chenhugging commited on
Commit
e471c8e
1 Parent(s): eb659e9

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - llama-factory
6
+ - lora
7
+ - generated_from_trainer
8
+ base_model: chargoddard/Yi-6B-Llama
9
+ model-index:
10
+ - name: model-update
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # model-update
18
+
19
+ This model is a fine-tuned version of [chargoddard/Yi-6B-Llama](https://huggingface.co/chargoddard/Yi-6B-Llama) on the oncc_medqa_instruct dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0005
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 2
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
+ - total_eval_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_steps: 20
50
+ - num_epochs: 1.0
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - PEFT 0.8.2
59
+ - Transformers 4.37.2
60
+ - Pytorch 2.0.1+cu118
61
+ - Datasets 2.17.0
62
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "chargoddard/Yi-6B-Llama",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cdb0eeb571aa0c2f87bef30e2083bf6727c1a2320c98e0500b994b85cea41c
3
+ size 13124104
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99,
3
+ "train_loss": 0.358406629228946,
4
+ "train_runtime": 800.1231,
5
+ "train_samples_per_second": 4.066,
6
+ "train_steps_per_second": 0.126
7
+ }
checkpoint-100/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: /workspace/model
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/workspace/model",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08e9fc82f17ba7a28387fa22b3294d93028f6f85dc688798d69ec6dc09632fe
3
+ size 13124104
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8ade3f1342b70ce34ddcc4e0f4718ca7b553db90188389ea0a6e26a901813c
3
+ size 26321605
checkpoint-100/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c72e8d36a05a982cd2947a5d181d5f8e613d46270acdbcfe65a195ea6bda46
3
+ size 15607
checkpoint-100/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8120aa2f3dc2e6ec59249421f56fe5e51ff955146f2456ddcec561f8e2337a
3
+ size 15607
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9283128548e036d52bd040a3831b7928036afbfdfc596b518dc0a1f860ededc7
3
+ size 627
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-100/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<|startoftext|>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "<|endoftext|>",
33
+ "legacy": false,
34
+ "model_max_length": 200000,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "split_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "truncation_side": "right",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9828009828009828,
5
+ "eval_steps": 500,
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": 0.1,
13
+ "learning_rate": 0.000125,
14
+ "loss": 1.6979,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.2,
19
+ "learning_rate": 0.000375,
20
+ "loss": 0.7265,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.29,
25
+ "learning_rate": 0.0004969974623692023,
26
+ "loss": 0.1676,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.39,
31
+ "learning_rate": 0.0004640417248825666,
32
+ "loss": 0.1557,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.49,
37
+ "learning_rate": 0.00039928964792569654,
38
+ "loss": 0.1458,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.59,
43
+ "learning_rate": 0.00031236028601449537,
44
+ "loss": 0.1429,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.69,
49
+ "learning_rate": 0.0002161671750624673,
50
+ "loss": 0.1502,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.79,
55
+ "learning_rate": 0.00012500000000000006,
56
+ "loss": 0.1432,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.88,
61
+ "learning_rate": 5.2401832620310204e-05,
62
+ "loss": 0.1426,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.98,
67
+ "learning_rate": 9.157280346029916e-06,
68
+ "loss": 0.1354,
69
+ "step": 100
70
+ }
71
+ ],
72
+ "logging_steps": 10,
73
+ "max_steps": 101,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 1,
76
+ "save_steps": 100,
77
+ "total_flos": 5.498116162505933e+16,
78
+ "train_batch_size": 4,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b364c2a141e55b094faf42c78d3d1ca139ada42a4780c3ad12f5e893f115e625
3
+ size 4411
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<|startoftext|>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "<|endoftext|>",
33
+ "legacy": false,
34
+ "model_max_length": 200000,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "split_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "truncation_side": "right",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99,
3
+ "train_loss": 0.358406629228946,
4
+ "train_runtime": 800.1231,
5
+ "train_samples_per_second": 4.066,
6
+ "train_steps_per_second": 0.126
7
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 101, "loss": 1.6979, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000125, "epoch": 0.1, "percentage": 9.9, "elapsed_time": "0:01:18", "remaining_time": "0:11:58"}
2
+ {"current_steps": 20, "total_steps": 101, "loss": 0.7265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000375, "epoch": 0.2, "percentage": 19.8, "elapsed_time": "0:02:35", "remaining_time": "0:10:31"}
3
+ {"current_steps": 30, "total_steps": 101, "loss": 0.1676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004969974623692023, "epoch": 0.29, "percentage": 29.7, "elapsed_time": "0:03:56", "remaining_time": "0:09:18"}
4
+ {"current_steps": 40, "total_steps": 101, "loss": 0.1557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004640417248825666, "epoch": 0.39, "percentage": 39.6, "elapsed_time": "0:05:15", "remaining_time": "0:08:01"}
5
+ {"current_steps": 50, "total_steps": 101, "loss": 0.1458, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00039928964792569654, "epoch": 0.49, "percentage": 49.5, "elapsed_time": "0:06:31", "remaining_time": "0:06:38"}
6
+ {"current_steps": 60, "total_steps": 101, "loss": 0.1429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00031236028601449537, "epoch": 0.59, "percentage": 59.41, "elapsed_time": "0:07:52", "remaining_time": "0:05:22"}
7
+ {"current_steps": 70, "total_steps": 101, "loss": 0.1502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002161671750624673, "epoch": 0.69, "percentage": 69.31, "elapsed_time": "0:09:12", "remaining_time": "0:04:04"}
8
+ {"current_steps": 80, "total_steps": 101, "loss": 0.1432, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012500000000000006, "epoch": 0.79, "percentage": 79.21, "elapsed_time": "0:10:34", "remaining_time": "0:02:46"}
9
+ {"current_steps": 90, "total_steps": 101, "loss": 0.1426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.2401832620310204e-05, "epoch": 0.88, "percentage": 89.11, "elapsed_time": "0:11:54", "remaining_time": "0:01:27"}
10
+ {"current_steps": 100, "total_steps": 101, "loss": 0.1354, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.157280346029916e-06, "epoch": 0.98, "percentage": 99.01, "elapsed_time": "0:13:10", "remaining_time": "0:00:07"}
11
+ {"current_steps": 101, "total_steps": 101, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.99, "percentage": 100.0, "elapsed_time": "0:13:19", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9926289926289926,
5
+ "eval_steps": 500,
6
+ "global_step": 101,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "learning_rate": 0.000125,
14
+ "loss": 1.6979,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.2,
19
+ "learning_rate": 0.000375,
20
+ "loss": 0.7265,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.29,
25
+ "learning_rate": 0.0004969974623692023,
26
+ "loss": 0.1676,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.39,
31
+ "learning_rate": 0.0004640417248825666,
32
+ "loss": 0.1557,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.49,
37
+ "learning_rate": 0.00039928964792569654,
38
+ "loss": 0.1458,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.59,
43
+ "learning_rate": 0.00031236028601449537,
44
+ "loss": 0.1429,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.69,
49
+ "learning_rate": 0.0002161671750624673,
50
+ "loss": 0.1502,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.79,
55
+ "learning_rate": 0.00012500000000000006,
56
+ "loss": 0.1432,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.88,
61
+ "learning_rate": 5.2401832620310204e-05,
62
+ "loss": 0.1426,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.98,
67
+ "learning_rate": 9.157280346029916e-06,
68
+ "loss": 0.1354,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.99,
73
+ "step": 101,
74
+ "total_flos": 5.556156411097907e+16,
75
+ "train_loss": 0.358406629228946,
76
+ "train_runtime": 800.1231,
77
+ "train_samples_per_second": 4.066,
78
+ "train_steps_per_second": 0.126
79
+ }
80
+ ],
81
+ "logging_steps": 10,
82
+ "max_steps": 101,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 1,
85
+ "save_steps": 100,
86
+ "total_flos": 5.556156411097907e+16,
87
+ "train_batch_size": 4,
88
+ "trial_name": null,
89
+ "trial_params": null
90
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b364c2a141e55b094faf42c78d3d1ca139ada42a4780c3ad12f5e893f115e625
3
+ size 4411