kkondratenko commited on
Commit
765b5fc
1 Parent(s): 99f2cf5

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. adapter_config.json +34 -0
  2. adapter_model.safetensors +3 -0
  3. checkpoint-10/README.md +202 -0
  4. checkpoint-10/adapter_config.json +34 -0
  5. checkpoint-10/adapter_model.safetensors +3 -0
  6. checkpoint-10/optimizer.pt +3 -0
  7. checkpoint-10/rng_state.pth +3 -0
  8. checkpoint-10/scheduler.pt +3 -0
  9. checkpoint-10/special_tokens_map.json +24 -0
  10. checkpoint-10/tokenizer.json +0 -0
  11. checkpoint-10/tokenizer.model +3 -0
  12. checkpoint-10/tokenizer_config.json +0 -0
  13. checkpoint-10/trainer_state.json +111 -0
  14. checkpoint-10/training_args.bin +3 -0
  15. checkpoint-100/README.md +202 -0
  16. checkpoint-100/adapter_config.json +34 -0
  17. checkpoint-100/adapter_model.safetensors +3 -0
  18. checkpoint-100/optimizer.pt +3 -0
  19. checkpoint-100/rng_state.pth +3 -0
  20. checkpoint-100/scheduler.pt +3 -0
  21. checkpoint-100/special_tokens_map.json +24 -0
  22. checkpoint-100/tokenizer.json +0 -0
  23. checkpoint-100/tokenizer.model +3 -0
  24. checkpoint-100/tokenizer_config.json +0 -0
  25. checkpoint-100/trainer_state.json +813 -0
  26. checkpoint-100/training_args.bin +3 -0
  27. checkpoint-110/README.md +202 -0
  28. checkpoint-110/adapter_config.json +34 -0
  29. checkpoint-110/adapter_model.safetensors +3 -0
  30. checkpoint-110/optimizer.pt +3 -0
  31. checkpoint-110/rng_state.pth +3 -0
  32. checkpoint-110/scheduler.pt +3 -0
  33. checkpoint-110/special_tokens_map.json +24 -0
  34. checkpoint-110/tokenizer.json +0 -0
  35. checkpoint-110/tokenizer.model +3 -0
  36. checkpoint-110/tokenizer_config.json +0 -0
  37. checkpoint-110/trainer_state.json +891 -0
  38. checkpoint-110/training_args.bin +3 -0
  39. checkpoint-20/README.md +202 -0
  40. checkpoint-20/adapter_config.json +34 -0
  41. checkpoint-20/adapter_model.safetensors +3 -0
  42. checkpoint-20/optimizer.pt +3 -0
  43. checkpoint-20/rng_state.pth +3 -0
  44. checkpoint-20/scheduler.pt +3 -0
  45. checkpoint-20/special_tokens_map.json +24 -0
  46. checkpoint-20/tokenizer.json +0 -0
  47. checkpoint-20/tokenizer.model +3 -0
  48. checkpoint-20/tokenizer_config.json +0 -0
  49. checkpoint-20/trainer_state.json +189 -0
  50. checkpoint-20/training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "q_proj",
26
+ "down_proj",
27
+ "up_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c9f905aed6e9f25263fb744a20a44aba1ee4946e9276f85bc3e907d6ea8847
3
+ size 83945296
checkpoint-10/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-10/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "q_proj",
26
+ "down_proj",
27
+ "up_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-10/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe1b2cb2b5176cb07aa02075bc7cfe7eb278aba26212c95e04733fb7465e9c0
3
+ size 83945296
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bafc6de9bf265cdd38aea5c6fbb52ee0106731dc3472f866e2e78ff4c6c213
3
+ size 42540500
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de81d42cc9ea8b47c3155988e70def875630cb4ba9d8c9ea987f752eaf1f5e8
3
+ size 14244
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3e785bf0a7658fe59029a42c1352ce61fa0ff388a14ece7afca8f7691316d2
3
+ size 1064
checkpoint-10/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-10/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
checkpoint-10/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.08771929824561403,
5
+ "eval_steps": 10,
6
+ "global_step": 10,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008771929824561403,
13
+ "grad_norm": 2.5680806636810303,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 1.6563,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017543859649122806,
20
+ "grad_norm": 2.0647432804107666,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 1.5849,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02631578947368421,
27
+ "grad_norm": 2.114915132522583,
28
+ "learning_rate": 5e-05,
29
+ "loss": 1.5868,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03508771929824561,
34
+ "grad_norm": 1.7573949098587036,
35
+ "learning_rate": 6.666666666666667e-05,
36
+ "loss": 1.6836,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.043859649122807015,
41
+ "grad_norm": 1.5793524980545044,
42
+ "learning_rate": 8.333333333333334e-05,
43
+ "loss": 1.4172,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05263157894736842,
48
+ "grad_norm": 1.7891627550125122,
49
+ "learning_rate": 0.0001,
50
+ "loss": 1.4405,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06140350877192982,
55
+ "grad_norm": 1.7529516220092773,
56
+ "learning_rate": 0.00011666666666666668,
57
+ "loss": 1.5647,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07017543859649122,
62
+ "grad_norm": 1.3582255840301514,
63
+ "learning_rate": 0.00013333333333333334,
64
+ "loss": 1.4112,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07894736842105263,
69
+ "grad_norm": 1.7452667951583862,
70
+ "learning_rate": 0.00015000000000000001,
71
+ "loss": 1.6427,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08771929824561403,
76
+ "grad_norm": 1.2840348482131958,
77
+ "learning_rate": 0.0001666666666666667,
78
+ "loss": 1.3915,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.08771929824561403,
83
+ "eval_loss": 1.3244520425796509,
84
+ "eval_runtime": 147.2051,
85
+ "eval_samples_per_second": 0.238,
86
+ "eval_steps_per_second": 0.041,
87
+ "step": 10
88
+ }
89
+ ],
90
+ "logging_steps": 1,
91
+ "max_steps": 114,
92
+ "num_input_tokens_seen": 0,
93
+ "num_train_epochs": 1,
94
+ "save_steps": 10,
95
+ "stateful_callbacks": {
96
+ "TrainerControl": {
97
+ "args": {
98
+ "should_epoch_stop": false,
99
+ "should_evaluate": false,
100
+ "should_log": false,
101
+ "should_save": true,
102
+ "should_training_stop": false
103
+ },
104
+ "attributes": {}
105
+ }
106
+ },
107
+ "total_flos": 2630164320092160.0,
108
+ "train_batch_size": 6,
109
+ "trial_name": null,
110
+ "trial_params": null
111
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5544cf0b69d25bfc7badefdf1d7d0f070dbf45678b2edf3c080e026b44041bd
3
+ size 5368
checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "q_proj",
26
+ "down_proj",
27
+ "up_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4c87d4ed22dcf4d305ef4d678bee1c023dd4a1343f217a760a4394df913b7bd
3
+ size 83945296
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:209defe0cb389c3d287c01491edff45a5f7b290403d9ada0026836b41c090e41
3
+ size 42540500
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde3e59b895f1def06e81f5bbfc523a1cbb8d08bd6d917ae44e4e00b77f30f88
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bc51dba652b6e8fca82062256d36d60a197bf038f986d4b3dc94faa81fb526
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
checkpoint-100/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,813 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8771929824561403,
5
+ "eval_steps": 10,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008771929824561403,
13
+ "grad_norm": 2.5680806636810303,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 1.6563,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017543859649122806,
20
+ "grad_norm": 2.0647432804107666,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 1.5849,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02631578947368421,
27
+ "grad_norm": 2.114915132522583,
28
+ "learning_rate": 5e-05,
29
+ "loss": 1.5868,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03508771929824561,
34
+ "grad_norm": 1.7573949098587036,
35
+ "learning_rate": 6.666666666666667e-05,
36
+ "loss": 1.6836,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.043859649122807015,
41
+ "grad_norm": 1.5793524980545044,
42
+ "learning_rate": 8.333333333333334e-05,
43
+ "loss": 1.4172,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05263157894736842,
48
+ "grad_norm": 1.7891627550125122,
49
+ "learning_rate": 0.0001,
50
+ "loss": 1.4405,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06140350877192982,
55
+ "grad_norm": 1.7529516220092773,
56
+ "learning_rate": 0.00011666666666666668,
57
+ "loss": 1.5647,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07017543859649122,
62
+ "grad_norm": 1.3582255840301514,
63
+ "learning_rate": 0.00013333333333333334,
64
+ "loss": 1.4112,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07894736842105263,
69
+ "grad_norm": 1.7452667951583862,
70
+ "learning_rate": 0.00015000000000000001,
71
+ "loss": 1.6427,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08771929824561403,
76
+ "grad_norm": 1.2840348482131958,
77
+ "learning_rate": 0.0001666666666666667,
78
+ "loss": 1.3915,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.08771929824561403,
83
+ "eval_loss": 1.3244520425796509,
84
+ "eval_runtime": 147.2051,
85
+ "eval_samples_per_second": 0.238,
86
+ "eval_steps_per_second": 0.041,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.09649122807017543,
91
+ "grad_norm": 2.1381897926330566,
92
+ "learning_rate": 0.00018333333333333334,
93
+ "loss": 1.3884,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.10526315789473684,
98
+ "grad_norm": 4.329859733581543,
99
+ "learning_rate": 0.0002,
100
+ "loss": 1.2958,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.11403508771929824,
105
+ "grad_norm": 2.177532196044922,
106
+ "learning_rate": 0.0001999525719713366,
107
+ "loss": 1.3211,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.12280701754385964,
112
+ "grad_norm": 2.4973137378692627,
113
+ "learning_rate": 0.00019981033287370443,
114
+ "loss": 1.2851,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.13157894736842105,
119
+ "grad_norm": 1.3471475839614868,
120
+ "learning_rate": 0.00019957341762950344,
121
+ "loss": 1.1561,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.14035087719298245,
126
+ "grad_norm": 1.4363510608673096,
127
+ "learning_rate": 0.0001992420509671936,
128
+ "loss": 1.364,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.14912280701754385,
133
+ "grad_norm": 1.6065610647201538,
134
+ "learning_rate": 0.00019881654720812594,
135
+ "loss": 1.1038,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.15789473684210525,
140
+ "grad_norm": 1.760709524154663,
141
+ "learning_rate": 0.0001982973099683902,
142
+ "loss": 1.3887,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.16666666666666666,
147
+ "grad_norm": 1.1617190837860107,
148
+ "learning_rate": 0.0001976848317759601,
149
+ "loss": 1.1831,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.17543859649122806,
154
+ "grad_norm": 0.8196442127227783,
155
+ "learning_rate": 0.00019697969360350098,
156
+ "loss": 1.01,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.17543859649122806,
161
+ "eval_loss": 1.1859098672866821,
162
+ "eval_runtime": 147.2373,
163
+ "eval_samples_per_second": 0.238,
164
+ "eval_steps_per_second": 0.041,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.18421052631578946,
169
+ "grad_norm": 1.0864627361297607,
170
+ "learning_rate": 0.00019618256431728194,
171
+ "loss": 1.2571,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.19298245614035087,
176
+ "grad_norm": 1.0493121147155762,
177
+ "learning_rate": 0.00019529420004271567,
178
+ "loss": 1.2444,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.20175438596491227,
183
+ "grad_norm": 0.7594426274299622,
184
+ "learning_rate": 0.00019431544344712776,
185
+ "loss": 1.1901,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.21052631578947367,
190
+ "grad_norm": 0.8312293887138367,
191
+ "learning_rate": 0.00019324722294043558,
192
+ "loss": 1.1946,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.21929824561403508,
197
+ "grad_norm": 0.8098247051239014,
198
+ "learning_rate": 0.0001920905517944954,
199
+ "loss": 1.1373,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.22807017543859648,
204
+ "grad_norm": 0.758610188961029,
205
+ "learning_rate": 0.00019084652718195238,
206
+ "loss": 1.362,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.23684210526315788,
211
+ "grad_norm": 0.7639715075492859,
212
+ "learning_rate": 0.00018951632913550626,
213
+ "loss": 1.1461,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.24561403508771928,
218
+ "grad_norm": 0.7925757765769958,
219
+ "learning_rate": 0.00018810121942857845,
220
+ "loss": 1.0797,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.2543859649122807,
225
+ "grad_norm": 0.7546517252922058,
226
+ "learning_rate": 0.00018660254037844388,
227
+ "loss": 1.2458,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.2631578947368421,
232
+ "grad_norm": 0.6947766542434692,
233
+ "learning_rate": 0.00018502171357296144,
234
+ "loss": 1.078,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.2631578947368421,
239
+ "eval_loss": 1.1665399074554443,
240
+ "eval_runtime": 147.8779,
241
+ "eval_samples_per_second": 0.237,
242
+ "eval_steps_per_second": 0.041,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.2719298245614035,
247
+ "grad_norm": 0.7786549925804138,
248
+ "learning_rate": 0.00018336023852211195,
249
+ "loss": 1.1101,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.2807017543859649,
254
+ "grad_norm": 1.0710453987121582,
255
+ "learning_rate": 0.0001816196912356222,
256
+ "loss": 1.2739,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.2894736842105263,
261
+ "grad_norm": 0.7918573021888733,
262
+ "learning_rate": 0.000179801722728024,
263
+ "loss": 0.9907,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.2982456140350877,
268
+ "grad_norm": 0.6867886185646057,
269
+ "learning_rate": 0.00017790805745256704,
270
+ "loss": 1.0217,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.30701754385964913,
275
+ "grad_norm": 0.7449227571487427,
276
+ "learning_rate": 0.00017594049166547073,
277
+ "loss": 0.9821,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.3157894736842105,
282
+ "grad_norm": 0.6568706631660461,
283
+ "learning_rate": 0.00017390089172206592,
284
+ "loss": 0.9773,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.32456140350877194,
289
+ "grad_norm": 0.8175464272499084,
290
+ "learning_rate": 0.0001717911923064442,
291
+ "loss": 1.2461,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.3333333333333333,
296
+ "grad_norm": 0.8352490663528442,
297
+ "learning_rate": 0.0001696133945962927,
298
+ "loss": 1.1108,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.34210526315789475,
303
+ "grad_norm": 0.7964888215065002,
304
+ "learning_rate": 0.00016736956436465573,
305
+ "loss": 1.1794,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.3508771929824561,
310
+ "grad_norm": 0.815345048904419,
311
+ "learning_rate": 0.0001650618300204242,
312
+ "loss": 1.1293,
313
+ "step": 40
314
+ },
315
+ {
316
+ "epoch": 0.3508771929824561,
317
+ "eval_loss": 1.1598470211029053,
318
+ "eval_runtime": 147.6693,
319
+ "eval_samples_per_second": 0.237,
320
+ "eval_steps_per_second": 0.041,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.35964912280701755,
325
+ "grad_norm": 0.7715421915054321,
326
+ "learning_rate": 0.0001626923805894107,
327
+ "loss": 1.0438,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.3684210526315789,
332
+ "grad_norm": 0.8257682919502258,
333
+ "learning_rate": 0.00016026346363792567,
334
+ "loss": 1.2495,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.37719298245614036,
339
+ "grad_norm": 0.8071096539497375,
340
+ "learning_rate": 0.00015777738314082514,
341
+ "loss": 1.2658,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.38596491228070173,
346
+ "grad_norm": 0.7582301497459412,
347
+ "learning_rate": 0.0001552364972960506,
348
+ "loss": 1.0439,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.39473684210526316,
353
+ "grad_norm": 0.6937515735626221,
354
+ "learning_rate": 0.0001526432162877356,
355
+ "loss": 1.1816,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.40350877192982454,
360
+ "grad_norm": 0.8269925117492676,
361
+ "learning_rate": 0.00015000000000000001,
362
+ "loss": 1.2806,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.41228070175438597,
367
+ "grad_norm": 0.7588099837303162,
368
+ "learning_rate": 0.00014730935568360102,
369
+ "loss": 1.3503,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.42105263157894735,
374
+ "grad_norm": 0.7436806559562683,
375
+ "learning_rate": 0.00014457383557765386,
376
+ "loss": 1.2563,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.4298245614035088,
381
+ "grad_norm": 0.7608836889266968,
382
+ "learning_rate": 0.00014179603448867835,
383
+ "loss": 1.0735,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.43859649122807015,
388
+ "grad_norm": 0.6600857973098755,
389
+ "learning_rate": 0.00013897858732926793,
390
+ "loss": 0.9887,
391
+ "step": 50
392
+ },
393
+ {
394
+ "epoch": 0.43859649122807015,
395
+ "eval_loss": 1.1527005434036255,
396
+ "eval_runtime": 147.8951,
397
+ "eval_samples_per_second": 0.237,
398
+ "eval_steps_per_second": 0.041,
399
+ "step": 50
400
+ },
401
+ {
402
+ "epoch": 0.4473684210526316,
403
+ "grad_norm": 0.7786328792572021,
404
+ "learning_rate": 0.00013612416661871533,
405
+ "loss": 1.4409,
406
+ "step": 51
407
+ },
408
+ {
409
+ "epoch": 0.45614035087719296,
410
+ "grad_norm": 0.684889018535614,
411
+ "learning_rate": 0.00013323547994796597,
412
+ "loss": 1.0834,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 0.4649122807017544,
417
+ "grad_norm": 0.6802189946174622,
418
+ "learning_rate": 0.00013031526741130435,
419
+ "loss": 0.9769,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 0.47368421052631576,
424
+ "grad_norm": 0.6572148203849792,
425
+ "learning_rate": 0.0001273662990072083,
426
+ "loss": 1.2772,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 0.4824561403508772,
431
+ "grad_norm": 0.650672435760498,
432
+ "learning_rate": 0.00012439137201083773,
433
+ "loss": 1.1134,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 0.49122807017543857,
438
+ "grad_norm": 0.7156693935394287,
439
+ "learning_rate": 0.00012139330832064974,
440
+ "loss": 1.2887,
441
+ "step": 56
442
+ },
443
+ {
444
+ "epoch": 0.5,
445
+ "grad_norm": 0.7310993075370789,
446
+ "learning_rate": 0.00011837495178165706,
447
+ "loss": 1.3283,
448
+ "step": 57
449
+ },
450
+ {
451
+ "epoch": 0.5087719298245614,
452
+ "grad_norm": 0.6791104078292847,
453
+ "learning_rate": 0.00011533916548786857,
454
+ "loss": 1.1324,
455
+ "step": 58
456
+ },
457
+ {
458
+ "epoch": 0.5175438596491229,
459
+ "grad_norm": 0.6673245429992676,
460
+ "learning_rate": 0.00011228882906647142,
461
+ "loss": 1.2071,
462
+ "step": 59
463
+ },
464
+ {
465
+ "epoch": 0.5263157894736842,
466
+ "grad_norm": 0.6640443205833435,
467
+ "learning_rate": 0.00010922683594633021,
468
+ "loss": 1.0523,
469
+ "step": 60
470
+ },
471
+ {
472
+ "epoch": 0.5263157894736842,
473
+ "eval_loss": 1.1480591297149658,
474
+ "eval_runtime": 148.2201,
475
+ "eval_samples_per_second": 0.236,
476
+ "eval_steps_per_second": 0.04,
477
+ "step": 60
478
+ },
479
+ {
480
+ "epoch": 0.5350877192982456,
481
+ "grad_norm": 0.6989058256149292,
482
+ "learning_rate": 0.00010615609061339432,
483
+ "loss": 1.1466,
484
+ "step": 61
485
+ },
486
+ {
487
+ "epoch": 0.543859649122807,
488
+ "grad_norm": 0.6784482598304749,
489
+ "learning_rate": 0.00010307950585561706,
490
+ "loss": 1.2856,
491
+ "step": 62
492
+ },
493
+ {
494
+ "epoch": 0.5526315789473685,
495
+ "grad_norm": 0.6532306671142578,
496
+ "learning_rate": 0.0001,
497
+ "loss": 1.0581,
498
+ "step": 63
499
+ },
500
+ {
501
+ "epoch": 0.5614035087719298,
502
+ "grad_norm": 0.6561712622642517,
503
+ "learning_rate": 9.692049414438299e-05,
504
+ "loss": 1.1082,
505
+ "step": 64
506
+ },
507
+ {
508
+ "epoch": 0.5701754385964912,
509
+ "grad_norm": 0.7943727374076843,
510
+ "learning_rate": 9.384390938660572e-05,
511
+ "loss": 1.1544,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 0.5789473684210527,
516
+ "grad_norm": 0.6938879489898682,
517
+ "learning_rate": 9.077316405366981e-05,
518
+ "loss": 1.1486,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 0.5877192982456141,
523
+ "grad_norm": 0.6842483878135681,
524
+ "learning_rate": 8.77111709335286e-05,
525
+ "loss": 0.9964,
526
+ "step": 67
527
+ },
528
+ {
529
+ "epoch": 0.5964912280701754,
530
+ "grad_norm": 0.7236644625663757,
531
+ "learning_rate": 8.466083451213144e-05,
532
+ "loss": 1.265,
533
+ "step": 68
534
+ },
535
+ {
536
+ "epoch": 0.6052631578947368,
537
+ "grad_norm": 0.658785879611969,
538
+ "learning_rate": 8.162504821834295e-05,
539
+ "loss": 1.0674,
540
+ "step": 69
541
+ },
542
+ {
543
+ "epoch": 0.6140350877192983,
544
+ "grad_norm": 0.6507206559181213,
545
+ "learning_rate": 7.860669167935028e-05,
546
+ "loss": 1.2665,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 0.6140350877192983,
551
+ "eval_loss": 1.144606351852417,
552
+ "eval_runtime": 148.057,
553
+ "eval_samples_per_second": 0.236,
554
+ "eval_steps_per_second": 0.041,
555
+ "step": 70
556
+ },
557
+ {
558
+ "epoch": 0.6228070175438597,
559
+ "grad_norm": 1.4312708377838135,
560
+ "learning_rate": 7.560862798916228e-05,
561
+ "loss": 1.1584,
562
+ "step": 71
563
+ },
564
+ {
565
+ "epoch": 0.631578947368421,
566
+ "grad_norm": 0.7182056307792664,
567
+ "learning_rate": 7.263370099279172e-05,
568
+ "loss": 1.0757,
569
+ "step": 72
570
+ },
571
+ {
572
+ "epoch": 0.6403508771929824,
573
+ "grad_norm": 0.6891857385635376,
574
+ "learning_rate": 6.968473258869566e-05,
575
+ "loss": 1.0821,
576
+ "step": 73
577
+ },
578
+ {
579
+ "epoch": 0.6491228070175439,
580
+ "grad_norm": 0.6840397119522095,
581
+ "learning_rate": 6.676452005203406e-05,
582
+ "loss": 0.9936,
583
+ "step": 74
584
+ },
585
+ {
586
+ "epoch": 0.6578947368421053,
587
+ "grad_norm": 0.6172062754631042,
588
+ "learning_rate": 6.387583338128471e-05,
589
+ "loss": 1.0458,
590
+ "step": 75
591
+ },
592
+ {
593
+ "epoch": 0.6666666666666666,
594
+ "grad_norm": 0.6407103538513184,
595
+ "learning_rate": 6.102141267073207e-05,
596
+ "loss": 1.0171,
597
+ "step": 76
598
+ },
599
+ {
600
+ "epoch": 0.6754385964912281,
601
+ "grad_norm": 0.9195757508277893,
602
+ "learning_rate": 5.82039655113217e-05,
603
+ "loss": 1.358,
604
+ "step": 77
605
+ },
606
+ {
607
+ "epoch": 0.6842105263157895,
608
+ "grad_norm": 0.6789188385009766,
609
+ "learning_rate": 5.542616442234618e-05,
610
+ "loss": 1.1702,
611
+ "step": 78
612
+ },
613
+ {
614
+ "epoch": 0.6929824561403509,
615
+ "grad_norm": 0.759657084941864,
616
+ "learning_rate": 5.269064431639901e-05,
617
+ "loss": 1.157,
618
+ "step": 79
619
+ },
620
+ {
621
+ "epoch": 0.7017543859649122,
622
+ "grad_norm": 0.7847995162010193,
623
+ "learning_rate": 5.000000000000002e-05,
624
+ "loss": 1.1225,
625
+ "step": 80
626
+ },
627
+ {
628
+ "epoch": 0.7017543859649122,
629
+ "eval_loss": 1.1422388553619385,
630
+ "eval_runtime": 148.829,
631
+ "eval_samples_per_second": 0.235,
632
+ "eval_steps_per_second": 0.04,
633
+ "step": 80
634
+ },
635
+ {
636
+ "epoch": 0.7105263157894737,
637
+ "grad_norm": 0.6668726205825806,
638
+ "learning_rate": 4.735678371226441e-05,
639
+ "loss": 1.0248,
640
+ "step": 81
641
+ },
642
+ {
643
+ "epoch": 0.7192982456140351,
644
+ "grad_norm": 0.9492083787918091,
645
+ "learning_rate": 4.476350270394942e-05,
646
+ "loss": 1.263,
647
+ "step": 82
648
+ },
649
+ {
650
+ "epoch": 0.7280701754385965,
651
+ "grad_norm": 0.7178658843040466,
652
+ "learning_rate": 4.222261685917489e-05,
653
+ "loss": 1.3507,
654
+ "step": 83
655
+ },
656
+ {
657
+ "epoch": 0.7368421052631579,
658
+ "grad_norm": 0.75201416015625,
659
+ "learning_rate": 3.973653636207437e-05,
660
+ "loss": 1.2211,
661
+ "step": 84
662
+ },
663
+ {
664
+ "epoch": 0.7456140350877193,
665
+ "grad_norm": 0.6311876773834229,
666
+ "learning_rate": 3.7307619410589376e-05,
667
+ "loss": 1.0633,
668
+ "step": 85
669
+ },
670
+ {
671
+ "epoch": 0.7543859649122807,
672
+ "grad_norm": 0.5766677856445312,
673
+ "learning_rate": 3.493816997957582e-05,
674
+ "loss": 0.9034,
675
+ "step": 86
676
+ },
677
+ {
678
+ "epoch": 0.7631578947368421,
679
+ "grad_norm": 0.6574028134346008,
680
+ "learning_rate": 3.263043563534428e-05,
681
+ "loss": 1.0327,
682
+ "step": 87
683
+ },
684
+ {
685
+ "epoch": 0.7719298245614035,
686
+ "grad_norm": 0.7002457976341248,
687
+ "learning_rate": 3.0386605403707346e-05,
688
+ "loss": 1.1285,
689
+ "step": 88
690
+ },
691
+ {
692
+ "epoch": 0.7807017543859649,
693
+ "grad_norm": 0.6196402311325073,
694
+ "learning_rate": 2.8208807693555818e-05,
695
+ "loss": 1.0958,
696
+ "step": 89
697
+ },
698
+ {
699
+ "epoch": 0.7894736842105263,
700
+ "grad_norm": 0.69408118724823,
701
+ "learning_rate": 2.6099108277934103e-05,
702
+ "loss": 1.3329,
703
+ "step": 90
704
+ },
705
+ {
706
+ "epoch": 0.7894736842105263,
707
+ "eval_loss": 1.140186071395874,
708
+ "eval_runtime": 147.8753,
709
+ "eval_samples_per_second": 0.237,
710
+ "eval_steps_per_second": 0.041,
711
+ "step": 90
712
+ },
713
+ {
714
+ "epoch": 0.7982456140350878,
715
+ "grad_norm": 0.5900521874427795,
716
+ "learning_rate": 2.405950833452928e-05,
717
+ "loss": 1.0236,
718
+ "step": 91
719
+ },
720
+ {
721
+ "epoch": 0.8070175438596491,
722
+ "grad_norm": 0.629959225654602,
723
+ "learning_rate": 2.2091942547432955e-05,
724
+ "loss": 1.0549,
725
+ "step": 92
726
+ },
727
+ {
728
+ "epoch": 0.8157894736842105,
729
+ "grad_norm": 0.6783764362335205,
730
+ "learning_rate": 2.0198277271976052e-05,
731
+ "loss": 1.018,
732
+ "step": 93
733
+ },
734
+ {
735
+ "epoch": 0.8245614035087719,
736
+ "grad_norm": 0.6238540410995483,
737
+ "learning_rate": 1.8380308764377842e-05,
738
+ "loss": 1.1294,
739
+ "step": 94
740
+ },
741
+ {
742
+ "epoch": 0.8333333333333334,
743
+ "grad_norm": 0.6851047277450562,
744
+ "learning_rate": 1.663976147788806e-05,
745
+ "loss": 1.1071,
746
+ "step": 95
747
+ },
748
+ {
749
+ "epoch": 0.8421052631578947,
750
+ "grad_norm": 0.6557275652885437,
751
+ "learning_rate": 1.4978286427038601e-05,
752
+ "loss": 1.1069,
753
+ "step": 96
754
+ },
755
+ {
756
+ "epoch": 0.8508771929824561,
757
+ "grad_norm": 0.6950388550758362,
758
+ "learning_rate": 1.339745962155613e-05,
759
+ "loss": 1.362,
760
+ "step": 97
761
+ },
762
+ {
763
+ "epoch": 0.8596491228070176,
764
+ "grad_norm": 0.685569703578949,
765
+ "learning_rate": 1.1898780571421552e-05,
766
+ "loss": 1.2406,
767
+ "step": 98
768
+ },
769
+ {
770
+ "epoch": 0.868421052631579,
771
+ "grad_norm": 0.9577943086624146,
772
+ "learning_rate": 1.0483670864493778e-05,
773
+ "loss": 1.2133,
774
+ "step": 99
775
+ },
776
+ {
777
+ "epoch": 0.8771929824561403,
778
+ "grad_norm": 0.8101325631141663,
779
+ "learning_rate": 9.153472818047625e-06,
780
+ "loss": 1.2042,
781
+ "step": 100
782
+ },
783
+ {
784
+ "epoch": 0.8771929824561403,
785
+ "eval_loss": 1.1394405364990234,
786
+ "eval_runtime": 148.8314,
787
+ "eval_samples_per_second": 0.235,
788
+ "eval_steps_per_second": 0.04,
789
+ "step": 100
790
+ }
791
+ ],
792
+ "logging_steps": 1,
793
+ "max_steps": 114,
794
+ "num_input_tokens_seen": 0,
795
+ "num_train_epochs": 1,
796
+ "save_steps": 10,
797
+ "stateful_callbacks": {
798
+ "TrainerControl": {
799
+ "args": {
800
+ "should_epoch_stop": false,
801
+ "should_evaluate": false,
802
+ "should_log": false,
803
+ "should_save": true,
804
+ "should_training_stop": false
805
+ },
806
+ "attributes": {}
807
+ }
808
+ },
809
+ "total_flos": 2.63016432009216e+16,
810
+ "train_batch_size": 6,
811
+ "trial_name": null,
812
+ "trial_params": null
813
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5544cf0b69d25bfc7badefdf1d7d0f070dbf45678b2edf3c080e026b44041bd
3
+ size 5368
checkpoint-110/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-110/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "q_proj",
26
+ "down_proj",
27
+ "up_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-110/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11070ea8fa8da74d35764cf884829059d0dd0467d18753bce80853af0702c590
3
+ size 83945296
checkpoint-110/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8660c04581911394054e162cf27e2c7110e01f93ba298b6c2b840872cbcdcc50
3
+ size 42540500
checkpoint-110/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1afef9e41d980bfe559dad8462a9cd63edf4e1430cd1aca2f3430c94cee1bccd
3
+ size 14244
checkpoint-110/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b119427a76fa40d46bf3a4ea91287fb996ae10077b5b8815fd12b8fc343ece4b
3
+ size 1064
checkpoint-110/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-110/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-110/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
checkpoint-110/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-110/trainer_state.json ADDED
@@ -0,0 +1,891 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9649122807017544,
5
+ "eval_steps": 10,
6
+ "global_step": 110,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008771929824561403,
13
+ "grad_norm": 2.5680806636810303,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 1.6563,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017543859649122806,
20
+ "grad_norm": 2.0647432804107666,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 1.5849,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02631578947368421,
27
+ "grad_norm": 2.114915132522583,
28
+ "learning_rate": 5e-05,
29
+ "loss": 1.5868,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03508771929824561,
34
+ "grad_norm": 1.7573949098587036,
35
+ "learning_rate": 6.666666666666667e-05,
36
+ "loss": 1.6836,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.043859649122807015,
41
+ "grad_norm": 1.5793524980545044,
42
+ "learning_rate": 8.333333333333334e-05,
43
+ "loss": 1.4172,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05263157894736842,
48
+ "grad_norm": 1.7891627550125122,
49
+ "learning_rate": 0.0001,
50
+ "loss": 1.4405,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06140350877192982,
55
+ "grad_norm": 1.7529516220092773,
56
+ "learning_rate": 0.00011666666666666668,
57
+ "loss": 1.5647,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07017543859649122,
62
+ "grad_norm": 1.3582255840301514,
63
+ "learning_rate": 0.00013333333333333334,
64
+ "loss": 1.4112,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07894736842105263,
69
+ "grad_norm": 1.7452667951583862,
70
+ "learning_rate": 0.00015000000000000001,
71
+ "loss": 1.6427,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08771929824561403,
76
+ "grad_norm": 1.2840348482131958,
77
+ "learning_rate": 0.0001666666666666667,
78
+ "loss": 1.3915,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.08771929824561403,
83
+ "eval_loss": 1.3244520425796509,
84
+ "eval_runtime": 147.2051,
85
+ "eval_samples_per_second": 0.238,
86
+ "eval_steps_per_second": 0.041,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.09649122807017543,
91
+ "grad_norm": 2.1381897926330566,
92
+ "learning_rate": 0.00018333333333333334,
93
+ "loss": 1.3884,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.10526315789473684,
98
+ "grad_norm": 4.329859733581543,
99
+ "learning_rate": 0.0002,
100
+ "loss": 1.2958,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.11403508771929824,
105
+ "grad_norm": 2.177532196044922,
106
+ "learning_rate": 0.0001999525719713366,
107
+ "loss": 1.3211,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.12280701754385964,
112
+ "grad_norm": 2.4973137378692627,
113
+ "learning_rate": 0.00019981033287370443,
114
+ "loss": 1.2851,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.13157894736842105,
119
+ "grad_norm": 1.3471475839614868,
120
+ "learning_rate": 0.00019957341762950344,
121
+ "loss": 1.1561,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.14035087719298245,
126
+ "grad_norm": 1.4363510608673096,
127
+ "learning_rate": 0.0001992420509671936,
128
+ "loss": 1.364,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.14912280701754385,
133
+ "grad_norm": 1.6065610647201538,
134
+ "learning_rate": 0.00019881654720812594,
135
+ "loss": 1.1038,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.15789473684210525,
140
+ "grad_norm": 1.760709524154663,
141
+ "learning_rate": 0.0001982973099683902,
142
+ "loss": 1.3887,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.16666666666666666,
147
+ "grad_norm": 1.1617190837860107,
148
+ "learning_rate": 0.0001976848317759601,
149
+ "loss": 1.1831,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.17543859649122806,
154
+ "grad_norm": 0.8196442127227783,
155
+ "learning_rate": 0.00019697969360350098,
156
+ "loss": 1.01,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.17543859649122806,
161
+ "eval_loss": 1.1859098672866821,
162
+ "eval_runtime": 147.2373,
163
+ "eval_samples_per_second": 0.238,
164
+ "eval_steps_per_second": 0.041,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.18421052631578946,
169
+ "grad_norm": 1.0864627361297607,
170
+ "learning_rate": 0.00019618256431728194,
171
+ "loss": 1.2571,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.19298245614035087,
176
+ "grad_norm": 1.0493121147155762,
177
+ "learning_rate": 0.00019529420004271567,
178
+ "loss": 1.2444,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.20175438596491227,
183
+ "grad_norm": 0.7594426274299622,
184
+ "learning_rate": 0.00019431544344712776,
185
+ "loss": 1.1901,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.21052631578947367,
190
+ "grad_norm": 0.8312293887138367,
191
+ "learning_rate": 0.00019324722294043558,
192
+ "loss": 1.1946,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.21929824561403508,
197
+ "grad_norm": 0.8098247051239014,
198
+ "learning_rate": 0.0001920905517944954,
199
+ "loss": 1.1373,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.22807017543859648,
204
+ "grad_norm": 0.758610188961029,
205
+ "learning_rate": 0.00019084652718195238,
206
+ "loss": 1.362,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.23684210526315788,
211
+ "grad_norm": 0.7639715075492859,
212
+ "learning_rate": 0.00018951632913550626,
213
+ "loss": 1.1461,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.24561403508771928,
218
+ "grad_norm": 0.7925757765769958,
219
+ "learning_rate": 0.00018810121942857845,
220
+ "loss": 1.0797,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.2543859649122807,
225
+ "grad_norm": 0.7546517252922058,
226
+ "learning_rate": 0.00018660254037844388,
227
+ "loss": 1.2458,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.2631578947368421,
232
+ "grad_norm": 0.6947766542434692,
233
+ "learning_rate": 0.00018502171357296144,
234
+ "loss": 1.078,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.2631578947368421,
239
+ "eval_loss": 1.1665399074554443,
240
+ "eval_runtime": 147.8779,
241
+ "eval_samples_per_second": 0.237,
242
+ "eval_steps_per_second": 0.041,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.2719298245614035,
247
+ "grad_norm": 0.7786549925804138,
248
+ "learning_rate": 0.00018336023852211195,
249
+ "loss": 1.1101,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.2807017543859649,
254
+ "grad_norm": 1.0710453987121582,
255
+ "learning_rate": 0.0001816196912356222,
256
+ "loss": 1.2739,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.2894736842105263,
261
+ "grad_norm": 0.7918573021888733,
262
+ "learning_rate": 0.000179801722728024,
263
+ "loss": 0.9907,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.2982456140350877,
268
+ "grad_norm": 0.6867886185646057,
269
+ "learning_rate": 0.00017790805745256704,
270
+ "loss": 1.0217,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.30701754385964913,
275
+ "grad_norm": 0.7449227571487427,
276
+ "learning_rate": 0.00017594049166547073,
277
+ "loss": 0.9821,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.3157894736842105,
282
+ "grad_norm": 0.6568706631660461,
283
+ "learning_rate": 0.00017390089172206592,
284
+ "loss": 0.9773,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.32456140350877194,
289
+ "grad_norm": 0.8175464272499084,
290
+ "learning_rate": 0.0001717911923064442,
291
+ "loss": 1.2461,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.3333333333333333,
296
+ "grad_norm": 0.8352490663528442,
297
+ "learning_rate": 0.0001696133945962927,
298
+ "loss": 1.1108,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.34210526315789475,
303
+ "grad_norm": 0.7964888215065002,
304
+ "learning_rate": 0.00016736956436465573,
305
+ "loss": 1.1794,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.3508771929824561,
310
+ "grad_norm": 0.815345048904419,
311
+ "learning_rate": 0.0001650618300204242,
312
+ "loss": 1.1293,
313
+ "step": 40
314
+ },
315
+ {
316
+ "epoch": 0.3508771929824561,
317
+ "eval_loss": 1.1598470211029053,
318
+ "eval_runtime": 147.6693,
319
+ "eval_samples_per_second": 0.237,
320
+ "eval_steps_per_second": 0.041,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.35964912280701755,
325
+ "grad_norm": 0.7715421915054321,
326
+ "learning_rate": 0.0001626923805894107,
327
+ "loss": 1.0438,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.3684210526315789,
332
+ "grad_norm": 0.8257682919502258,
333
+ "learning_rate": 0.00016026346363792567,
334
+ "loss": 1.2495,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.37719298245614036,
339
+ "grad_norm": 0.8071096539497375,
340
+ "learning_rate": 0.00015777738314082514,
341
+ "loss": 1.2658,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.38596491228070173,
346
+ "grad_norm": 0.7582301497459412,
347
+ "learning_rate": 0.0001552364972960506,
348
+ "loss": 1.0439,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.39473684210526316,
353
+ "grad_norm": 0.6937515735626221,
354
+ "learning_rate": 0.0001526432162877356,
355
+ "loss": 1.1816,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.40350877192982454,
360
+ "grad_norm": 0.8269925117492676,
361
+ "learning_rate": 0.00015000000000000001,
362
+ "loss": 1.2806,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.41228070175438597,
367
+ "grad_norm": 0.7588099837303162,
368
+ "learning_rate": 0.00014730935568360102,
369
+ "loss": 1.3503,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.42105263157894735,
374
+ "grad_norm": 0.7436806559562683,
375
+ "learning_rate": 0.00014457383557765386,
376
+ "loss": 1.2563,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.4298245614035088,
381
+ "grad_norm": 0.7608836889266968,
382
+ "learning_rate": 0.00014179603448867835,
383
+ "loss": 1.0735,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.43859649122807015,
388
+ "grad_norm": 0.6600857973098755,
389
+ "learning_rate": 0.00013897858732926793,
390
+ "loss": 0.9887,
391
+ "step": 50
392
+ },
393
+ {
394
+ "epoch": 0.43859649122807015,
395
+ "eval_loss": 1.1527005434036255,
396
+ "eval_runtime": 147.8951,
397
+ "eval_samples_per_second": 0.237,
398
+ "eval_steps_per_second": 0.041,
399
+ "step": 50
400
+ },
401
+ {
402
+ "epoch": 0.4473684210526316,
403
+ "grad_norm": 0.7786328792572021,
404
+ "learning_rate": 0.00013612416661871533,
405
+ "loss": 1.4409,
406
+ "step": 51
407
+ },
408
+ {
409
+ "epoch": 0.45614035087719296,
410
+ "grad_norm": 0.684889018535614,
411
+ "learning_rate": 0.00013323547994796597,
412
+ "loss": 1.0834,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 0.4649122807017544,
417
+ "grad_norm": 0.6802189946174622,
418
+ "learning_rate": 0.00013031526741130435,
419
+ "loss": 0.9769,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 0.47368421052631576,
424
+ "grad_norm": 0.6572148203849792,
425
+ "learning_rate": 0.0001273662990072083,
426
+ "loss": 1.2772,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 0.4824561403508772,
431
+ "grad_norm": 0.650672435760498,
432
+ "learning_rate": 0.00012439137201083773,
433
+ "loss": 1.1134,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 0.49122807017543857,
438
+ "grad_norm": 0.7156693935394287,
439
+ "learning_rate": 0.00012139330832064974,
440
+ "loss": 1.2887,
441
+ "step": 56
442
+ },
443
+ {
444
+ "epoch": 0.5,
445
+ "grad_norm": 0.7310993075370789,
446
+ "learning_rate": 0.00011837495178165706,
447
+ "loss": 1.3283,
448
+ "step": 57
449
+ },
450
+ {
451
+ "epoch": 0.5087719298245614,
452
+ "grad_norm": 0.6791104078292847,
453
+ "learning_rate": 0.00011533916548786857,
454
+ "loss": 1.1324,
455
+ "step": 58
456
+ },
457
+ {
458
+ "epoch": 0.5175438596491229,
459
+ "grad_norm": 0.6673245429992676,
460
+ "learning_rate": 0.00011228882906647142,
461
+ "loss": 1.2071,
462
+ "step": 59
463
+ },
464
+ {
465
+ "epoch": 0.5263157894736842,
466
+ "grad_norm": 0.6640443205833435,
467
+ "learning_rate": 0.00010922683594633021,
468
+ "loss": 1.0523,
469
+ "step": 60
470
+ },
471
+ {
472
+ "epoch": 0.5263157894736842,
473
+ "eval_loss": 1.1480591297149658,
474
+ "eval_runtime": 148.2201,
475
+ "eval_samples_per_second": 0.236,
476
+ "eval_steps_per_second": 0.04,
477
+ "step": 60
478
+ },
479
+ {
480
+ "epoch": 0.5350877192982456,
481
+ "grad_norm": 0.6989058256149292,
482
+ "learning_rate": 0.00010615609061339432,
483
+ "loss": 1.1466,
484
+ "step": 61
485
+ },
486
+ {
487
+ "epoch": 0.543859649122807,
488
+ "grad_norm": 0.6784482598304749,
489
+ "learning_rate": 0.00010307950585561706,
490
+ "loss": 1.2856,
491
+ "step": 62
492
+ },
493
+ {
494
+ "epoch": 0.5526315789473685,
495
+ "grad_norm": 0.6532306671142578,
496
+ "learning_rate": 0.0001,
497
+ "loss": 1.0581,
498
+ "step": 63
499
+ },
500
+ {
501
+ "epoch": 0.5614035087719298,
502
+ "grad_norm": 0.6561712622642517,
503
+ "learning_rate": 9.692049414438299e-05,
504
+ "loss": 1.1082,
505
+ "step": 64
506
+ },
507
+ {
508
+ "epoch": 0.5701754385964912,
509
+ "grad_norm": 0.7943727374076843,
510
+ "learning_rate": 9.384390938660572e-05,
511
+ "loss": 1.1544,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 0.5789473684210527,
516
+ "grad_norm": 0.6938879489898682,
517
+ "learning_rate": 9.077316405366981e-05,
518
+ "loss": 1.1486,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 0.5877192982456141,
523
+ "grad_norm": 0.6842483878135681,
524
+ "learning_rate": 8.77111709335286e-05,
525
+ "loss": 0.9964,
526
+ "step": 67
527
+ },
528
+ {
529
+ "epoch": 0.5964912280701754,
530
+ "grad_norm": 0.7236644625663757,
531
+ "learning_rate": 8.466083451213144e-05,
532
+ "loss": 1.265,
533
+ "step": 68
534
+ },
535
+ {
536
+ "epoch": 0.6052631578947368,
537
+ "grad_norm": 0.658785879611969,
538
+ "learning_rate": 8.162504821834295e-05,
539
+ "loss": 1.0674,
540
+ "step": 69
541
+ },
542
+ {
543
+ "epoch": 0.6140350877192983,
544
+ "grad_norm": 0.6507206559181213,
545
+ "learning_rate": 7.860669167935028e-05,
546
+ "loss": 1.2665,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 0.6140350877192983,
551
+ "eval_loss": 1.144606351852417,
552
+ "eval_runtime": 148.057,
553
+ "eval_samples_per_second": 0.236,
554
+ "eval_steps_per_second": 0.041,
555
+ "step": 70
556
+ },
557
+ {
558
+ "epoch": 0.6228070175438597,
559
+ "grad_norm": 1.4312708377838135,
560
+ "learning_rate": 7.560862798916228e-05,
561
+ "loss": 1.1584,
562
+ "step": 71
563
+ },
564
+ {
565
+ "epoch": 0.631578947368421,
566
+ "grad_norm": 0.7182056307792664,
567
+ "learning_rate": 7.263370099279172e-05,
568
+ "loss": 1.0757,
569
+ "step": 72
570
+ },
571
+ {
572
+ "epoch": 0.6403508771929824,
573
+ "grad_norm": 0.6891857385635376,
574
+ "learning_rate": 6.968473258869566e-05,
575
+ "loss": 1.0821,
576
+ "step": 73
577
+ },
578
+ {
579
+ "epoch": 0.6491228070175439,
580
+ "grad_norm": 0.6840397119522095,
581
+ "learning_rate": 6.676452005203406e-05,
582
+ "loss": 0.9936,
583
+ "step": 74
584
+ },
585
+ {
586
+ "epoch": 0.6578947368421053,
587
+ "grad_norm": 0.6172062754631042,
588
+ "learning_rate": 6.387583338128471e-05,
589
+ "loss": 1.0458,
590
+ "step": 75
591
+ },
592
+ {
593
+ "epoch": 0.6666666666666666,
594
+ "grad_norm": 0.6407103538513184,
595
+ "learning_rate": 6.102141267073207e-05,
596
+ "loss": 1.0171,
597
+ "step": 76
598
+ },
599
+ {
600
+ "epoch": 0.6754385964912281,
601
+ "grad_norm": 0.9195757508277893,
602
+ "learning_rate": 5.82039655113217e-05,
603
+ "loss": 1.358,
604
+ "step": 77
605
+ },
606
+ {
607
+ "epoch": 0.6842105263157895,
608
+ "grad_norm": 0.6789188385009766,
609
+ "learning_rate": 5.542616442234618e-05,
610
+ "loss": 1.1702,
611
+ "step": 78
612
+ },
613
+ {
614
+ "epoch": 0.6929824561403509,
615
+ "grad_norm": 0.759657084941864,
616
+ "learning_rate": 5.269064431639901e-05,
617
+ "loss": 1.157,
618
+ "step": 79
619
+ },
620
+ {
621
+ "epoch": 0.7017543859649122,
622
+ "grad_norm": 0.7847995162010193,
623
+ "learning_rate": 5.000000000000002e-05,
624
+ "loss": 1.1225,
625
+ "step": 80
626
+ },
627
+ {
628
+ "epoch": 0.7017543859649122,
629
+ "eval_loss": 1.1422388553619385,
630
+ "eval_runtime": 148.829,
631
+ "eval_samples_per_second": 0.235,
632
+ "eval_steps_per_second": 0.04,
633
+ "step": 80
634
+ },
635
+ {
636
+ "epoch": 0.7105263157894737,
637
+ "grad_norm": 0.6668726205825806,
638
+ "learning_rate": 4.735678371226441e-05,
639
+ "loss": 1.0248,
640
+ "step": 81
641
+ },
642
+ {
643
+ "epoch": 0.7192982456140351,
644
+ "grad_norm": 0.9492083787918091,
645
+ "learning_rate": 4.476350270394942e-05,
646
+ "loss": 1.263,
647
+ "step": 82
648
+ },
649
+ {
650
+ "epoch": 0.7280701754385965,
651
+ "grad_norm": 0.7178658843040466,
652
+ "learning_rate": 4.222261685917489e-05,
653
+ "loss": 1.3507,
654
+ "step": 83
655
+ },
656
+ {
657
+ "epoch": 0.7368421052631579,
658
+ "grad_norm": 0.75201416015625,
659
+ "learning_rate": 3.973653636207437e-05,
660
+ "loss": 1.2211,
661
+ "step": 84
662
+ },
663
+ {
664
+ "epoch": 0.7456140350877193,
665
+ "grad_norm": 0.6311876773834229,
666
+ "learning_rate": 3.7307619410589376e-05,
667
+ "loss": 1.0633,
668
+ "step": 85
669
+ },
670
+ {
671
+ "epoch": 0.7543859649122807,
672
+ "grad_norm": 0.5766677856445312,
673
+ "learning_rate": 3.493816997957582e-05,
674
+ "loss": 0.9034,
675
+ "step": 86
676
+ },
677
+ {
678
+ "epoch": 0.7631578947368421,
679
+ "grad_norm": 0.6574028134346008,
680
+ "learning_rate": 3.263043563534428e-05,
681
+ "loss": 1.0327,
682
+ "step": 87
683
+ },
684
+ {
685
+ "epoch": 0.7719298245614035,
686
+ "grad_norm": 0.7002457976341248,
687
+ "learning_rate": 3.0386605403707346e-05,
688
+ "loss": 1.1285,
689
+ "step": 88
690
+ },
691
+ {
692
+ "epoch": 0.7807017543859649,
693
+ "grad_norm": 0.6196402311325073,
694
+ "learning_rate": 2.8208807693555818e-05,
695
+ "loss": 1.0958,
696
+ "step": 89
697
+ },
698
+ {
699
+ "epoch": 0.7894736842105263,
700
+ "grad_norm": 0.69408118724823,
701
+ "learning_rate": 2.6099108277934103e-05,
702
+ "loss": 1.3329,
703
+ "step": 90
704
+ },
705
+ {
706
+ "epoch": 0.7894736842105263,
707
+ "eval_loss": 1.140186071395874,
708
+ "eval_runtime": 147.8753,
709
+ "eval_samples_per_second": 0.237,
710
+ "eval_steps_per_second": 0.041,
711
+ "step": 90
712
+ },
713
+ {
714
+ "epoch": 0.7982456140350878,
715
+ "grad_norm": 0.5900521874427795,
716
+ "learning_rate": 2.405950833452928e-05,
717
+ "loss": 1.0236,
718
+ "step": 91
719
+ },
720
+ {
721
+ "epoch": 0.8070175438596491,
722
+ "grad_norm": 0.629959225654602,
723
+ "learning_rate": 2.2091942547432955e-05,
724
+ "loss": 1.0549,
725
+ "step": 92
726
+ },
727
+ {
728
+ "epoch": 0.8157894736842105,
729
+ "grad_norm": 0.6783764362335205,
730
+ "learning_rate": 2.0198277271976052e-05,
731
+ "loss": 1.018,
732
+ "step": 93
733
+ },
734
+ {
735
+ "epoch": 0.8245614035087719,
736
+ "grad_norm": 0.6238540410995483,
737
+ "learning_rate": 1.8380308764377842e-05,
738
+ "loss": 1.1294,
739
+ "step": 94
740
+ },
741
+ {
742
+ "epoch": 0.8333333333333334,
743
+ "grad_norm": 0.6851047277450562,
744
+ "learning_rate": 1.663976147788806e-05,
745
+ "loss": 1.1071,
746
+ "step": 95
747
+ },
748
+ {
749
+ "epoch": 0.8421052631578947,
750
+ "grad_norm": 0.6557275652885437,
751
+ "learning_rate": 1.4978286427038601e-05,
752
+ "loss": 1.1069,
753
+ "step": 96
754
+ },
755
+ {
756
+ "epoch": 0.8508771929824561,
757
+ "grad_norm": 0.6950388550758362,
758
+ "learning_rate": 1.339745962155613e-05,
759
+ "loss": 1.362,
760
+ "step": 97
761
+ },
762
+ {
763
+ "epoch": 0.8596491228070176,
764
+ "grad_norm": 0.685569703578949,
765
+ "learning_rate": 1.1898780571421552e-05,
766
+ "loss": 1.2406,
767
+ "step": 98
768
+ },
769
+ {
770
+ "epoch": 0.868421052631579,
771
+ "grad_norm": 0.9577943086624146,
772
+ "learning_rate": 1.0483670864493778e-05,
773
+ "loss": 1.2133,
774
+ "step": 99
775
+ },
776
+ {
777
+ "epoch": 0.8771929824561403,
778
+ "grad_norm": 0.8101325631141663,
779
+ "learning_rate": 9.153472818047625e-06,
780
+ "loss": 1.2042,
781
+ "step": 100
782
+ },
783
+ {
784
+ "epoch": 0.8771929824561403,
785
+ "eval_loss": 1.1394405364990234,
786
+ "eval_runtime": 148.8314,
787
+ "eval_samples_per_second": 0.235,
788
+ "eval_steps_per_second": 0.04,
789
+ "step": 100
790
+ },
791
+ {
792
+ "epoch": 0.8859649122807017,
793
+ "grad_norm": 0.594924807548523,
794
+ "learning_rate": 7.909448205504632e-06,
795
+ "loss": 1.2039,
796
+ "step": 101
797
+ },
798
+ {
799
+ "epoch": 0.8947368421052632,
800
+ "grad_norm": 0.5793190002441406,
801
+ "learning_rate": 6.75277705956443e-06,
802
+ "loss": 0.9641,
803
+ "step": 102
804
+ },
805
+ {
806
+ "epoch": 0.9035087719298246,
807
+ "grad_norm": 0.7169210314750671,
808
+ "learning_rate": 5.684556552872256e-06,
809
+ "loss": 1.1543,
810
+ "step": 103
811
+ },
812
+ {
813
+ "epoch": 0.9122807017543859,
814
+ "grad_norm": 0.6444424986839294,
815
+ "learning_rate": 4.705799957284351e-06,
816
+ "loss": 1.3011,
817
+ "step": 104
818
+ },
819
+ {
820
+ "epoch": 0.9210526315789473,
821
+ "grad_norm": 0.6580212116241455,
822
+ "learning_rate": 3.817435682718096e-06,
823
+ "loss": 1.296,
824
+ "step": 105
825
+ },
826
+ {
827
+ "epoch": 0.9298245614035088,
828
+ "grad_norm": 0.6932122707366943,
829
+ "learning_rate": 3.0203063964990617e-06,
830
+ "loss": 1.189,
831
+ "step": 106
832
+ },
833
+ {
834
+ "epoch": 0.9385964912280702,
835
+ "grad_norm": 0.6152276396751404,
836
+ "learning_rate": 2.315168224039932e-06,
837
+ "loss": 1.2102,
838
+ "step": 107
839
+ },
840
+ {
841
+ "epoch": 0.9473684210526315,
842
+ "grad_norm": 0.6482554078102112,
843
+ "learning_rate": 1.7026900316098215e-06,
844
+ "loss": 1.2161,
845
+ "step": 108
846
+ },
847
+ {
848
+ "epoch": 0.956140350877193,
849
+ "grad_norm": 0.5617808699607849,
850
+ "learning_rate": 1.1834527918740623e-06,
851
+ "loss": 0.9505,
852
+ "step": 109
853
+ },
854
+ {
855
+ "epoch": 0.9649122807017544,
856
+ "grad_norm": 0.730237603187561,
857
+ "learning_rate": 7.579490328064265e-07,
858
+ "loss": 1.0548,
859
+ "step": 110
860
+ },
861
+ {
862
+ "epoch": 0.9649122807017544,
863
+ "eval_loss": 1.1392273902893066,
864
+ "eval_runtime": 148.088,
865
+ "eval_samples_per_second": 0.236,
866
+ "eval_steps_per_second": 0.041,
867
+ "step": 110
868
+ }
869
+ ],
870
+ "logging_steps": 1,
871
+ "max_steps": 114,
872
+ "num_input_tokens_seen": 0,
873
+ "num_train_epochs": 1,
874
+ "save_steps": 10,
875
+ "stateful_callbacks": {
876
+ "TrainerControl": {
877
+ "args": {
878
+ "should_epoch_stop": false,
879
+ "should_evaluate": false,
880
+ "should_log": false,
881
+ "should_save": true,
882
+ "should_training_stop": false
883
+ },
884
+ "attributes": {}
885
+ }
886
+ },
887
+ "total_flos": 2.893180752101376e+16,
888
+ "train_batch_size": 6,
889
+ "trial_name": null,
890
+ "trial_params": null
891
+ }
checkpoint-110/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5544cf0b69d25bfc7badefdf1d7d0f070dbf45678b2edf3c080e026b44041bd
3
+ size 5368
checkpoint-20/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-20/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "q_proj",
26
+ "down_proj",
27
+ "up_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-20/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30beeb4dcebaeeb246085b8168b91fd12e4ead328fdd8ab33b682621fdba4d7f
3
+ size 83945296
checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406c1db66bd1b318b2b50cebfa46924b1e72a979f0594e8a7638a4bfb628f098
3
+ size 42540500
checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623598f35f112eb1763e682e076fe88dfe3af30309d84c1a4e925614fc013ecd
3
+ size 14244
checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea93d11a9371f7bcfe90c2fd95b89211b4a87c6d94711f18a4272f1d3b2d84ac
3
+ size 1064
checkpoint-20/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-20/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
checkpoint-20/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20/trainer_state.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.17543859649122806,
5
+ "eval_steps": 10,
6
+ "global_step": 20,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008771929824561403,
13
+ "grad_norm": 2.5680806636810303,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 1.6563,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017543859649122806,
20
+ "grad_norm": 2.0647432804107666,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 1.5849,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02631578947368421,
27
+ "grad_norm": 2.114915132522583,
28
+ "learning_rate": 5e-05,
29
+ "loss": 1.5868,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03508771929824561,
34
+ "grad_norm": 1.7573949098587036,
35
+ "learning_rate": 6.666666666666667e-05,
36
+ "loss": 1.6836,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.043859649122807015,
41
+ "grad_norm": 1.5793524980545044,
42
+ "learning_rate": 8.333333333333334e-05,
43
+ "loss": 1.4172,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05263157894736842,
48
+ "grad_norm": 1.7891627550125122,
49
+ "learning_rate": 0.0001,
50
+ "loss": 1.4405,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06140350877192982,
55
+ "grad_norm": 1.7529516220092773,
56
+ "learning_rate": 0.00011666666666666668,
57
+ "loss": 1.5647,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07017543859649122,
62
+ "grad_norm": 1.3582255840301514,
63
+ "learning_rate": 0.00013333333333333334,
64
+ "loss": 1.4112,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07894736842105263,
69
+ "grad_norm": 1.7452667951583862,
70
+ "learning_rate": 0.00015000000000000001,
71
+ "loss": 1.6427,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08771929824561403,
76
+ "grad_norm": 1.2840348482131958,
77
+ "learning_rate": 0.0001666666666666667,
78
+ "loss": 1.3915,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.08771929824561403,
83
+ "eval_loss": 1.3244520425796509,
84
+ "eval_runtime": 147.2051,
85
+ "eval_samples_per_second": 0.238,
86
+ "eval_steps_per_second": 0.041,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.09649122807017543,
91
+ "grad_norm": 2.1381897926330566,
92
+ "learning_rate": 0.00018333333333333334,
93
+ "loss": 1.3884,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.10526315789473684,
98
+ "grad_norm": 4.329859733581543,
99
+ "learning_rate": 0.0002,
100
+ "loss": 1.2958,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.11403508771929824,
105
+ "grad_norm": 2.177532196044922,
106
+ "learning_rate": 0.0001999525719713366,
107
+ "loss": 1.3211,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.12280701754385964,
112
+ "grad_norm": 2.4973137378692627,
113
+ "learning_rate": 0.00019981033287370443,
114
+ "loss": 1.2851,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.13157894736842105,
119
+ "grad_norm": 1.3471475839614868,
120
+ "learning_rate": 0.00019957341762950344,
121
+ "loss": 1.1561,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.14035087719298245,
126
+ "grad_norm": 1.4363510608673096,
127
+ "learning_rate": 0.0001992420509671936,
128
+ "loss": 1.364,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.14912280701754385,
133
+ "grad_norm": 1.6065610647201538,
134
+ "learning_rate": 0.00019881654720812594,
135
+ "loss": 1.1038,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.15789473684210525,
140
+ "grad_norm": 1.760709524154663,
141
+ "learning_rate": 0.0001982973099683902,
142
+ "loss": 1.3887,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.16666666666666666,
147
+ "grad_norm": 1.1617190837860107,
148
+ "learning_rate": 0.0001976848317759601,
149
+ "loss": 1.1831,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.17543859649122806,
154
+ "grad_norm": 0.8196442127227783,
155
+ "learning_rate": 0.00019697969360350098,
156
+ "loss": 1.01,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.17543859649122806,
161
+ "eval_loss": 1.1859098672866821,
162
+ "eval_runtime": 147.2373,
163
+ "eval_samples_per_second": 0.238,
164
+ "eval_steps_per_second": 0.041,
165
+ "step": 20
166
+ }
167
+ ],
168
+ "logging_steps": 1,
169
+ "max_steps": 114,
170
+ "num_input_tokens_seen": 0,
171
+ "num_train_epochs": 1,
172
+ "save_steps": 10,
173
+ "stateful_callbacks": {
174
+ "TrainerControl": {
175
+ "args": {
176
+ "should_epoch_stop": false,
177
+ "should_evaluate": false,
178
+ "should_log": false,
179
+ "should_save": true,
180
+ "should_training_stop": false
181
+ },
182
+ "attributes": {}
183
+ }
184
+ },
185
+ "total_flos": 5260328640184320.0,
186
+ "train_batch_size": 6,
187
+ "trial_name": null,
188
+ "trial_params": null
189
+ }
checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5544cf0b69d25bfc7badefdf1d7d0f070dbf45678b2edf3c080e026b44041bd
3
+ size 5368