FrAnKu34t23 commited on
Commit
35cb202
·
verified ·
1 Parent(s): 681a296

Upload merged fine-tuned risk prediction model

Browse files
Files changed (50) hide show
  1. README.md +207 -0
  2. adapter_config.json +37 -0
  3. adapter_model.safetensors +3 -0
  4. checkpoint-1050/README.md +207 -0
  5. checkpoint-1050/adapter_config.json +37 -0
  6. checkpoint-1050/adapter_model.safetensors +3 -0
  7. checkpoint-1050/merges.txt +0 -0
  8. checkpoint-1050/optimizer.pt +3 -0
  9. checkpoint-1050/rng_state.pth +3 -0
  10. checkpoint-1050/scheduler.pt +3 -0
  11. checkpoint-1050/special_tokens_map.json +6 -0
  12. checkpoint-1050/tokenizer.json +0 -0
  13. checkpoint-1050/tokenizer_config.json +21 -0
  14. checkpoint-1050/trainer_state.json +776 -0
  15. checkpoint-1050/training_args.bin +3 -0
  16. checkpoint-1050/vocab.json +0 -0
  17. checkpoint-1100/README.md +207 -0
  18. checkpoint-1100/adapter_config.json +37 -0
  19. checkpoint-1100/adapter_model.safetensors +3 -0
  20. checkpoint-1100/merges.txt +0 -0
  21. checkpoint-1100/optimizer.pt +3 -0
  22. checkpoint-1100/rng_state.pth +3 -0
  23. checkpoint-1100/scheduler.pt +3 -0
  24. checkpoint-1100/special_tokens_map.json +6 -0
  25. checkpoint-1100/tokenizer.json +0 -0
  26. checkpoint-1100/tokenizer_config.json +21 -0
  27. checkpoint-1100/trainer_state.json +811 -0
  28. checkpoint-1100/training_args.bin +3 -0
  29. checkpoint-1100/vocab.json +0 -0
  30. checkpoint-1104/README.md +207 -0
  31. checkpoint-1104/adapter_config.json +37 -0
  32. checkpoint-1104/adapter_model.safetensors +3 -0
  33. checkpoint-1104/merges.txt +0 -0
  34. checkpoint-1104/optimizer.pt +3 -0
  35. checkpoint-1104/rng_state.pth +3 -0
  36. checkpoint-1104/scheduler.pt +3 -0
  37. checkpoint-1104/special_tokens_map.json +6 -0
  38. checkpoint-1104/tokenizer.json +0 -0
  39. checkpoint-1104/tokenizer_config.json +21 -0
  40. checkpoint-1104/trainer_state.json +811 -0
  41. checkpoint-1104/training_args.bin +3 -0
  42. checkpoint-1104/vocab.json +0 -0
  43. merges.txt +0 -0
  44. runs/Aug11_08-00-49_32f9660e4c7f/events.out.tfevents.1754899250.32f9660e4c7f.357.1 +3 -0
  45. special_tokens_map.json +6 -0
  46. tokenizer.json +0 -0
  47. tokenizer_config.json +21 -0
  48. training_args.bin +3 -0
  49. training_metadata.json +24 -0
  50. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: distilgpt2
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:distilgpt2
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.17.0
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "distilgpt2",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "c_proj",
29
+ "c_attn"
30
+ ],
31
+ "target_parameters": null,
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_qalora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1813de2f5341cddcec1cb95f398491e59df450771f1625e60fa7561ee908327c
3
+ size 1626544
checkpoint-1050/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: distilgpt2
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:distilgpt2
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.17.0
checkpoint-1050/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "distilgpt2",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "c_proj",
29
+ "c_attn"
30
+ ],
31
+ "target_parameters": null,
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_qalora": false,
36
+ "use_rslora": false
37
+ }
checkpoint-1050/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76633f832d13c262c7a8d8b2dc1e74a3ceb4f8b97d55e3c953342c096bac3368
3
+ size 1626544
checkpoint-1050/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1050/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8647ec24d9faf872388f3b68deefdffd97ee6a8a3d81425e755a85334a1c62ea
3
+ size 3274682
checkpoint-1050/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c75fa6a77f151dbde4e3365bc160e3cbbf022d7cb62f21eea24db34f045a6d7
3
+ size 14244
checkpoint-1050/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07f0dc40235fb682a158cb0e23804d6f41ae229549da5302c63fd7000cefe505
3
+ size 1064
checkpoint-1050/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-1050/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1050/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-1050/trainer_state.json ADDED
@@ -0,0 +1,776 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 7.608695652173913,
6
+ "eval_steps": 50,
7
+ "global_step": 1050,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.007246376811594203,
14
+ "grad_norm": 1.9687033891677856,
15
+ "learning_rate": 0.0,
16
+ "loss": 19.2682,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.07246376811594203,
21
+ "grad_norm": 1.703112006187439,
22
+ "learning_rate": 1.8e-05,
23
+ "loss": 12.4529,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.14492753623188406,
28
+ "grad_norm": 3.6209306716918945,
29
+ "learning_rate": 3.8e-05,
30
+ "loss": 17.5169,
31
+ "step": 20
32
+ },
33
+ {
34
+ "epoch": 0.21739130434782608,
35
+ "grad_norm": 2.09627366065979,
36
+ "learning_rate": 5.8e-05,
37
+ "loss": 16.0619,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 0.2898550724637681,
42
+ "grad_norm": 1.9405275583267212,
43
+ "learning_rate": 7.800000000000001e-05,
44
+ "loss": 20.228,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 0.36231884057971014,
49
+ "grad_norm": 8.32076644897461,
50
+ "learning_rate": 9.8e-05,
51
+ "loss": 16.0457,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.43478260869565216,
56
+ "grad_norm": 1.1994603872299194,
57
+ "learning_rate": 9.9146110056926e-05,
58
+ "loss": 15.9109,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.5072463768115942,
63
+ "grad_norm": 1.3328566551208496,
64
+ "learning_rate": 9.819734345351043e-05,
65
+ "loss": 15.6408,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.5797101449275363,
70
+ "grad_norm": 6.663642406463623,
71
+ "learning_rate": 9.724857685009489e-05,
72
+ "loss": 13.4492,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.6521739130434783,
77
+ "grad_norm": 4.154050350189209,
78
+ "learning_rate": 9.629981024667933e-05,
79
+ "loss": 16.0048,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.7246376811594203,
84
+ "grad_norm": 12.047609329223633,
85
+ "learning_rate": 9.535104364326376e-05,
86
+ "loss": 42.9753,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.7971014492753623,
91
+ "grad_norm": 4.798079490661621,
92
+ "learning_rate": 9.44022770398482e-05,
93
+ "loss": 17.2692,
94
+ "step": 110
95
+ },
96
+ {
97
+ "epoch": 0.8695652173913043,
98
+ "grad_norm": 6.930491924285889,
99
+ "learning_rate": 9.345351043643265e-05,
100
+ "loss": 13.9401,
101
+ "step": 120
102
+ },
103
+ {
104
+ "epoch": 0.9420289855072463,
105
+ "grad_norm": 7.896566867828369,
106
+ "learning_rate": 9.250474383301708e-05,
107
+ "loss": 16.1242,
108
+ "step": 130
109
+ },
110
+ {
111
+ "epoch": 1.0144927536231885,
112
+ "grad_norm": 10.504218101501465,
113
+ "learning_rate": 9.155597722960152e-05,
114
+ "loss": 9.8417,
115
+ "step": 140
116
+ },
117
+ {
118
+ "epoch": 1.0869565217391304,
119
+ "grad_norm": 9.594452857971191,
120
+ "learning_rate": 9.060721062618596e-05,
121
+ "loss": 12.6395,
122
+ "step": 150
123
+ },
124
+ {
125
+ "epoch": 1.1594202898550725,
126
+ "grad_norm": 16.113290786743164,
127
+ "learning_rate": 8.96584440227704e-05,
128
+ "loss": 11.6141,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 1.2318840579710144,
133
+ "grad_norm": 10.904824256896973,
134
+ "learning_rate": 8.870967741935484e-05,
135
+ "loss": 15.8041,
136
+ "step": 170
137
+ },
138
+ {
139
+ "epoch": 1.3043478260869565,
140
+ "grad_norm": 4.2903852462768555,
141
+ "learning_rate": 8.776091081593929e-05,
142
+ "loss": 10.5756,
143
+ "step": 180
144
+ },
145
+ {
146
+ "epoch": 1.3768115942028984,
147
+ "grad_norm": 3.3363027572631836,
148
+ "learning_rate": 8.681214421252373e-05,
149
+ "loss": 12.2632,
150
+ "step": 190
151
+ },
152
+ {
153
+ "epoch": 1.4492753623188406,
154
+ "grad_norm": 5.582556247711182,
155
+ "learning_rate": 8.586337760910817e-05,
156
+ "loss": 10.2026,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 1.5217391304347827,
161
+ "grad_norm": 3.090460777282715,
162
+ "learning_rate": 8.49146110056926e-05,
163
+ "loss": 9.8113,
164
+ "step": 210
165
+ },
166
+ {
167
+ "epoch": 1.5942028985507246,
168
+ "grad_norm": 20.330148696899414,
169
+ "learning_rate": 8.396584440227704e-05,
170
+ "loss": 9.2478,
171
+ "step": 220
172
+ },
173
+ {
174
+ "epoch": 1.6666666666666665,
175
+ "grad_norm": 16.418106079101562,
176
+ "learning_rate": 8.301707779886149e-05,
177
+ "loss": 11.377,
178
+ "step": 230
179
+ },
180
+ {
181
+ "epoch": 1.7391304347826086,
182
+ "grad_norm": 1.9852267503738403,
183
+ "learning_rate": 8.206831119544592e-05,
184
+ "loss": 9.8674,
185
+ "step": 240
186
+ },
187
+ {
188
+ "epoch": 1.8115942028985508,
189
+ "grad_norm": 4.2618489265441895,
190
+ "learning_rate": 8.111954459203036e-05,
191
+ "loss": 10.9124,
192
+ "step": 250
193
+ },
194
+ {
195
+ "epoch": 1.8840579710144927,
196
+ "grad_norm": 5.334084510803223,
197
+ "learning_rate": 8.017077798861481e-05,
198
+ "loss": 29.9208,
199
+ "step": 260
200
+ },
201
+ {
202
+ "epoch": 1.9565217391304348,
203
+ "grad_norm": 7.662145614624023,
204
+ "learning_rate": 7.922201138519924e-05,
205
+ "loss": 9.4491,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 2.028985507246377,
210
+ "grad_norm": 2.990098476409912,
211
+ "learning_rate": 7.827324478178368e-05,
212
+ "loss": 12.7051,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 2.101449275362319,
217
+ "grad_norm": 11.343267440795898,
218
+ "learning_rate": 7.732447817836812e-05,
219
+ "loss": 10.1094,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 2.1739130434782608,
224
+ "grad_norm": 4.076178550720215,
225
+ "learning_rate": 7.637571157495257e-05,
226
+ "loss": 10.8557,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 2.246376811594203,
231
+ "grad_norm": 3.965240240097046,
232
+ "learning_rate": 7.542694497153701e-05,
233
+ "loss": 10.2597,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 2.318840579710145,
238
+ "grad_norm": 16.37909507751465,
239
+ "learning_rate": 7.447817836812145e-05,
240
+ "loss": 9.0119,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 2.391304347826087,
245
+ "grad_norm": 3.6150219440460205,
246
+ "learning_rate": 7.352941176470589e-05,
247
+ "loss": 26.6018,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 2.463768115942029,
252
+ "grad_norm": 19.880943298339844,
253
+ "learning_rate": 7.258064516129033e-05,
254
+ "loss": 9.6189,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 2.536231884057971,
259
+ "grad_norm": 3.5458195209503174,
260
+ "learning_rate": 7.163187855787477e-05,
261
+ "loss": 8.4988,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 2.608695652173913,
266
+ "grad_norm": 13.963035583496094,
267
+ "learning_rate": 7.06831119544592e-05,
268
+ "loss": 11.8011,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 2.681159420289855,
273
+ "grad_norm": 19.048301696777344,
274
+ "learning_rate": 6.973434535104365e-05,
275
+ "loss": 10.9278,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 2.753623188405797,
280
+ "grad_norm": 4.992802143096924,
281
+ "learning_rate": 6.878557874762808e-05,
282
+ "loss": 8.919,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 2.8260869565217392,
287
+ "grad_norm": 11.363718032836914,
288
+ "learning_rate": 6.783681214421252e-05,
289
+ "loss": 13.1761,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 2.898550724637681,
294
+ "grad_norm": 5.374908924102783,
295
+ "learning_rate": 6.688804554079696e-05,
296
+ "loss": 10.3222,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 2.971014492753623,
301
+ "grad_norm": 8.949808120727539,
302
+ "learning_rate": 6.59392789373814e-05,
303
+ "loss": 10.7587,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 3.0434782608695654,
308
+ "grad_norm": 4.645139217376709,
309
+ "learning_rate": 6.499051233396585e-05,
310
+ "loss": 7.0093,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 3.1159420289855073,
315
+ "grad_norm": 1.7357378005981445,
316
+ "learning_rate": 6.404174573055029e-05,
317
+ "loss": 10.5791,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 3.1884057971014492,
322
+ "grad_norm": 6.632950305938721,
323
+ "learning_rate": 6.309297912713473e-05,
324
+ "loss": 8.7916,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 3.260869565217391,
329
+ "grad_norm": 3.3891420364379883,
330
+ "learning_rate": 6.214421252371917e-05,
331
+ "loss": 10.3499,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 3.3333333333333335,
336
+ "grad_norm": 10.14654541015625,
337
+ "learning_rate": 6.119544592030361e-05,
338
+ "loss": 8.5833,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 3.4057971014492754,
343
+ "grad_norm": 3.27583384513855,
344
+ "learning_rate": 6.0246679316888046e-05,
345
+ "loss": 28.3443,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 3.4782608695652173,
350
+ "grad_norm": 16.218280792236328,
351
+ "learning_rate": 5.9297912713472494e-05,
352
+ "loss": 11.3033,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 3.550724637681159,
357
+ "grad_norm": 5.851198196411133,
358
+ "learning_rate": 5.834914611005693e-05,
359
+ "loss": 7.5228,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 3.6231884057971016,
364
+ "grad_norm": 13.043642044067383,
365
+ "learning_rate": 5.740037950664137e-05,
366
+ "loss": 11.608,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 3.6956521739130435,
371
+ "grad_norm": 3.651071071624756,
372
+ "learning_rate": 5.645161290322582e-05,
373
+ "loss": 9.3775,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 3.7681159420289854,
378
+ "grad_norm": 3.946401357650757,
379
+ "learning_rate": 5.550284629981025e-05,
380
+ "loss": 9.9621,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 3.8405797101449277,
385
+ "grad_norm": 5.363879680633545,
386
+ "learning_rate": 5.4554079696394686e-05,
387
+ "loss": 7.2515,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 3.9130434782608696,
392
+ "grad_norm": 18.565500259399414,
393
+ "learning_rate": 5.360531309297913e-05,
394
+ "loss": 9.9015,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 3.9855072463768115,
399
+ "grad_norm": 2.068690299987793,
400
+ "learning_rate": 5.2656546489563575e-05,
401
+ "loss": 8.6521,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 4.057971014492754,
406
+ "grad_norm": 8.377117156982422,
407
+ "learning_rate": 5.170777988614801e-05,
408
+ "loss": 11.6352,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 4.130434782608695,
413
+ "grad_norm": 6.822054386138916,
414
+ "learning_rate": 5.075901328273245e-05,
415
+ "loss": 8.9412,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 4.202898550724638,
420
+ "grad_norm": 17.24335479736328,
421
+ "learning_rate": 4.981024667931689e-05,
422
+ "loss": 9.5539,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 4.27536231884058,
427
+ "grad_norm": 13.434685707092285,
428
+ "learning_rate": 4.8861480075901326e-05,
429
+ "loss": 10.8367,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 4.3478260869565215,
434
+ "grad_norm": 17.375398635864258,
435
+ "learning_rate": 4.791271347248577e-05,
436
+ "loss": 10.818,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 4.420289855072464,
441
+ "grad_norm": 4.53552770614624,
442
+ "learning_rate": 4.6963946869070216e-05,
443
+ "loss": 7.442,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 4.492753623188406,
448
+ "grad_norm": 4.74644136428833,
449
+ "learning_rate": 4.601518026565465e-05,
450
+ "loss": 9.6362,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 4.565217391304348,
455
+ "grad_norm": 3.9156153202056885,
456
+ "learning_rate": 4.506641366223909e-05,
457
+ "loss": 11.4203,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 4.63768115942029,
462
+ "grad_norm": 18.31324005126953,
463
+ "learning_rate": 4.411764705882353e-05,
464
+ "loss": 8.557,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 4.710144927536232,
469
+ "grad_norm": 4.924636363983154,
470
+ "learning_rate": 4.3168880455407974e-05,
471
+ "loss": 9.608,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 4.782608695652174,
476
+ "grad_norm": 5.3758769035339355,
477
+ "learning_rate": 4.222011385199241e-05,
478
+ "loss": 8.9764,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 4.855072463768116,
483
+ "grad_norm": 8.584567070007324,
484
+ "learning_rate": 4.1271347248576856e-05,
485
+ "loss": 9.621,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 4.927536231884058,
490
+ "grad_norm": 4.82368803024292,
491
+ "learning_rate": 4.032258064516129e-05,
492
+ "loss": 24.5753,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 5.0,
497
+ "grad_norm": 2.3411295413970947,
498
+ "learning_rate": 3.937381404174573e-05,
499
+ "loss": 7.9662,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 5.072463768115942,
504
+ "grad_norm": 3.99580979347229,
505
+ "learning_rate": 3.842504743833017e-05,
506
+ "loss": 6.8737,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 5.144927536231884,
511
+ "grad_norm": 24.173742294311523,
512
+ "learning_rate": 3.7476280834914614e-05,
513
+ "loss": 11.8038,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 5.217391304347826,
518
+ "grad_norm": 25.25533676147461,
519
+ "learning_rate": 3.6527514231499055e-05,
520
+ "loss": 11.9047,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 5.2898550724637685,
525
+ "grad_norm": 4.739432334899902,
526
+ "learning_rate": 3.557874762808349e-05,
527
+ "loss": 9.503,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 5.36231884057971,
532
+ "grad_norm": 7.874780178070068,
533
+ "learning_rate": 3.462998102466794e-05,
534
+ "loss": 10.949,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 5.434782608695652,
539
+ "grad_norm": 3.363119602203369,
540
+ "learning_rate": 3.368121442125237e-05,
541
+ "loss": 10.2591,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 5.507246376811594,
546
+ "grad_norm": 5.406454086303711,
547
+ "learning_rate": 3.273244781783681e-05,
548
+ "loss": 7.7785,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 5.579710144927536,
553
+ "grad_norm": 6.118616580963135,
554
+ "learning_rate": 3.1783681214421254e-05,
555
+ "loss": 7.2315,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 5.6521739130434785,
560
+ "grad_norm": 16.83717918395996,
561
+ "learning_rate": 3.0834914611005695e-05,
562
+ "loss": 7.6301,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 5.72463768115942,
567
+ "grad_norm": 11.110983848571777,
568
+ "learning_rate": 2.9886148007590137e-05,
569
+ "loss": 9.153,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 5.797101449275362,
574
+ "grad_norm": 8.291231155395508,
575
+ "learning_rate": 2.8937381404174574e-05,
576
+ "loss": 10.3227,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 5.869565217391305,
581
+ "grad_norm": 2.8294785022735596,
582
+ "learning_rate": 2.7988614800759016e-05,
583
+ "loss": 6.8461,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 5.942028985507246,
588
+ "grad_norm": 11.522751808166504,
589
+ "learning_rate": 2.7039848197343453e-05,
590
+ "loss": 25.7992,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 6.0144927536231885,
595
+ "grad_norm": 5.239048480987549,
596
+ "learning_rate": 2.6091081593927898e-05,
597
+ "loss": 10.1367,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 6.086956521739131,
602
+ "grad_norm": 14.244694709777832,
603
+ "learning_rate": 2.5142314990512332e-05,
604
+ "loss": 8.1876,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 6.159420289855072,
609
+ "grad_norm": 3.612367868423462,
610
+ "learning_rate": 2.4193548387096777e-05,
611
+ "loss": 9.5329,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 6.231884057971015,
616
+ "grad_norm": 4.118394374847412,
617
+ "learning_rate": 2.3244781783681215e-05,
618
+ "loss": 8.8621,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 6.304347826086957,
623
+ "grad_norm": 2.245436906814575,
624
+ "learning_rate": 2.2296015180265656e-05,
625
+ "loss": 7.363,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 6.3768115942028984,
630
+ "grad_norm": 7.4832658767700195,
631
+ "learning_rate": 2.1347248576850097e-05,
632
+ "loss": 8.4077,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 6.449275362318841,
637
+ "grad_norm": 20.146770477294922,
638
+ "learning_rate": 2.0398481973434535e-05,
639
+ "loss": 27.7444,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 6.521739130434782,
644
+ "grad_norm": 6.686460018157959,
645
+ "learning_rate": 1.9449715370018976e-05,
646
+ "loss": 9.9147,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 6.594202898550725,
651
+ "grad_norm": 11.729459762573242,
652
+ "learning_rate": 1.8500948766603414e-05,
653
+ "loss": 10.427,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 6.666666666666667,
658
+ "grad_norm": 5.6112518310546875,
659
+ "learning_rate": 1.7552182163187855e-05,
660
+ "loss": 8.1236,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 6.739130434782608,
665
+ "grad_norm": 21.59635353088379,
666
+ "learning_rate": 1.66034155597723e-05,
667
+ "loss": 8.0663,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 6.811594202898551,
672
+ "grad_norm": 7.840078353881836,
673
+ "learning_rate": 1.5654648956356737e-05,
674
+ "loss": 11.4745,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 6.884057971014493,
679
+ "grad_norm": 8.633024215698242,
680
+ "learning_rate": 1.4705882352941177e-05,
681
+ "loss": 8.9603,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 6.956521739130435,
686
+ "grad_norm": 2.9932422637939453,
687
+ "learning_rate": 1.3757115749525618e-05,
688
+ "loss": 8.8133,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 7.028985507246377,
693
+ "grad_norm": 4.314597129821777,
694
+ "learning_rate": 1.2808349146110058e-05,
695
+ "loss": 6.8162,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 7.101449275362318,
700
+ "grad_norm": 18.329147338867188,
701
+ "learning_rate": 1.1859582542694497e-05,
702
+ "loss": 11.9377,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 7.173913043478261,
707
+ "grad_norm": 7.561063289642334,
708
+ "learning_rate": 1.0910815939278938e-05,
709
+ "loss": 6.8045,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 7.246376811594203,
714
+ "grad_norm": 5.871479511260986,
715
+ "learning_rate": 9.962049335863378e-06,
716
+ "loss": 9.549,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 7.318840579710145,
721
+ "grad_norm": 3.1535987854003906,
722
+ "learning_rate": 9.013282732447819e-06,
723
+ "loss": 6.7738,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 7.391304347826087,
728
+ "grad_norm": 32.92097854614258,
729
+ "learning_rate": 8.064516129032258e-06,
730
+ "loss": 27.4036,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 7.463768115942029,
735
+ "grad_norm": 7.275607109069824,
736
+ "learning_rate": 7.115749525616698e-06,
737
+ "loss": 9.3496,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 7.536231884057971,
742
+ "grad_norm": 7.355132579803467,
743
+ "learning_rate": 6.166982922201139e-06,
744
+ "loss": 7.1842,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 7.608695652173913,
749
+ "grad_norm": 11.539506912231445,
750
+ "learning_rate": 5.218216318785579e-06,
751
+ "loss": 10.1211,
752
+ "step": 1050
753
+ }
754
+ ],
755
+ "logging_steps": 10,
756
+ "max_steps": 1104,
757
+ "num_input_tokens_seen": 0,
758
+ "num_train_epochs": 8,
759
+ "save_steps": 50,
760
+ "stateful_callbacks": {
761
+ "TrainerControl": {
762
+ "args": {
763
+ "should_epoch_stop": false,
764
+ "should_evaluate": false,
765
+ "should_log": false,
766
+ "should_save": true,
767
+ "should_training_stop": false
768
+ },
769
+ "attributes": {}
770
+ }
771
+ },
772
+ "total_flos": 104534819831808.0,
773
+ "train_batch_size": 4,
774
+ "trial_name": null,
775
+ "trial_params": null
776
+ }
checkpoint-1050/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdcca55b05009ba158cf393bed852a146a2c6196feb7ea8edd64cb7f7e5f6a66
3
+ size 5368
checkpoint-1050/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: distilgpt2
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:distilgpt2
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.17.0
checkpoint-1100/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "distilgpt2",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "c_proj",
29
+ "c_attn"
30
+ ],
31
+ "target_parameters": null,
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_qalora": false,
36
+ "use_rslora": false
37
+ }
checkpoint-1100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2279a40fc0621e88075fef54eba4fe48b7f0f11ff76485a33d666af6c998c64
3
+ size 1626544
checkpoint-1100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4d20a686919359b98d88219e71cd27403ab330928ef6fe3a16a4ebcf932751
3
+ size 3274682
checkpoint-1100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:746414c19c6a55eeeb4c0b1101344566a2fa879e002bd40ceb29ef826b19bdfc
3
+ size 14244
checkpoint-1100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba748dc16f6d78a40c04582a3e66451ced07748ee0256733367d1d31d5c08f7
3
+ size 1064
checkpoint-1100/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-1100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-1100/trainer_state.json ADDED
@@ -0,0 +1,811 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 7.971014492753623,
6
+ "eval_steps": 50,
7
+ "global_step": 1100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.007246376811594203,
14
+ "grad_norm": 1.9687033891677856,
15
+ "learning_rate": 0.0,
16
+ "loss": 19.2682,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.07246376811594203,
21
+ "grad_norm": 1.703112006187439,
22
+ "learning_rate": 1.8e-05,
23
+ "loss": 12.4529,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.14492753623188406,
28
+ "grad_norm": 3.6209306716918945,
29
+ "learning_rate": 3.8e-05,
30
+ "loss": 17.5169,
31
+ "step": 20
32
+ },
33
+ {
34
+ "epoch": 0.21739130434782608,
35
+ "grad_norm": 2.09627366065979,
36
+ "learning_rate": 5.8e-05,
37
+ "loss": 16.0619,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 0.2898550724637681,
42
+ "grad_norm": 1.9405275583267212,
43
+ "learning_rate": 7.800000000000001e-05,
44
+ "loss": 20.228,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 0.36231884057971014,
49
+ "grad_norm": 8.32076644897461,
50
+ "learning_rate": 9.8e-05,
51
+ "loss": 16.0457,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.43478260869565216,
56
+ "grad_norm": 1.1994603872299194,
57
+ "learning_rate": 9.9146110056926e-05,
58
+ "loss": 15.9109,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.5072463768115942,
63
+ "grad_norm": 1.3328566551208496,
64
+ "learning_rate": 9.819734345351043e-05,
65
+ "loss": 15.6408,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.5797101449275363,
70
+ "grad_norm": 6.663642406463623,
71
+ "learning_rate": 9.724857685009489e-05,
72
+ "loss": 13.4492,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.6521739130434783,
77
+ "grad_norm": 4.154050350189209,
78
+ "learning_rate": 9.629981024667933e-05,
79
+ "loss": 16.0048,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.7246376811594203,
84
+ "grad_norm": 12.047609329223633,
85
+ "learning_rate": 9.535104364326376e-05,
86
+ "loss": 42.9753,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.7971014492753623,
91
+ "grad_norm": 4.798079490661621,
92
+ "learning_rate": 9.44022770398482e-05,
93
+ "loss": 17.2692,
94
+ "step": 110
95
+ },
96
+ {
97
+ "epoch": 0.8695652173913043,
98
+ "grad_norm": 6.930491924285889,
99
+ "learning_rate": 9.345351043643265e-05,
100
+ "loss": 13.9401,
101
+ "step": 120
102
+ },
103
+ {
104
+ "epoch": 0.9420289855072463,
105
+ "grad_norm": 7.896566867828369,
106
+ "learning_rate": 9.250474383301708e-05,
107
+ "loss": 16.1242,
108
+ "step": 130
109
+ },
110
+ {
111
+ "epoch": 1.0144927536231885,
112
+ "grad_norm": 10.504218101501465,
113
+ "learning_rate": 9.155597722960152e-05,
114
+ "loss": 9.8417,
115
+ "step": 140
116
+ },
117
+ {
118
+ "epoch": 1.0869565217391304,
119
+ "grad_norm": 9.594452857971191,
120
+ "learning_rate": 9.060721062618596e-05,
121
+ "loss": 12.6395,
122
+ "step": 150
123
+ },
124
+ {
125
+ "epoch": 1.1594202898550725,
126
+ "grad_norm": 16.113290786743164,
127
+ "learning_rate": 8.96584440227704e-05,
128
+ "loss": 11.6141,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 1.2318840579710144,
133
+ "grad_norm": 10.904824256896973,
134
+ "learning_rate": 8.870967741935484e-05,
135
+ "loss": 15.8041,
136
+ "step": 170
137
+ },
138
+ {
139
+ "epoch": 1.3043478260869565,
140
+ "grad_norm": 4.2903852462768555,
141
+ "learning_rate": 8.776091081593929e-05,
142
+ "loss": 10.5756,
143
+ "step": 180
144
+ },
145
+ {
146
+ "epoch": 1.3768115942028984,
147
+ "grad_norm": 3.3363027572631836,
148
+ "learning_rate": 8.681214421252373e-05,
149
+ "loss": 12.2632,
150
+ "step": 190
151
+ },
152
+ {
153
+ "epoch": 1.4492753623188406,
154
+ "grad_norm": 5.582556247711182,
155
+ "learning_rate": 8.586337760910817e-05,
156
+ "loss": 10.2026,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 1.5217391304347827,
161
+ "grad_norm": 3.090460777282715,
162
+ "learning_rate": 8.49146110056926e-05,
163
+ "loss": 9.8113,
164
+ "step": 210
165
+ },
166
+ {
167
+ "epoch": 1.5942028985507246,
168
+ "grad_norm": 20.330148696899414,
169
+ "learning_rate": 8.396584440227704e-05,
170
+ "loss": 9.2478,
171
+ "step": 220
172
+ },
173
+ {
174
+ "epoch": 1.6666666666666665,
175
+ "grad_norm": 16.418106079101562,
176
+ "learning_rate": 8.301707779886149e-05,
177
+ "loss": 11.377,
178
+ "step": 230
179
+ },
180
+ {
181
+ "epoch": 1.7391304347826086,
182
+ "grad_norm": 1.9852267503738403,
183
+ "learning_rate": 8.206831119544592e-05,
184
+ "loss": 9.8674,
185
+ "step": 240
186
+ },
187
+ {
188
+ "epoch": 1.8115942028985508,
189
+ "grad_norm": 4.2618489265441895,
190
+ "learning_rate": 8.111954459203036e-05,
191
+ "loss": 10.9124,
192
+ "step": 250
193
+ },
194
+ {
195
+ "epoch": 1.8840579710144927,
196
+ "grad_norm": 5.334084510803223,
197
+ "learning_rate": 8.017077798861481e-05,
198
+ "loss": 29.9208,
199
+ "step": 260
200
+ },
201
+ {
202
+ "epoch": 1.9565217391304348,
203
+ "grad_norm": 7.662145614624023,
204
+ "learning_rate": 7.922201138519924e-05,
205
+ "loss": 9.4491,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 2.028985507246377,
210
+ "grad_norm": 2.990098476409912,
211
+ "learning_rate": 7.827324478178368e-05,
212
+ "loss": 12.7051,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 2.101449275362319,
217
+ "grad_norm": 11.343267440795898,
218
+ "learning_rate": 7.732447817836812e-05,
219
+ "loss": 10.1094,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 2.1739130434782608,
224
+ "grad_norm": 4.076178550720215,
225
+ "learning_rate": 7.637571157495257e-05,
226
+ "loss": 10.8557,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 2.246376811594203,
231
+ "grad_norm": 3.965240240097046,
232
+ "learning_rate": 7.542694497153701e-05,
233
+ "loss": 10.2597,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 2.318840579710145,
238
+ "grad_norm": 16.37909507751465,
239
+ "learning_rate": 7.447817836812145e-05,
240
+ "loss": 9.0119,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 2.391304347826087,
245
+ "grad_norm": 3.6150219440460205,
246
+ "learning_rate": 7.352941176470589e-05,
247
+ "loss": 26.6018,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 2.463768115942029,
252
+ "grad_norm": 19.880943298339844,
253
+ "learning_rate": 7.258064516129033e-05,
254
+ "loss": 9.6189,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 2.536231884057971,
259
+ "grad_norm": 3.5458195209503174,
260
+ "learning_rate": 7.163187855787477e-05,
261
+ "loss": 8.4988,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 2.608695652173913,
266
+ "grad_norm": 13.963035583496094,
267
+ "learning_rate": 7.06831119544592e-05,
268
+ "loss": 11.8011,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 2.681159420289855,
273
+ "grad_norm": 19.048301696777344,
274
+ "learning_rate": 6.973434535104365e-05,
275
+ "loss": 10.9278,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 2.753623188405797,
280
+ "grad_norm": 4.992802143096924,
281
+ "learning_rate": 6.878557874762808e-05,
282
+ "loss": 8.919,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 2.8260869565217392,
287
+ "grad_norm": 11.363718032836914,
288
+ "learning_rate": 6.783681214421252e-05,
289
+ "loss": 13.1761,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 2.898550724637681,
294
+ "grad_norm": 5.374908924102783,
295
+ "learning_rate": 6.688804554079696e-05,
296
+ "loss": 10.3222,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 2.971014492753623,
301
+ "grad_norm": 8.949808120727539,
302
+ "learning_rate": 6.59392789373814e-05,
303
+ "loss": 10.7587,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 3.0434782608695654,
308
+ "grad_norm": 4.645139217376709,
309
+ "learning_rate": 6.499051233396585e-05,
310
+ "loss": 7.0093,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 3.1159420289855073,
315
+ "grad_norm": 1.7357378005981445,
316
+ "learning_rate": 6.404174573055029e-05,
317
+ "loss": 10.5791,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 3.1884057971014492,
322
+ "grad_norm": 6.632950305938721,
323
+ "learning_rate": 6.309297912713473e-05,
324
+ "loss": 8.7916,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 3.260869565217391,
329
+ "grad_norm": 3.3891420364379883,
330
+ "learning_rate": 6.214421252371917e-05,
331
+ "loss": 10.3499,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 3.3333333333333335,
336
+ "grad_norm": 10.14654541015625,
337
+ "learning_rate": 6.119544592030361e-05,
338
+ "loss": 8.5833,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 3.4057971014492754,
343
+ "grad_norm": 3.27583384513855,
344
+ "learning_rate": 6.0246679316888046e-05,
345
+ "loss": 28.3443,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 3.4782608695652173,
350
+ "grad_norm": 16.218280792236328,
351
+ "learning_rate": 5.9297912713472494e-05,
352
+ "loss": 11.3033,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 3.550724637681159,
357
+ "grad_norm": 5.851198196411133,
358
+ "learning_rate": 5.834914611005693e-05,
359
+ "loss": 7.5228,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 3.6231884057971016,
364
+ "grad_norm": 13.043642044067383,
365
+ "learning_rate": 5.740037950664137e-05,
366
+ "loss": 11.608,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 3.6956521739130435,
371
+ "grad_norm": 3.651071071624756,
372
+ "learning_rate": 5.645161290322582e-05,
373
+ "loss": 9.3775,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 3.7681159420289854,
378
+ "grad_norm": 3.946401357650757,
379
+ "learning_rate": 5.550284629981025e-05,
380
+ "loss": 9.9621,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 3.8405797101449277,
385
+ "grad_norm": 5.363879680633545,
386
+ "learning_rate": 5.4554079696394686e-05,
387
+ "loss": 7.2515,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 3.9130434782608696,
392
+ "grad_norm": 18.565500259399414,
393
+ "learning_rate": 5.360531309297913e-05,
394
+ "loss": 9.9015,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 3.9855072463768115,
399
+ "grad_norm": 2.068690299987793,
400
+ "learning_rate": 5.2656546489563575e-05,
401
+ "loss": 8.6521,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 4.057971014492754,
406
+ "grad_norm": 8.377117156982422,
407
+ "learning_rate": 5.170777988614801e-05,
408
+ "loss": 11.6352,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 4.130434782608695,
413
+ "grad_norm": 6.822054386138916,
414
+ "learning_rate": 5.075901328273245e-05,
415
+ "loss": 8.9412,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 4.202898550724638,
420
+ "grad_norm": 17.24335479736328,
421
+ "learning_rate": 4.981024667931689e-05,
422
+ "loss": 9.5539,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 4.27536231884058,
427
+ "grad_norm": 13.434685707092285,
428
+ "learning_rate": 4.8861480075901326e-05,
429
+ "loss": 10.8367,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 4.3478260869565215,
434
+ "grad_norm": 17.375398635864258,
435
+ "learning_rate": 4.791271347248577e-05,
436
+ "loss": 10.818,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 4.420289855072464,
441
+ "grad_norm": 4.53552770614624,
442
+ "learning_rate": 4.6963946869070216e-05,
443
+ "loss": 7.442,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 4.492753623188406,
448
+ "grad_norm": 4.74644136428833,
449
+ "learning_rate": 4.601518026565465e-05,
450
+ "loss": 9.6362,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 4.565217391304348,
455
+ "grad_norm": 3.9156153202056885,
456
+ "learning_rate": 4.506641366223909e-05,
457
+ "loss": 11.4203,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 4.63768115942029,
462
+ "grad_norm": 18.31324005126953,
463
+ "learning_rate": 4.411764705882353e-05,
464
+ "loss": 8.557,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 4.710144927536232,
469
+ "grad_norm": 4.924636363983154,
470
+ "learning_rate": 4.3168880455407974e-05,
471
+ "loss": 9.608,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 4.782608695652174,
476
+ "grad_norm": 5.3758769035339355,
477
+ "learning_rate": 4.222011385199241e-05,
478
+ "loss": 8.9764,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 4.855072463768116,
483
+ "grad_norm": 8.584567070007324,
484
+ "learning_rate": 4.1271347248576856e-05,
485
+ "loss": 9.621,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 4.927536231884058,
490
+ "grad_norm": 4.82368803024292,
491
+ "learning_rate": 4.032258064516129e-05,
492
+ "loss": 24.5753,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 5.0,
497
+ "grad_norm": 2.3411295413970947,
498
+ "learning_rate": 3.937381404174573e-05,
499
+ "loss": 7.9662,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 5.072463768115942,
504
+ "grad_norm": 3.99580979347229,
505
+ "learning_rate": 3.842504743833017e-05,
506
+ "loss": 6.8737,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 5.144927536231884,
511
+ "grad_norm": 24.173742294311523,
512
+ "learning_rate": 3.7476280834914614e-05,
513
+ "loss": 11.8038,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 5.217391304347826,
518
+ "grad_norm": 25.25533676147461,
519
+ "learning_rate": 3.6527514231499055e-05,
520
+ "loss": 11.9047,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 5.2898550724637685,
525
+ "grad_norm": 4.739432334899902,
526
+ "learning_rate": 3.557874762808349e-05,
527
+ "loss": 9.503,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 5.36231884057971,
532
+ "grad_norm": 7.874780178070068,
533
+ "learning_rate": 3.462998102466794e-05,
534
+ "loss": 10.949,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 5.434782608695652,
539
+ "grad_norm": 3.363119602203369,
540
+ "learning_rate": 3.368121442125237e-05,
541
+ "loss": 10.2591,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 5.507246376811594,
546
+ "grad_norm": 5.406454086303711,
547
+ "learning_rate": 3.273244781783681e-05,
548
+ "loss": 7.7785,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 5.579710144927536,
553
+ "grad_norm": 6.118616580963135,
554
+ "learning_rate": 3.1783681214421254e-05,
555
+ "loss": 7.2315,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 5.6521739130434785,
560
+ "grad_norm": 16.83717918395996,
561
+ "learning_rate": 3.0834914611005695e-05,
562
+ "loss": 7.6301,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 5.72463768115942,
567
+ "grad_norm": 11.110983848571777,
568
+ "learning_rate": 2.9886148007590137e-05,
569
+ "loss": 9.153,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 5.797101449275362,
574
+ "grad_norm": 8.291231155395508,
575
+ "learning_rate": 2.8937381404174574e-05,
576
+ "loss": 10.3227,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 5.869565217391305,
581
+ "grad_norm": 2.8294785022735596,
582
+ "learning_rate": 2.7988614800759016e-05,
583
+ "loss": 6.8461,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 5.942028985507246,
588
+ "grad_norm": 11.522751808166504,
589
+ "learning_rate": 2.7039848197343453e-05,
590
+ "loss": 25.7992,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 6.0144927536231885,
595
+ "grad_norm": 5.239048480987549,
596
+ "learning_rate": 2.6091081593927898e-05,
597
+ "loss": 10.1367,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 6.086956521739131,
602
+ "grad_norm": 14.244694709777832,
603
+ "learning_rate": 2.5142314990512332e-05,
604
+ "loss": 8.1876,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 6.159420289855072,
609
+ "grad_norm": 3.612367868423462,
610
+ "learning_rate": 2.4193548387096777e-05,
611
+ "loss": 9.5329,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 6.231884057971015,
616
+ "grad_norm": 4.118394374847412,
617
+ "learning_rate": 2.3244781783681215e-05,
618
+ "loss": 8.8621,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 6.304347826086957,
623
+ "grad_norm": 2.245436906814575,
624
+ "learning_rate": 2.2296015180265656e-05,
625
+ "loss": 7.363,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 6.3768115942028984,
630
+ "grad_norm": 7.4832658767700195,
631
+ "learning_rate": 2.1347248576850097e-05,
632
+ "loss": 8.4077,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 6.449275362318841,
637
+ "grad_norm": 20.146770477294922,
638
+ "learning_rate": 2.0398481973434535e-05,
639
+ "loss": 27.7444,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 6.521739130434782,
644
+ "grad_norm": 6.686460018157959,
645
+ "learning_rate": 1.9449715370018976e-05,
646
+ "loss": 9.9147,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 6.594202898550725,
651
+ "grad_norm": 11.729459762573242,
652
+ "learning_rate": 1.8500948766603414e-05,
653
+ "loss": 10.427,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 6.666666666666667,
658
+ "grad_norm": 5.6112518310546875,
659
+ "learning_rate": 1.7552182163187855e-05,
660
+ "loss": 8.1236,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 6.739130434782608,
665
+ "grad_norm": 21.59635353088379,
666
+ "learning_rate": 1.66034155597723e-05,
667
+ "loss": 8.0663,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 6.811594202898551,
672
+ "grad_norm": 7.840078353881836,
673
+ "learning_rate": 1.5654648956356737e-05,
674
+ "loss": 11.4745,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 6.884057971014493,
679
+ "grad_norm": 8.633024215698242,
680
+ "learning_rate": 1.4705882352941177e-05,
681
+ "loss": 8.9603,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 6.956521739130435,
686
+ "grad_norm": 2.9932422637939453,
687
+ "learning_rate": 1.3757115749525618e-05,
688
+ "loss": 8.8133,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 7.028985507246377,
693
+ "grad_norm": 4.314597129821777,
694
+ "learning_rate": 1.2808349146110058e-05,
695
+ "loss": 6.8162,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 7.101449275362318,
700
+ "grad_norm": 18.329147338867188,
701
+ "learning_rate": 1.1859582542694497e-05,
702
+ "loss": 11.9377,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 7.173913043478261,
707
+ "grad_norm": 7.561063289642334,
708
+ "learning_rate": 1.0910815939278938e-05,
709
+ "loss": 6.8045,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 7.246376811594203,
714
+ "grad_norm": 5.871479511260986,
715
+ "learning_rate": 9.962049335863378e-06,
716
+ "loss": 9.549,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 7.318840579710145,
721
+ "grad_norm": 3.1535987854003906,
722
+ "learning_rate": 9.013282732447819e-06,
723
+ "loss": 6.7738,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 7.391304347826087,
728
+ "grad_norm": 32.92097854614258,
729
+ "learning_rate": 8.064516129032258e-06,
730
+ "loss": 27.4036,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 7.463768115942029,
735
+ "grad_norm": 7.275607109069824,
736
+ "learning_rate": 7.115749525616698e-06,
737
+ "loss": 9.3496,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 7.536231884057971,
742
+ "grad_norm": 7.355132579803467,
743
+ "learning_rate": 6.166982922201139e-06,
744
+ "loss": 7.1842,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 7.608695652173913,
749
+ "grad_norm": 11.539506912231445,
750
+ "learning_rate": 5.218216318785579e-06,
751
+ "loss": 10.1211,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 7.681159420289855,
756
+ "grad_norm": 5.036221981048584,
757
+ "learning_rate": 4.269449715370019e-06,
758
+ "loss": 10.1483,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 7.753623188405797,
763
+ "grad_norm": 24.608356475830078,
764
+ "learning_rate": 3.320683111954459e-06,
765
+ "loss": 9.3202,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 7.826086956521739,
770
+ "grad_norm": 9.034127235412598,
771
+ "learning_rate": 2.3719165085388996e-06,
772
+ "loss": 9.5748,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 7.898550724637682,
777
+ "grad_norm": 13.333020210266113,
778
+ "learning_rate": 1.4231499051233397e-06,
779
+ "loss": 8.6569,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 7.971014492753623,
784
+ "grad_norm": 7.102665424346924,
785
+ "learning_rate": 4.743833017077799e-07,
786
+ "loss": 8.791,
787
+ "step": 1100
788
+ }
789
+ ],
790
+ "logging_steps": 10,
791
+ "max_steps": 1104,
792
+ "num_input_tokens_seen": 0,
793
+ "num_train_epochs": 8,
794
+ "save_steps": 50,
795
+ "stateful_callbacks": {
796
+ "TrainerControl": {
797
+ "args": {
798
+ "should_epoch_stop": false,
799
+ "should_evaluate": false,
800
+ "should_log": false,
801
+ "should_save": true,
802
+ "should_training_stop": false
803
+ },
804
+ "attributes": {}
805
+ }
806
+ },
807
+ "total_flos": 109513821487104.0,
808
+ "train_batch_size": 4,
809
+ "trial_name": null,
810
+ "trial_params": null
811
+ }
checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdcca55b05009ba158cf393bed852a146a2c6196feb7ea8edd64cb7f7e5f6a66
3
+ size 5368
checkpoint-1100/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1104/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: distilgpt2
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:distilgpt2
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.17.0
checkpoint-1104/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "distilgpt2",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "c_proj",
29
+ "c_attn"
30
+ ],
31
+ "target_parameters": null,
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_qalora": false,
36
+ "use_rslora": false
37
+ }
checkpoint-1104/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1813de2f5341cddcec1cb95f398491e59df450771f1625e60fa7561ee908327c
3
+ size 1626544
checkpoint-1104/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1104/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0f59242e9b67335127c66287f95fcf68fea4ee5b0a677078ec15ea76765e5e
3
+ size 3274682
checkpoint-1104/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c941df5bfb4392324bd00009af01a99f7fc9c5c9e987e5127930e52df9a1994
3
+ size 14244
checkpoint-1104/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c553f3aafa48dc85728de235858e5f39c92381516af1aefcc7bae321d272b63
3
+ size 1064
checkpoint-1104/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-1104/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1104/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-1104/trainer_state.json ADDED
@@ -0,0 +1,811 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 8.0,
6
+ "eval_steps": 50,
7
+ "global_step": 1104,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.007246376811594203,
14
+ "grad_norm": 1.9687033891677856,
15
+ "learning_rate": 0.0,
16
+ "loss": 19.2682,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.07246376811594203,
21
+ "grad_norm": 1.703112006187439,
22
+ "learning_rate": 1.8e-05,
23
+ "loss": 12.4529,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.14492753623188406,
28
+ "grad_norm": 3.6209306716918945,
29
+ "learning_rate": 3.8e-05,
30
+ "loss": 17.5169,
31
+ "step": 20
32
+ },
33
+ {
34
+ "epoch": 0.21739130434782608,
35
+ "grad_norm": 2.09627366065979,
36
+ "learning_rate": 5.8e-05,
37
+ "loss": 16.0619,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 0.2898550724637681,
42
+ "grad_norm": 1.9405275583267212,
43
+ "learning_rate": 7.800000000000001e-05,
44
+ "loss": 20.228,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 0.36231884057971014,
49
+ "grad_norm": 8.32076644897461,
50
+ "learning_rate": 9.8e-05,
51
+ "loss": 16.0457,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.43478260869565216,
56
+ "grad_norm": 1.1994603872299194,
57
+ "learning_rate": 9.9146110056926e-05,
58
+ "loss": 15.9109,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.5072463768115942,
63
+ "grad_norm": 1.3328566551208496,
64
+ "learning_rate": 9.819734345351043e-05,
65
+ "loss": 15.6408,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.5797101449275363,
70
+ "grad_norm": 6.663642406463623,
71
+ "learning_rate": 9.724857685009489e-05,
72
+ "loss": 13.4492,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.6521739130434783,
77
+ "grad_norm": 4.154050350189209,
78
+ "learning_rate": 9.629981024667933e-05,
79
+ "loss": 16.0048,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.7246376811594203,
84
+ "grad_norm": 12.047609329223633,
85
+ "learning_rate": 9.535104364326376e-05,
86
+ "loss": 42.9753,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.7971014492753623,
91
+ "grad_norm": 4.798079490661621,
92
+ "learning_rate": 9.44022770398482e-05,
93
+ "loss": 17.2692,
94
+ "step": 110
95
+ },
96
+ {
97
+ "epoch": 0.8695652173913043,
98
+ "grad_norm": 6.930491924285889,
99
+ "learning_rate": 9.345351043643265e-05,
100
+ "loss": 13.9401,
101
+ "step": 120
102
+ },
103
+ {
104
+ "epoch": 0.9420289855072463,
105
+ "grad_norm": 7.896566867828369,
106
+ "learning_rate": 9.250474383301708e-05,
107
+ "loss": 16.1242,
108
+ "step": 130
109
+ },
110
+ {
111
+ "epoch": 1.0144927536231885,
112
+ "grad_norm": 10.504218101501465,
113
+ "learning_rate": 9.155597722960152e-05,
114
+ "loss": 9.8417,
115
+ "step": 140
116
+ },
117
+ {
118
+ "epoch": 1.0869565217391304,
119
+ "grad_norm": 9.594452857971191,
120
+ "learning_rate": 9.060721062618596e-05,
121
+ "loss": 12.6395,
122
+ "step": 150
123
+ },
124
+ {
125
+ "epoch": 1.1594202898550725,
126
+ "grad_norm": 16.113290786743164,
127
+ "learning_rate": 8.96584440227704e-05,
128
+ "loss": 11.6141,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 1.2318840579710144,
133
+ "grad_norm": 10.904824256896973,
134
+ "learning_rate": 8.870967741935484e-05,
135
+ "loss": 15.8041,
136
+ "step": 170
137
+ },
138
+ {
139
+ "epoch": 1.3043478260869565,
140
+ "grad_norm": 4.2903852462768555,
141
+ "learning_rate": 8.776091081593929e-05,
142
+ "loss": 10.5756,
143
+ "step": 180
144
+ },
145
+ {
146
+ "epoch": 1.3768115942028984,
147
+ "grad_norm": 3.3363027572631836,
148
+ "learning_rate": 8.681214421252373e-05,
149
+ "loss": 12.2632,
150
+ "step": 190
151
+ },
152
+ {
153
+ "epoch": 1.4492753623188406,
154
+ "grad_norm": 5.582556247711182,
155
+ "learning_rate": 8.586337760910817e-05,
156
+ "loss": 10.2026,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 1.5217391304347827,
161
+ "grad_norm": 3.090460777282715,
162
+ "learning_rate": 8.49146110056926e-05,
163
+ "loss": 9.8113,
164
+ "step": 210
165
+ },
166
+ {
167
+ "epoch": 1.5942028985507246,
168
+ "grad_norm": 20.330148696899414,
169
+ "learning_rate": 8.396584440227704e-05,
170
+ "loss": 9.2478,
171
+ "step": 220
172
+ },
173
+ {
174
+ "epoch": 1.6666666666666665,
175
+ "grad_norm": 16.418106079101562,
176
+ "learning_rate": 8.301707779886149e-05,
177
+ "loss": 11.377,
178
+ "step": 230
179
+ },
180
+ {
181
+ "epoch": 1.7391304347826086,
182
+ "grad_norm": 1.9852267503738403,
183
+ "learning_rate": 8.206831119544592e-05,
184
+ "loss": 9.8674,
185
+ "step": 240
186
+ },
187
+ {
188
+ "epoch": 1.8115942028985508,
189
+ "grad_norm": 4.2618489265441895,
190
+ "learning_rate": 8.111954459203036e-05,
191
+ "loss": 10.9124,
192
+ "step": 250
193
+ },
194
+ {
195
+ "epoch": 1.8840579710144927,
196
+ "grad_norm": 5.334084510803223,
197
+ "learning_rate": 8.017077798861481e-05,
198
+ "loss": 29.9208,
199
+ "step": 260
200
+ },
201
+ {
202
+ "epoch": 1.9565217391304348,
203
+ "grad_norm": 7.662145614624023,
204
+ "learning_rate": 7.922201138519924e-05,
205
+ "loss": 9.4491,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 2.028985507246377,
210
+ "grad_norm": 2.990098476409912,
211
+ "learning_rate": 7.827324478178368e-05,
212
+ "loss": 12.7051,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 2.101449275362319,
217
+ "grad_norm": 11.343267440795898,
218
+ "learning_rate": 7.732447817836812e-05,
219
+ "loss": 10.1094,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 2.1739130434782608,
224
+ "grad_norm": 4.076178550720215,
225
+ "learning_rate": 7.637571157495257e-05,
226
+ "loss": 10.8557,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 2.246376811594203,
231
+ "grad_norm": 3.965240240097046,
232
+ "learning_rate": 7.542694497153701e-05,
233
+ "loss": 10.2597,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 2.318840579710145,
238
+ "grad_norm": 16.37909507751465,
239
+ "learning_rate": 7.447817836812145e-05,
240
+ "loss": 9.0119,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 2.391304347826087,
245
+ "grad_norm": 3.6150219440460205,
246
+ "learning_rate": 7.352941176470589e-05,
247
+ "loss": 26.6018,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 2.463768115942029,
252
+ "grad_norm": 19.880943298339844,
253
+ "learning_rate": 7.258064516129033e-05,
254
+ "loss": 9.6189,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 2.536231884057971,
259
+ "grad_norm": 3.5458195209503174,
260
+ "learning_rate": 7.163187855787477e-05,
261
+ "loss": 8.4988,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 2.608695652173913,
266
+ "grad_norm": 13.963035583496094,
267
+ "learning_rate": 7.06831119544592e-05,
268
+ "loss": 11.8011,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 2.681159420289855,
273
+ "grad_norm": 19.048301696777344,
274
+ "learning_rate": 6.973434535104365e-05,
275
+ "loss": 10.9278,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 2.753623188405797,
280
+ "grad_norm": 4.992802143096924,
281
+ "learning_rate": 6.878557874762808e-05,
282
+ "loss": 8.919,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 2.8260869565217392,
287
+ "grad_norm": 11.363718032836914,
288
+ "learning_rate": 6.783681214421252e-05,
289
+ "loss": 13.1761,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 2.898550724637681,
294
+ "grad_norm": 5.374908924102783,
295
+ "learning_rate": 6.688804554079696e-05,
296
+ "loss": 10.3222,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 2.971014492753623,
301
+ "grad_norm": 8.949808120727539,
302
+ "learning_rate": 6.59392789373814e-05,
303
+ "loss": 10.7587,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 3.0434782608695654,
308
+ "grad_norm": 4.645139217376709,
309
+ "learning_rate": 6.499051233396585e-05,
310
+ "loss": 7.0093,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 3.1159420289855073,
315
+ "grad_norm": 1.7357378005981445,
316
+ "learning_rate": 6.404174573055029e-05,
317
+ "loss": 10.5791,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 3.1884057971014492,
322
+ "grad_norm": 6.632950305938721,
323
+ "learning_rate": 6.309297912713473e-05,
324
+ "loss": 8.7916,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 3.260869565217391,
329
+ "grad_norm": 3.3891420364379883,
330
+ "learning_rate": 6.214421252371917e-05,
331
+ "loss": 10.3499,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 3.3333333333333335,
336
+ "grad_norm": 10.14654541015625,
337
+ "learning_rate": 6.119544592030361e-05,
338
+ "loss": 8.5833,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 3.4057971014492754,
343
+ "grad_norm": 3.27583384513855,
344
+ "learning_rate": 6.0246679316888046e-05,
345
+ "loss": 28.3443,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 3.4782608695652173,
350
+ "grad_norm": 16.218280792236328,
351
+ "learning_rate": 5.9297912713472494e-05,
352
+ "loss": 11.3033,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 3.550724637681159,
357
+ "grad_norm": 5.851198196411133,
358
+ "learning_rate": 5.834914611005693e-05,
359
+ "loss": 7.5228,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 3.6231884057971016,
364
+ "grad_norm": 13.043642044067383,
365
+ "learning_rate": 5.740037950664137e-05,
366
+ "loss": 11.608,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 3.6956521739130435,
371
+ "grad_norm": 3.651071071624756,
372
+ "learning_rate": 5.645161290322582e-05,
373
+ "loss": 9.3775,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 3.7681159420289854,
378
+ "grad_norm": 3.946401357650757,
379
+ "learning_rate": 5.550284629981025e-05,
380
+ "loss": 9.9621,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 3.8405797101449277,
385
+ "grad_norm": 5.363879680633545,
386
+ "learning_rate": 5.4554079696394686e-05,
387
+ "loss": 7.2515,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 3.9130434782608696,
392
+ "grad_norm": 18.565500259399414,
393
+ "learning_rate": 5.360531309297913e-05,
394
+ "loss": 9.9015,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 3.9855072463768115,
399
+ "grad_norm": 2.068690299987793,
400
+ "learning_rate": 5.2656546489563575e-05,
401
+ "loss": 8.6521,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 4.057971014492754,
406
+ "grad_norm": 8.377117156982422,
407
+ "learning_rate": 5.170777988614801e-05,
408
+ "loss": 11.6352,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 4.130434782608695,
413
+ "grad_norm": 6.822054386138916,
414
+ "learning_rate": 5.075901328273245e-05,
415
+ "loss": 8.9412,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 4.202898550724638,
420
+ "grad_norm": 17.24335479736328,
421
+ "learning_rate": 4.981024667931689e-05,
422
+ "loss": 9.5539,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 4.27536231884058,
427
+ "grad_norm": 13.434685707092285,
428
+ "learning_rate": 4.8861480075901326e-05,
429
+ "loss": 10.8367,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 4.3478260869565215,
434
+ "grad_norm": 17.375398635864258,
435
+ "learning_rate": 4.791271347248577e-05,
436
+ "loss": 10.818,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 4.420289855072464,
441
+ "grad_norm": 4.53552770614624,
442
+ "learning_rate": 4.6963946869070216e-05,
443
+ "loss": 7.442,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 4.492753623188406,
448
+ "grad_norm": 4.74644136428833,
449
+ "learning_rate": 4.601518026565465e-05,
450
+ "loss": 9.6362,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 4.565217391304348,
455
+ "grad_norm": 3.9156153202056885,
456
+ "learning_rate": 4.506641366223909e-05,
457
+ "loss": 11.4203,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 4.63768115942029,
462
+ "grad_norm": 18.31324005126953,
463
+ "learning_rate": 4.411764705882353e-05,
464
+ "loss": 8.557,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 4.710144927536232,
469
+ "grad_norm": 4.924636363983154,
470
+ "learning_rate": 4.3168880455407974e-05,
471
+ "loss": 9.608,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 4.782608695652174,
476
+ "grad_norm": 5.3758769035339355,
477
+ "learning_rate": 4.222011385199241e-05,
478
+ "loss": 8.9764,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 4.855072463768116,
483
+ "grad_norm": 8.584567070007324,
484
+ "learning_rate": 4.1271347248576856e-05,
485
+ "loss": 9.621,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 4.927536231884058,
490
+ "grad_norm": 4.82368803024292,
491
+ "learning_rate": 4.032258064516129e-05,
492
+ "loss": 24.5753,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 5.0,
497
+ "grad_norm": 2.3411295413970947,
498
+ "learning_rate": 3.937381404174573e-05,
499
+ "loss": 7.9662,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 5.072463768115942,
504
+ "grad_norm": 3.99580979347229,
505
+ "learning_rate": 3.842504743833017e-05,
506
+ "loss": 6.8737,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 5.144927536231884,
511
+ "grad_norm": 24.173742294311523,
512
+ "learning_rate": 3.7476280834914614e-05,
513
+ "loss": 11.8038,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 5.217391304347826,
518
+ "grad_norm": 25.25533676147461,
519
+ "learning_rate": 3.6527514231499055e-05,
520
+ "loss": 11.9047,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 5.2898550724637685,
525
+ "grad_norm": 4.739432334899902,
526
+ "learning_rate": 3.557874762808349e-05,
527
+ "loss": 9.503,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 5.36231884057971,
532
+ "grad_norm": 7.874780178070068,
533
+ "learning_rate": 3.462998102466794e-05,
534
+ "loss": 10.949,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 5.434782608695652,
539
+ "grad_norm": 3.363119602203369,
540
+ "learning_rate": 3.368121442125237e-05,
541
+ "loss": 10.2591,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 5.507246376811594,
546
+ "grad_norm": 5.406454086303711,
547
+ "learning_rate": 3.273244781783681e-05,
548
+ "loss": 7.7785,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 5.579710144927536,
553
+ "grad_norm": 6.118616580963135,
554
+ "learning_rate": 3.1783681214421254e-05,
555
+ "loss": 7.2315,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 5.6521739130434785,
560
+ "grad_norm": 16.83717918395996,
561
+ "learning_rate": 3.0834914611005695e-05,
562
+ "loss": 7.6301,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 5.72463768115942,
567
+ "grad_norm": 11.110983848571777,
568
+ "learning_rate": 2.9886148007590137e-05,
569
+ "loss": 9.153,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 5.797101449275362,
574
+ "grad_norm": 8.291231155395508,
575
+ "learning_rate": 2.8937381404174574e-05,
576
+ "loss": 10.3227,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 5.869565217391305,
581
+ "grad_norm": 2.8294785022735596,
582
+ "learning_rate": 2.7988614800759016e-05,
583
+ "loss": 6.8461,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 5.942028985507246,
588
+ "grad_norm": 11.522751808166504,
589
+ "learning_rate": 2.7039848197343453e-05,
590
+ "loss": 25.7992,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 6.0144927536231885,
595
+ "grad_norm": 5.239048480987549,
596
+ "learning_rate": 2.6091081593927898e-05,
597
+ "loss": 10.1367,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 6.086956521739131,
602
+ "grad_norm": 14.244694709777832,
603
+ "learning_rate": 2.5142314990512332e-05,
604
+ "loss": 8.1876,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 6.159420289855072,
609
+ "grad_norm": 3.612367868423462,
610
+ "learning_rate": 2.4193548387096777e-05,
611
+ "loss": 9.5329,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 6.231884057971015,
616
+ "grad_norm": 4.118394374847412,
617
+ "learning_rate": 2.3244781783681215e-05,
618
+ "loss": 8.8621,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 6.304347826086957,
623
+ "grad_norm": 2.245436906814575,
624
+ "learning_rate": 2.2296015180265656e-05,
625
+ "loss": 7.363,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 6.3768115942028984,
630
+ "grad_norm": 7.4832658767700195,
631
+ "learning_rate": 2.1347248576850097e-05,
632
+ "loss": 8.4077,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 6.449275362318841,
637
+ "grad_norm": 20.146770477294922,
638
+ "learning_rate": 2.0398481973434535e-05,
639
+ "loss": 27.7444,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 6.521739130434782,
644
+ "grad_norm": 6.686460018157959,
645
+ "learning_rate": 1.9449715370018976e-05,
646
+ "loss": 9.9147,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 6.594202898550725,
651
+ "grad_norm": 11.729459762573242,
652
+ "learning_rate": 1.8500948766603414e-05,
653
+ "loss": 10.427,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 6.666666666666667,
658
+ "grad_norm": 5.6112518310546875,
659
+ "learning_rate": 1.7552182163187855e-05,
660
+ "loss": 8.1236,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 6.739130434782608,
665
+ "grad_norm": 21.59635353088379,
666
+ "learning_rate": 1.66034155597723e-05,
667
+ "loss": 8.0663,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 6.811594202898551,
672
+ "grad_norm": 7.840078353881836,
673
+ "learning_rate": 1.5654648956356737e-05,
674
+ "loss": 11.4745,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 6.884057971014493,
679
+ "grad_norm": 8.633024215698242,
680
+ "learning_rate": 1.4705882352941177e-05,
681
+ "loss": 8.9603,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 6.956521739130435,
686
+ "grad_norm": 2.9932422637939453,
687
+ "learning_rate": 1.3757115749525618e-05,
688
+ "loss": 8.8133,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 7.028985507246377,
693
+ "grad_norm": 4.314597129821777,
694
+ "learning_rate": 1.2808349146110058e-05,
695
+ "loss": 6.8162,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 7.101449275362318,
700
+ "grad_norm": 18.329147338867188,
701
+ "learning_rate": 1.1859582542694497e-05,
702
+ "loss": 11.9377,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 7.173913043478261,
707
+ "grad_norm": 7.561063289642334,
708
+ "learning_rate": 1.0910815939278938e-05,
709
+ "loss": 6.8045,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 7.246376811594203,
714
+ "grad_norm": 5.871479511260986,
715
+ "learning_rate": 9.962049335863378e-06,
716
+ "loss": 9.549,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 7.318840579710145,
721
+ "grad_norm": 3.1535987854003906,
722
+ "learning_rate": 9.013282732447819e-06,
723
+ "loss": 6.7738,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 7.391304347826087,
728
+ "grad_norm": 32.92097854614258,
729
+ "learning_rate": 8.064516129032258e-06,
730
+ "loss": 27.4036,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 7.463768115942029,
735
+ "grad_norm": 7.275607109069824,
736
+ "learning_rate": 7.115749525616698e-06,
737
+ "loss": 9.3496,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 7.536231884057971,
742
+ "grad_norm": 7.355132579803467,
743
+ "learning_rate": 6.166982922201139e-06,
744
+ "loss": 7.1842,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 7.608695652173913,
749
+ "grad_norm": 11.539506912231445,
750
+ "learning_rate": 5.218216318785579e-06,
751
+ "loss": 10.1211,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 7.681159420289855,
756
+ "grad_norm": 5.036221981048584,
757
+ "learning_rate": 4.269449715370019e-06,
758
+ "loss": 10.1483,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 7.753623188405797,
763
+ "grad_norm": 24.608356475830078,
764
+ "learning_rate": 3.320683111954459e-06,
765
+ "loss": 9.3202,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 7.826086956521739,
770
+ "grad_norm": 9.034127235412598,
771
+ "learning_rate": 2.3719165085388996e-06,
772
+ "loss": 9.5748,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 7.898550724637682,
777
+ "grad_norm": 13.333020210266113,
778
+ "learning_rate": 1.4231499051233397e-06,
779
+ "loss": 8.6569,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 7.971014492753623,
784
+ "grad_norm": 7.102665424346924,
785
+ "learning_rate": 4.743833017077799e-07,
786
+ "loss": 8.791,
787
+ "step": 1100
788
+ }
789
+ ],
790
+ "logging_steps": 10,
791
+ "max_steps": 1104,
792
+ "num_input_tokens_seen": 0,
793
+ "num_train_epochs": 8,
794
+ "save_steps": 50,
795
+ "stateful_callbacks": {
796
+ "TrainerControl": {
797
+ "args": {
798
+ "should_epoch_stop": false,
799
+ "should_evaluate": false,
800
+ "should_log": false,
801
+ "should_save": true,
802
+ "should_training_stop": true
803
+ },
804
+ "attributes": {}
805
+ }
806
+ },
807
+ "total_flos": 109892759371776.0,
808
+ "train_batch_size": 4,
809
+ "trial_name": null,
810
+ "trial_params": null
811
+ }
checkpoint-1104/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdcca55b05009ba158cf393bed852a146a2c6196feb7ea8edd64cb7f7e5f6a66
3
+ size 5368
checkpoint-1104/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Aug11_08-00-49_32f9660e4c7f/events.out.tfevents.1754899250.32f9660e4c7f.357.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc3e86e89d4b9c8f59032b148b7181d8314b6cda429c27a3629d886521441c6
3
+ size 29061
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdcca55b05009ba158cf393bed852a146a2c6196feb7ea8edd64cb7f7e5f6a66
3
+ size 5368
training_metadata.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_file": "construction_risk_natural_scenarios.jsonl",
3
+ "training_samples": 551,
4
+ "cause_weights": {
5
+ "Caught In Between": 8.193548387096774,
6
+ "Struck By Object": 3.097560975609756,
7
+ "Electrocution": 3.4324324324324325,
8
+ "Falls": 1.0,
9
+ "Transportation Incidents": 3.4324324324324325,
10
+ "Other/Unspecified": 12.7,
11
+ "Contact With Objects": 16.933333333333334,
12
+ "Exposure Harmful Substances": 254.0
13
+ },
14
+ "optimization_config": {
15
+ "learning_rate": 0.0001,
16
+ "batch_size": 4,
17
+ "max_length": 256,
18
+ "epochs": 8,
19
+ "lora_r": 8,
20
+ "lora_alpha": 16,
21
+ "label_smoothing": 0.05,
22
+ "gradient_clipping": 1.0
23
+ }
24
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff