step": 4800
250
+ },
251
+ {
252
+ "epoch": 0.32022478524140474,
253
+ "grad_norm": 0.2656671702861786,
254
+ "learning_rate": 0.00013599648263300045,
255
+ "loss": 0.9207,
256
+ "step": 5100
257
+ },
258
+ {
259
+ "epoch": 0.32022478524140474,
260
+ "eval_loss": 0.9165565371513367,
261
+ "eval_runtime": 299.8304,
262
+ "eval_samples_per_second": 17.173,
263
+ "eval_steps_per_second": 2.148,
264
+ "step": 5100
265
+ },
266
+ {
267
+ "epoch": 0.33906153731442856,
268
+ "grad_norm": 0.2907351851463318,
269
+ "learning_rate": 0.00013222787513347153,
270
+ "loss": 0.9149,
271
+ "step": 5400
272
+ },
273
+ {
274
+ "epoch": 0.33906153731442856,
275
+ "eval_loss": 0.9132035374641418,
276
+ "eval_runtime": 299.8597,
277
+ "eval_samples_per_second": 17.171,
278
+ "eval_steps_per_second": 2.148,
279
+ "step": 5400
280
+ },
281
+ {
282
+ "epoch": 0.3578982893874524,
283
+ "grad_norm": 0.39790818095207214,
284
+ "learning_rate": 0.0001284592676339426,
285
+ "loss": 0.9063,
286
+ "step": 5700
287
+ },
288
+ {
289
+ "epoch": 0.3578982893874524,
290
+ "eval_loss": 0.9105966687202454,
291
+ "eval_runtime": 300.0175,
292
+ "eval_samples_per_second": 17.162,
293
+ "eval_steps_per_second": 2.147,
294
+ "step": 5700
295
+ },
296
+ {
297
+ "epoch": 0.37673504146047615,
298
+ "grad_norm": 0.3338871896266937,
299
+ "learning_rate": 0.00012469066013441369,
300
+ "loss": 0.9046,
301
+ "step": 6000
302
+ },
303
+ {
304
+ "epoch": 0.37673504146047615,
305
+ "eval_loss": 0.9074862003326416,
306
+ "eval_runtime": 299.8956,
307
+ "eval_samples_per_second": 17.169,
308
+ "eval_steps_per_second": 2.147,
309
+ "step": 6000
310
+ },
311
+ {
312
+ "epoch": 0.39557179353349997,
313
+ "grad_norm": 0.2925800383090973,
314
+ "learning_rate": 0.00012092205263488474,
315
+ "loss": 0.907,
316
+ "step": 6300
317
+ },
318
+ {
319
+ "epoch": 0.39557179353349997,
320
+ "eval_loss": 0.9044873118400574,
321
+ "eval_runtime": 300.0697,
322
+ "eval_samples_per_second": 17.159,
323
+ "eval_steps_per_second": 2.146,
324
+ "step": 6300
325
+ },
326
+ {
327
+ "epoch": 0.4144085456065238,
328
+ "grad_norm": 0.34801357984542847,
329
+ "learning_rate": 0.00011715344513535582,
330
+ "loss": 0.9042,
331
+ "step": 6600
332
+ },
333
+ {
334
+ "epoch": 0.4144085456065238,
335
+ "eval_loss": 0.9019830822944641,
336
+ "eval_runtime": 299.9421,
337
+ "eval_samples_per_second": 17.167,
338
+ "eval_steps_per_second": 2.147,
339
+ "step": 6600
340
+ },
341
+ {
342
+ "epoch": 0.4332452976795476,
343
+ "grad_norm": 0.3444356918334961,
344
+ "learning_rate": 0.0001133848376358269,
345
+ "loss": 0.9019,
346
+ "step": 6900
347
+ },
348
+ {
349
+ "epoch": 0.4332452976795476,
350
+ "eval_loss": 0.8995754718780518,
351
+ "eval_runtime": 299.921,
352
+ "eval_samples_per_second": 17.168,
353
+ "eval_steps_per_second": 2.147,
354
+ "step": 6900
355
+ },
356
+ {
357
+ "epoch": 0.45208204975257144,
358
+ "grad_norm": 0.3366526961326599,
359
+ "learning_rate": 0.00010961623013629799,
360
+ "loss": 0.9041,
361
+ "step": 7200
362
+ },
363
+ {
364
+ "epoch": 0.45208204975257144,
365
+ "eval_loss": 0.8974488973617554,
366
+ "eval_runtime": 299.9169,
367
+ "eval_samples_per_second": 17.168,
368
+ "eval_steps_per_second": 2.147,
369
+ "step": 7200
370
+ },
371
+ {
372
+ "epoch": 0.4709188018255952,
373
+ "grad_norm": 0.34138697385787964,
374
+ "learning_rate": 0.00010584762263676907,
375
+ "loss": 0.9001,
376
+ "step": 7500
377
+ },
378
+ {
379
+ "epoch": 0.4709188018255952,
380
+ "eval_loss": 0.8951303958892822,
381
+ "eval_runtime": 299.8867,
382
+ "eval_samples_per_second": 17.17,
383
+ "eval_steps_per_second": 2.147,
384
+ "step": 7500
385
+ },
386
+ {
387
+ "epoch": 0.489755553898619,
388
+ "grad_norm": 0.35338446497917175,
389
+ "learning_rate": 0.00010207901513724012,
390
+ "loss": 0.8962,
391
+ "step": 7800
392
+ },
393
+ {
394
+ "epoch": 0.489755553898619,
395
+ "eval_loss": 0.8931267261505127,
396
+ "eval_runtime": 300.0707,
397
+ "eval_samples_per_second": 17.159,
398
+ "eval_steps_per_second": 2.146,
399
+ "step": 7800
400
+ },
401
+ {
402
+ "epoch": 0.5085923059716428,
403
+ "grad_norm": 0.33024904131889343,
404
+ "learning_rate": 9.83104076377112e-05,
405
+ "loss": 0.901,
406
+ "step": 8100
407
+ },
408
+ {
409
+ "epoch": 0.5085923059716428,
410
+ "eval_loss": 0.8908406496047974,
411
+ "eval_runtime": 300.0908,
412
+ "eval_samples_per_second": 17.158,
413
+ "eval_steps_per_second": 2.146,
414
+ "step": 8100
415
+ },
416
+ {
417
+ "epoch": 0.5274290580446667,
418
+ "grad_norm": 0.30269181728363037,
419
+ "learning_rate": 9.454180013818228e-05,
420
+ "loss": 0.8886,
421
+ "step": 8400
422
+ },
423
+ {
424
+ "epoch": 0.5274290580446667,
425
+ "eval_loss": 0.8892831802368164,
426
+ "eval_runtime": 299.9819,
427
+ "eval_samples_per_second": 17.164,
428
+ "eval_steps_per_second": 2.147,
429
+ "step": 8400
430
+ },
431
+ {
432
+ "epoch": 0.5462658101176905,
433
+ "grad_norm": 0.32455185055732727,
434
+ "learning_rate": 9.077319263865335e-05,
435
+ "loss": 0.8823,
436
+ "step": 8700
437
+ },
438
+ {
439
+ "epoch": 0.5462658101176905,
440
+ "eval_loss": 0.887444019317627,
441
+ "eval_runtime": 300.1485,
442
+ "eval_samples_per_second": 17.155,
443
+ "eval_steps_per_second": 2.146,
444
+ "step": 8700
445
+ },
446
+ {
447
+ "epoch": 0.5651025621907143,
448
+ "grad_norm": 0.32726097106933594,
449
+ "learning_rate": 8.700458513912443e-05,
450
+ "loss": 0.8773,
451
+ "step": 9000
452
+ },
453
+ {
454
+ "epoch": 0.5651025621907143,
455
+ "eval_loss": 0.885347306728363,
456
+ "eval_runtime": 300.0218,
457
+ "eval_samples_per_second": 17.162,
458
+ "eval_steps_per_second": 2.147,
459
+ "step": 9000
460
+ },
461
+ {
462
+ "epoch": 0.5839393142637381,
463
+ "grad_norm": 0.3211737275123596,
464
+ "learning_rate": 8.323597763959551e-05,
465
+ "loss": 0.8876,
466
+ "step": 9300
467
+ },
468
+ {
469
+ "epoch": 0.5839393142637381,
470
+ "eval_loss": 0.8837311267852783,
471
+ "eval_runtime": 299.8508,
472
+ "eval_samples_per_second": 17.172,
473
+ "eval_steps_per_second": 2.148,
474
+ "step": 9300
475
+ },
476
+ {
477
+ "epoch": 0.6027760663367618,
478
+ "grad_norm": 0.3470586836338043,
479
+ "learning_rate": 7.946737014006658e-05,
480
+ "loss": 0.888,
481
+ "step": 9600
482
+ },
483
+ {
484
+ "epoch": 0.6027760663367618,
485
+ "eval_loss": 0.8818086981773376,
486
+ "eval_runtime": 299.9724,
487
+ "eval_samples_per_second": 17.165,
488
+ "eval_steps_per_second": 2.147,
489
+ "step": 9600
490
+ },
491
+ {
492
+ "epoch": 0.6216128184097857,
493
+ "grad_norm": 0.3012458384037018,
494
+ "learning_rate": 7.569876264053766e-05,
495
+ "loss": 0.8833,
496
+ "step": 9900
497
+ },
498
+ {
499
+ "epoch": 0.6216128184097857,
500
+ "eval_loss": 0.8803924322128296,
501
+ "eval_runtime": 300.0969,
502
+ "eval_samples_per_second": 17.158,
503
+ "eval_steps_per_second": 2.146,
504
+ "step": 9900
505
+ },
506
+ {
507
+ "epoch": 0.6404495704828095,
508
+ "grad_norm": 0.32445794343948364,
509
+ "learning_rate": 7.194271716600717e-05,
510
+ "loss": 0.8841,
511
+ "step": 10200
512
+ },
513
+ {
514
+ "epoch": 0.6404495704828095,
515
+ "eval_loss": 0.8785931468009949,
516
+ "eval_runtime": 299.8302,
517
+ "eval_samples_per_second": 17.173,
518
+ "eval_steps_per_second": 2.148,
519
+ "step": 10200
520
+ },
521
+ {
522
+ "epoch": 0.6592863225558333,
523
+ "grad_norm": 0.33264926075935364,
524
+ "learning_rate": 6.817410966647824e-05,
525
+ "loss": 0.8852,
526
+ "step": 10500
527
+ },
528
+ {
529
+ "epoch": 0.6592863225558333,
530
+ "eval_loss": 0.8771566152572632,
531
+ "eval_runtime": 300.0665,
532
+ "eval_samples_per_second": 17.16,
533
+ "eval_steps_per_second": 2.146,
534
+ "step": 10500
535
+ },
536
+ {
537
+ "epoch": 0.6781230746288571,
538
+ "grad_norm": 0.3084549307823181,
539
+ "learning_rate": 6.440550216694932e-05,
540
+ "loss": 0.8793,
541
+ "step": 10800
542
+ },
543
+ {
544
+ "epoch": 0.6781230746288571,
545
+ "eval_loss": 0.8756351470947266,
546
+ "eval_runtime": 300.155,
547
+ "eval_samples_per_second": 17.154,
548
+ "eval_steps_per_second": 2.146,
549
+ "step": 10800
550
+ },
551
+ {
552
+ "epoch": 0.696959826701881,
553
+ "grad_norm": 0.3315499722957611,
554
+ "learning_rate": 6.0636894667420396e-05,
555
+ "loss": 0.8687,
556
+ "step": 11100
557
+ },
558
+ {
559
+ "epoch": 0.696959826701881,
560
+ "eval_loss": 0.8744714260101318,
561
+ "eval_runtime": 300.5183,
562
+ "eval_samples_per_second": 17.134,
563
+ "eval_steps_per_second": 2.143,
564
+ "step": 11100
565
+ },
566
+ {
567
+ "epoch": 0.7157965787749048,
568
+ "grad_norm": 0.35962772369384766,
569
+ "learning_rate": 5.686828716789147e-05,
570
+ "loss": 0.8631,
571
+ "step": 11400
572
+ },
573
+ {
574
+ "epoch": 0.7157965787749048,
575
+ "eval_loss": 0.8730462789535522,
576
+ "eval_runtime": 299.7837,
577
+ "eval_samples_per_second": 17.176,
578
+ "eval_steps_per_second": 2.148,
579
+ "step": 11400
580
+ },
581
+ {
582
+ "epoch": 0.7346333308479286,
583
+ "grad_norm": 0.33538639545440674,
584
+ "learning_rate": 5.3099679668362547e-05,
585
+ "loss": 0.879,
586
+ "step": 11700
587
+ },
588
+ {
589
+ "epoch": 0.7346333308479286,
590
+ "eval_loss": 0.8714411854743958,
591
+ "eval_runtime": 299.9502,
592
+ "eval_samples_per_second": 17.166,
593
+ "eval_steps_per_second": 2.147,
594
+ "step": 11700
595
+ },
596
+ {
597
+ "epoch": 0.7534700829209523,
598
+ "grad_norm": 0.3434339165687561,
599
+ "learning_rate": 4.933107216883362e-05,
600
+ "loss": 0.8616,
601
+ "step": 12000
602
+ },
603
+ {
604
+ "epoch": 0.7534700829209523,
605
+ "eval_loss": 0.8703322410583496,
606
+ "eval_runtime": 300.0139,
607
+ "eval_samples_per_second": 17.163,
608
+ "eval_steps_per_second": 2.147,
609
+ "step": 12000
610
+ },
611
+ {
612
+ "epoch": 0.7723068349939761,
613
+ "grad_norm": 0.34114760160446167,
614
+ "learning_rate": 4.55624646693047e-05,
615
+ "loss": 0.8708,
616
+ "step": 12300
617
+ },
618
+ {
619
+ "epoch": 0.7723068349939761,
620
+ "eval_loss": 0.8692737817764282,
621
+ "eval_runtime": 299.9274,
622
+ "eval_samples_per_second": 17.167,
623
+ "eval_steps_per_second": 2.147,
624
+ "step": 12300
625
+ },
626
+ {
627
+ "epoch": 0.7911435870669999,
628
+ "grad_norm": 0.40352341532707214,
629
+ "learning_rate": 4.18064191947742e-05,
630
+ "loss": 0.8724,
631
+ "step": 12600
632
+ },
633
+ {
634
+ "epoch": 0.7911435870669999,
635
+ "eval_loss": 0.8681650161743164,
636
+ "eval_runtime": 300.4231,
637
+ "eval_samples_per_second": 17.139,
638
+ "eval_steps_per_second": 2.144,
639
+ "step": 12600
640
+ },
641
+ {
642
+ "epoch": 0.8099803391400238,
643
+ "grad_norm": 0.36962220072746277,
644
+ "learning_rate": 3.8037811695245274e-05,
645
+ "loss": 0.8672,
646
+ "step": 12900
647
+ },
648
+ {
649
+ "epoch": 0.8099803391400238,
650
+ "eval_loss": 0.8672531247138977,
651
+ "eval_runtime": 299.8101,
652
+ "eval_samples_per_second": 17.174,
653
+ "eval_steps_per_second": 2.148,
654
+ "step": 12900
655
+ },
656
+ {
657
+ "epoch": 0.8288170912130476,
658
+ "grad_norm": 0.4042891561985016,
659
+ "learning_rate": 3.426920419571635e-05,
660
+ "loss": 0.8643,
661
+ "step": 13200
662
+ },
663
+ {
664
+ "epoch": 0.8288170912130476,
665
+ "eval_loss": 0.8664665818214417,
666
+ "eval_runtime": 299.8585,
667
+ "eval_samples_per_second": 17.171,
668
+ "eval_steps_per_second": 2.148,
669
+ "step": 13200
670
+ },
671
+ {
672
+ "epoch": 0.8476538432860714,
673
+ "grad_norm": 0.2992730140686035,
674
+ "learning_rate": 3.0500596696187428e-05,
675
+ "loss": 0.8632,
676
+ "step": 13500
677
+ },
678
+ {
679
+ "epoch": 0.8476538432860714,
680
+ "eval_loss": 0.8653113842010498,
681
+ "eval_runtime": 299.946,
682
+ "eval_samples_per_second": 17.166,
683
+ "eval_steps_per_second": 2.147,
684
+ "step": 13500
685
+ },
686
+ {
687
+ "epoch": 0.8664905953590952,
688
+ "grad_norm": 0.31725963950157166,
689
+ "learning_rate": 2.6731989196658503e-05,
690
+ "loss": 0.8564,
691
+ "step": 13800
692
+ },
693
+ {
694
+ "epoch": 0.8664905953590952,
695
+ "eval_loss": 0.8644812107086182,
696
+ "eval_runtime": 299.8536,
697
+ "eval_samples_per_second": 17.172,
698
+ "eval_steps_per_second": 2.148,
699
+ "step": 13800
700
+ },
701
+ {
702
+ "epoch": 0.885327347432119,
703
+ "grad_norm": 0.3101350963115692,
704
+ "learning_rate": 2.296338169712958e-05,
705
+ "loss": 0.861,
706
+ "step": 14100
707
+ },
708
+ {
709
+ "epoch": 0.885327347432119,
710
+ "eval_loss": 0.8637036085128784,
711
+ "eval_runtime": 300.356,
712
+ "eval_samples_per_second": 17.143,
713
+ "eval_steps_per_second": 2.144,
714
+ "step": 14100
715
+ },
716
+ {
717
+ "epoch": 0.9041640995051429,
718
+ "grad_norm": 0.33058223128318787,
719
+ "learning_rate": 1.9194774197600654e-05,
720
+ "loss": 0.8543,
721
+ "step": 14400
722
+ },
723
+ {
724
+ "epoch": 0.9041640995051429,
725
+ "eval_loss": 0.8630216121673584,
726
+ "eval_runtime": 299.9507,
727
+ "eval_samples_per_second": 17.166,
728
+ "eval_steps_per_second": 2.147,
729
+ "step": 14400
730
+ },
731
+ {
732
+ "epoch": 0.9230008515781666,
733
+ "grad_norm": 0.35784465074539185,
734
+ "learning_rate": 1.5438728723070158e-05,
735
+ "loss": 0.868,
736
+ "step": 14700
737
+ },
738
+ {
739
+ "epoch": 0.9230008515781666,
740
+ "eval_loss": 0.8623820543289185,
741
+ "eval_runtime": 299.933,
742
+ "eval_samples_per_second": 17.167,
743
+ "eval_steps_per_second": 2.147,
744
+ "step": 14700
745
+ },
746
+ {
747
+ "epoch": 0.9418376036511904,
748
+ "grad_norm": 0.3938862383365631,
749
+ "learning_rate": 1.1670121223541235e-05,
750
+ "loss": 0.8607,
751
+ "step": 15000
752
+ },
753
+ {
754
+ "epoch": 0.9418376036511904,
755
+ "eval_loss": 0.861863911151886,
756
+ "eval_runtime": 299.8746,
757
+ "eval_samples_per_second": 17.171,
758
+ "eval_steps_per_second": 2.148,
759
+ "step": 15000
760
+ },
761
+ {
762
+ "epoch": 0.9606743557242142,
763
+ "grad_norm": 0.3867338001728058,
764
+ "learning_rate": 7.90151372401231e-06,
765
+ "loss": 0.8491,
766
+ "step": 15300
767
+ },
768
+ {
769
+ "epoch": 0.9606743557242142,
770
+ "eval_loss": 0.8613755106925964,
771
+ "eval_runtime": 299.919,
772
+ "eval_samples_per_second": 17.168,
773
+ "eval_steps_per_second": 2.147,
774
+ "step": 15300
775
+ },
776
+ {
777
+ "epoch": 0.979511107797238,
778
+ "grad_norm": 0.3372841477394104,
779
+ "learning_rate": 4.132906224483387e-06,
780
+ "loss": 0.8643,
781
+ "step": 15600
782
+ },
783
+ {
784
+ "epoch": 0.979511107797238,
785
+ "eval_loss": 0.8610811829566956,
786
+ "eval_runtime": 299.8287,
787
+ "eval_samples_per_second": 17.173,
788
+ "eval_steps_per_second": 2.148,
789
+ "step": 15600
790
+ },
791
+ {
792
+ "epoch": 0.9983478598702619,
793
+ "grad_norm": 0.3431134819984436,
794
+ "learning_rate": 3.642987249544627e-07,
795
+ "loss": 0.8633,
796
+ "step": 15900
797
+ },
798
+ {
799
+ "epoch": 0.9983478598702619,
800
+ "eval_loss": 0.8609164953231812,
801
+ "eval_runtime": 299.9008,
802
+ "eval_samples_per_second": 17.169,
803
+ "eval_steps_per_second": 2.147,
804
+ "step": 15900
805
+ }
806
+ ],
807
+ "logging_steps": 300,
808
+ "max_steps": 15926,
809
+ "num_input_tokens_seen": 0,
810
+ "num_train_epochs": 1,
811
+ "save_steps": 300,
812
+ "stateful_callbacks": {
813
+ "TrainerControl": {
814
+ "args": {
815
+ "should_epoch_stop": false,
816
+ "should_evaluate": false,
817
+ "should_log": false,
818
+ "should_save": true,
819
+ "should_training_stop": true
820
+ },
821
+ "attributes": {}
822
+ }
823
+ },
824
+ "total_flos": 4.1684162719241994e+18,
825
+ "train_batch_size": 2,
826
+ "trial_name": null,
827
+ "trial_params": null
828
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f203c239c4cec4ae0f20b8df027141ae6e9dc293c497c04f5b902ecf835d5f65
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff