Hugging Face's logo

YufeiWeng
/
Qwen-LoRA-Adapter-DaDaoZhengFeng

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
YufeiWeng commited on
Commit
328f0f0
·
verified ·
1 Parent(s): 3cbeadf

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. README.md +202 -0
  2. adapter_config.json +28 -0
  3. adapter_model.safetensors +3 -0
  4. qwen.tiktoken +0 -0
  5. runs/Feb06_21-54-53_f13f084abb3d/events.out.tfevents.1738878902.f13f084abb3d.6719.0 +3 -0
  6. special_tokens_map.json +3 -0
  7. tokenizer_config.json +14 -0
  8. trainer_state.json +1838 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen-7B-Chat-Int4
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 0.7.1
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen-7B-Chat-Int4",
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": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "w1",
23
+ "w2",
24
+ "c_proj",
25
+ "c_attn"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca1d2beb6136c62fce3140181f5d1905edff64cf7ccaa84f67b38e7e8d1b3a23
3
+ size 286302920
qwen.tiktoken ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb06_21-54-53_f13f084abb3d/events.out.tfevents.1738878902.f13f084abb3d.6719.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f2132a111194277763a26195bfecb4f9930bd28b2b9f1705303130c3282f41
3
+ size 53081
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "pad_token": "<|endoftext|>"
3
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {},
3
+ "auto_map": {
4
+ "AutoTokenizer": [
5
+ "Qwen/Qwen-7B-Chat-Int4--tokenization_qwen.QWenTokenizer",
6
+ null
7
+ ]
8
+ },
9
+ "clean_up_tokenization_spaces": true,
10
+ "model_max_length": 3500,
11
+ "pad_token": "<|endoftext|>",
12
+ "padding_side": "right",
13
+ "tokenizer_class": "QWenTokenizer"
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,1838 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.959866220735786,
5
+ "eval_steps": 500,
6
+ "global_step": 296,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.0,
14
+ "loss": 3.3735,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 0.00018927892607143717,
20
+ "loss": 3.4333,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.04,
25
+ "learning_rate": 0.0003,
26
+ "loss": 3.4033,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.05,
31
+ "learning_rate": 0.0003,
32
+ "loss": 3.2866,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.07,
37
+ "learning_rate": 0.0003,
38
+ "loss": 3.1956,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.08,
43
+ "learning_rate": 0.0003,
44
+ "loss": 3.2327,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.09,
49
+ "learning_rate": 0.0003,
50
+ "loss": 3.2285,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.11,
55
+ "learning_rate": 0.0003,
56
+ "loss": 3.1553,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.12,
61
+ "learning_rate": 0.0003,
62
+ "loss": 3.1208,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.13,
67
+ "learning_rate": 0.0003,
68
+ "loss": 3.1433,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.15,
73
+ "learning_rate": 0.0003,
74
+ "loss": 3.2463,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.16,
79
+ "learning_rate": 0.0003,
80
+ "loss": 3.2375,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.17,
85
+ "learning_rate": 0.0003,
86
+ "loss": 3.1509,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.19,
91
+ "learning_rate": 0.0003,
92
+ "loss": 3.1587,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.2,
97
+ "learning_rate": 0.0003,
98
+ "loss": 3.1511,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.21,
103
+ "learning_rate": 0.0003,
104
+ "loss": 3.1155,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.23,
109
+ "learning_rate": 0.0003,
110
+ "loss": 3.2439,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.24,
115
+ "learning_rate": 0.0003,
116
+ "loss": 3.124,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.25,
121
+ "learning_rate": 0.0003,
122
+ "loss": 3.1448,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.27,
127
+ "learning_rate": 0.0003,
128
+ "loss": 3.1562,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.28,
133
+ "learning_rate": 0.0003,
134
+ "loss": 3.1211,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.29,
139
+ "learning_rate": 0.0003,
140
+ "loss": 3.1689,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.31,
145
+ "learning_rate": 0.0003,
146
+ "loss": 3.032,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.32,
151
+ "learning_rate": 0.0003,
152
+ "loss": 3.0703,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.33,
157
+ "learning_rate": 0.0003,
158
+ "loss": 3.0483,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.35,
163
+ "learning_rate": 0.0003,
164
+ "loss": 3.0603,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.36,
169
+ "learning_rate": 0.0003,
170
+ "loss": 3.0596,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.37,
175
+ "learning_rate": 0.0003,
176
+ "loss": 3.0471,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.39,
181
+ "learning_rate": 0.0003,
182
+ "loss": 3.0806,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.4,
187
+ "learning_rate": 0.0003,
188
+ "loss": 3.1157,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.41,
193
+ "learning_rate": 0.0003,
194
+ "loss": 2.957,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.43,
199
+ "learning_rate": 0.0003,
200
+ "loss": 3.0391,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.44,
205
+ "learning_rate": 0.0003,
206
+ "loss": 3.0684,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.45,
211
+ "learning_rate": 0.0003,
212
+ "loss": 3.0413,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.47,
217
+ "learning_rate": 0.0003,
218
+ "loss": 2.9812,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.48,
223
+ "learning_rate": 0.0003,
224
+ "loss": 2.9978,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.49,
229
+ "learning_rate": 0.0003,
230
+ "loss": 2.9976,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.51,
235
+ "learning_rate": 0.0003,
236
+ "loss": 2.9836,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.52,
241
+ "learning_rate": 0.0003,
242
+ "loss": 3.002,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.54,
247
+ "learning_rate": 0.0003,
248
+ "loss": 3.0127,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.55,
253
+ "learning_rate": 0.0003,
254
+ "loss": 2.9312,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.56,
259
+ "learning_rate": 0.0003,
260
+ "loss": 2.9155,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.58,
265
+ "learning_rate": 0.0003,
266
+ "loss": 3.0063,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.59,
271
+ "learning_rate": 0.0003,
272
+ "loss": 2.9919,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.6,
277
+ "learning_rate": 0.0003,
278
+ "loss": 2.9868,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.62,
283
+ "learning_rate": 0.0003,
284
+ "loss": 3.0422,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.63,
289
+ "learning_rate": 0.0003,
290
+ "loss": 2.9829,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.64,
295
+ "learning_rate": 0.0003,
296
+ "loss": 2.9717,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.66,
301
+ "learning_rate": 0.0003,
302
+ "loss": 3.0137,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.67,
307
+ "learning_rate": 0.0003,
308
+ "loss": 2.9841,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.68,
313
+ "learning_rate": 0.0003,
314
+ "loss": 2.9727,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.7,
319
+ "learning_rate": 0.0003,
320
+ "loss": 2.9177,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.71,
325
+ "learning_rate": 0.0003,
326
+ "loss": 2.928,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.72,
331
+ "learning_rate": 0.0003,
332
+ "loss": 2.9106,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.74,
337
+ "learning_rate": 0.0003,
338
+ "loss": 2.9189,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.75,
343
+ "learning_rate": 0.0003,
344
+ "loss": 2.9849,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.76,
349
+ "learning_rate": 0.0003,
350
+ "loss": 2.9912,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.78,
355
+ "learning_rate": 0.0003,
356
+ "loss": 2.9336,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.79,
361
+ "learning_rate": 0.0003,
362
+ "loss": 3.0144,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.8,
367
+ "learning_rate": 0.0003,
368
+ "loss": 2.938,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.82,
373
+ "learning_rate": 0.0003,
374
+ "loss": 2.9417,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.83,
379
+ "learning_rate": 0.0003,
380
+ "loss": 3.0129,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.84,
385
+ "learning_rate": 0.0003,
386
+ "loss": 2.9568,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.86,
391
+ "learning_rate": 0.0003,
392
+ "loss": 2.9773,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.87,
397
+ "learning_rate": 0.0003,
398
+ "loss": 2.8545,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.88,
403
+ "learning_rate": 0.0003,
404
+ "loss": 2.9648,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.9,
409
+ "learning_rate": 0.0003,
410
+ "loss": 2.9768,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.91,
415
+ "learning_rate": 0.0003,
416
+ "loss": 2.9709,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.92,
421
+ "learning_rate": 0.0003,
422
+ "loss": 2.8271,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.94,
427
+ "learning_rate": 0.0003,
428
+ "loss": 2.8428,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.95,
433
+ "learning_rate": 0.0003,
434
+ "loss": 2.8523,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.96,
439
+ "learning_rate": 0.0003,
440
+ "loss": 2.9082,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.98,
445
+ "learning_rate": 0.0003,
446
+ "loss": 2.9089,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.99,
451
+ "learning_rate": 0.0003,
452
+ "loss": 2.845,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.99,
457
+ "eval_loss": 2.943359375,
458
+ "eval_runtime": 93.5805,
459
+ "eval_samples_per_second": 2.511,
460
+ "eval_steps_per_second": 1.261,
461
+ "step": 74
462
+ },
463
+ {
464
+ "epoch": 1.0,
465
+ "learning_rate": 0.0003,
466
+ "loss": 2.8491,
467
+ "step": 75
468
+ },
469
+ {
470
+ "epoch": 1.02,
471
+ "learning_rate": 0.0003,
472
+ "loss": 2.7544,
473
+ "step": 76
474
+ },
475
+ {
476
+ "epoch": 1.03,
477
+ "learning_rate": 0.0003,
478
+ "loss": 2.7939,
479
+ "step": 77
480
+ },
481
+ {
482
+ "epoch": 1.04,
483
+ "learning_rate": 0.0003,
484
+ "loss": 2.834,
485
+ "step": 78
486
+ },
487
+ {
488
+ "epoch": 1.06,
489
+ "learning_rate": 0.0003,
490
+ "loss": 2.8313,
491
+ "step": 79
492
+ },
493
+ {
494
+ "epoch": 1.07,
495
+ "learning_rate": 0.0003,
496
+ "loss": 2.8206,
497
+ "step": 80
498
+ },
499
+ {
500
+ "epoch": 1.08,
501
+ "learning_rate": 0.0003,
502
+ "loss": 2.8225,
503
+ "step": 81
504
+ },
505
+ {
506
+ "epoch": 1.1,
507
+ "learning_rate": 0.0003,
508
+ "loss": 2.8218,
509
+ "step": 82
510
+ },
511
+ {
512
+ "epoch": 1.11,
513
+ "learning_rate": 0.0003,
514
+ "loss": 2.7241,
515
+ "step": 83
516
+ },
517
+ {
518
+ "epoch": 1.12,
519
+ "learning_rate": 0.0003,
520
+ "loss": 2.7415,
521
+ "step": 84
522
+ },
523
+ {
524
+ "epoch": 1.14,
525
+ "learning_rate": 0.0003,
526
+ "loss": 2.8203,
527
+ "step": 85
528
+ },
529
+ {
530
+ "epoch": 1.15,
531
+ "learning_rate": 0.0003,
532
+ "loss": 2.7729,
533
+ "step": 86
534
+ },
535
+ {
536
+ "epoch": 1.16,
537
+ "learning_rate": 0.0003,
538
+ "loss": 2.7581,
539
+ "step": 87
540
+ },
541
+ {
542
+ "epoch": 1.18,
543
+ "learning_rate": 0.0003,
544
+ "loss": 2.75,
545
+ "step": 88
546
+ },
547
+ {
548
+ "epoch": 1.19,
549
+ "learning_rate": 0.0003,
550
+ "loss": 2.7783,
551
+ "step": 89
552
+ },
553
+ {
554
+ "epoch": 1.2,
555
+ "learning_rate": 0.0003,
556
+ "loss": 2.7671,
557
+ "step": 90
558
+ },
559
+ {
560
+ "epoch": 1.22,
561
+ "learning_rate": 0.0003,
562
+ "loss": 2.7773,
563
+ "step": 91
564
+ },
565
+ {
566
+ "epoch": 1.23,
567
+ "learning_rate": 0.0003,
568
+ "loss": 2.7808,
569
+ "step": 92
570
+ },
571
+ {
572
+ "epoch": 1.24,
573
+ "learning_rate": 0.0003,
574
+ "loss": 2.6885,
575
+ "step": 93
576
+ },
577
+ {
578
+ "epoch": 1.26,
579
+ "learning_rate": 0.0003,
580
+ "loss": 2.7766,
581
+ "step": 94
582
+ },
583
+ {
584
+ "epoch": 1.27,
585
+ "learning_rate": 0.0003,
586
+ "loss": 2.8889,
587
+ "step": 95
588
+ },
589
+ {
590
+ "epoch": 1.28,
591
+ "learning_rate": 0.0003,
592
+ "loss": 2.7654,
593
+ "step": 96
594
+ },
595
+ {
596
+ "epoch": 1.3,
597
+ "learning_rate": 0.0003,
598
+ "loss": 2.7915,
599
+ "step": 97
600
+ },
601
+ {
602
+ "epoch": 1.31,
603
+ "learning_rate": 0.0003,
604
+ "loss": 2.7454,
605
+ "step": 98
606
+ },
607
+ {
608
+ "epoch": 1.32,
609
+ "learning_rate": 0.0003,
610
+ "loss": 2.7744,
611
+ "step": 99
612
+ },
613
+ {
614
+ "epoch": 1.34,
615
+ "learning_rate": 0.0003,
616
+ "loss": 2.7595,
617
+ "step": 100
618
+ },
619
+ {
620
+ "epoch": 1.35,
621
+ "learning_rate": 0.0003,
622
+ "loss": 2.7566,
623
+ "step": 101
624
+ },
625
+ {
626
+ "epoch": 1.36,
627
+ "learning_rate": 0.0003,
628
+ "loss": 2.6567,
629
+ "step": 102
630
+ },
631
+ {
632
+ "epoch": 1.38,
633
+ "learning_rate": 0.0003,
634
+ "loss": 2.7207,
635
+ "step": 103
636
+ },
637
+ {
638
+ "epoch": 1.39,
639
+ "learning_rate": 0.0003,
640
+ "loss": 2.7051,
641
+ "step": 104
642
+ },
643
+ {
644
+ "epoch": 1.4,
645
+ "learning_rate": 0.0003,
646
+ "loss": 2.6968,
647
+ "step": 105
648
+ },
649
+ {
650
+ "epoch": 1.42,
651
+ "learning_rate": 0.0003,
652
+ "loss": 2.7419,
653
+ "step": 106
654
+ },
655
+ {
656
+ "epoch": 1.43,
657
+ "learning_rate": 0.0003,
658
+ "loss": 2.7764,
659
+ "step": 107
660
+ },
661
+ {
662
+ "epoch": 1.44,
663
+ "learning_rate": 0.0003,
664
+ "loss": 2.6992,
665
+ "step": 108
666
+ },
667
+ {
668
+ "epoch": 1.46,
669
+ "learning_rate": 0.0003,
670
+ "loss": 2.7251,
671
+ "step": 109
672
+ },
673
+ {
674
+ "epoch": 1.47,
675
+ "learning_rate": 0.0003,
676
+ "loss": 2.7183,
677
+ "step": 110
678
+ },
679
+ {
680
+ "epoch": 1.48,
681
+ "learning_rate": 0.0003,
682
+ "loss": 2.7048,
683
+ "step": 111
684
+ },
685
+ {
686
+ "epoch": 1.5,
687
+ "learning_rate": 0.0003,
688
+ "loss": 2.6912,
689
+ "step": 112
690
+ },
691
+ {
692
+ "epoch": 1.51,
693
+ "learning_rate": 0.0003,
694
+ "loss": 2.7107,
695
+ "step": 113
696
+ },
697
+ {
698
+ "epoch": 1.53,
699
+ "learning_rate": 0.0003,
700
+ "loss": 2.7776,
701
+ "step": 114
702
+ },
703
+ {
704
+ "epoch": 1.54,
705
+ "learning_rate": 0.0003,
706
+ "loss": 2.7649,
707
+ "step": 115
708
+ },
709
+ {
710
+ "epoch": 1.55,
711
+ "learning_rate": 0.0003,
712
+ "loss": 2.7378,
713
+ "step": 116
714
+ },
715
+ {
716
+ "epoch": 1.57,
717
+ "learning_rate": 0.0003,
718
+ "loss": 2.7139,
719
+ "step": 117
720
+ },
721
+ {
722
+ "epoch": 1.58,
723
+ "learning_rate": 0.0003,
724
+ "loss": 2.7139,
725
+ "step": 118
726
+ },
727
+ {
728
+ "epoch": 1.59,
729
+ "learning_rate": 0.0003,
730
+ "loss": 2.7632,
731
+ "step": 119
732
+ },
733
+ {
734
+ "epoch": 1.61,
735
+ "learning_rate": 0.0003,
736
+ "loss": 2.7268,
737
+ "step": 120
738
+ },
739
+ {
740
+ "epoch": 1.62,
741
+ "learning_rate": 0.0003,
742
+ "loss": 2.7534,
743
+ "step": 121
744
+ },
745
+ {
746
+ "epoch": 1.63,
747
+ "learning_rate": 0.0003,
748
+ "loss": 2.7964,
749
+ "step": 122
750
+ },
751
+ {
752
+ "epoch": 1.65,
753
+ "learning_rate": 0.0003,
754
+ "loss": 2.729,
755
+ "step": 123
756
+ },
757
+ {
758
+ "epoch": 1.66,
759
+ "learning_rate": 0.0003,
760
+ "loss": 2.748,
761
+ "step": 124
762
+ },
763
+ {
764
+ "epoch": 1.67,
765
+ "learning_rate": 0.0003,
766
+ "loss": 2.7483,
767
+ "step": 125
768
+ },
769
+ {
770
+ "epoch": 1.69,
771
+ "learning_rate": 0.0003,
772
+ "loss": 2.7832,
773
+ "step": 126
774
+ },
775
+ {
776
+ "epoch": 1.7,
777
+ "learning_rate": 0.0003,
778
+ "loss": 2.6958,
779
+ "step": 127
780
+ },
781
+ {
782
+ "epoch": 1.71,
783
+ "learning_rate": 0.0003,
784
+ "loss": 2.7148,
785
+ "step": 128
786
+ },
787
+ {
788
+ "epoch": 1.73,
789
+ "learning_rate": 0.0003,
790
+ "loss": 2.6577,
791
+ "step": 129
792
+ },
793
+ {
794
+ "epoch": 1.74,
795
+ "learning_rate": 0.0003,
796
+ "loss": 2.7297,
797
+ "step": 130
798
+ },
799
+ {
800
+ "epoch": 1.75,
801
+ "learning_rate": 0.0003,
802
+ "loss": 2.7915,
803
+ "step": 131
804
+ },
805
+ {
806
+ "epoch": 1.77,
807
+ "learning_rate": 0.0003,
808
+ "loss": 2.7109,
809
+ "step": 132
810
+ },
811
+ {
812
+ "epoch": 1.78,
813
+ "learning_rate": 0.0003,
814
+ "loss": 2.7217,
815
+ "step": 133
816
+ },
817
+ {
818
+ "epoch": 1.79,
819
+ "learning_rate": 0.0003,
820
+ "loss": 2.7512,
821
+ "step": 134
822
+ },
823
+ {
824
+ "epoch": 1.81,
825
+ "learning_rate": 0.0003,
826
+ "loss": 2.8252,
827
+ "step": 135
828
+ },
829
+ {
830
+ "epoch": 1.82,
831
+ "learning_rate": 0.0003,
832
+ "loss": 2.7615,
833
+ "step": 136
834
+ },
835
+ {
836
+ "epoch": 1.83,
837
+ "learning_rate": 0.0003,
838
+ "loss": 2.7061,
839
+ "step": 137
840
+ },
841
+ {
842
+ "epoch": 1.85,
843
+ "learning_rate": 0.0003,
844
+ "loss": 2.7461,
845
+ "step": 138
846
+ },
847
+ {
848
+ "epoch": 1.86,
849
+ "learning_rate": 0.0003,
850
+ "loss": 2.6477,
851
+ "step": 139
852
+ },
853
+ {
854
+ "epoch": 1.87,
855
+ "learning_rate": 0.0003,
856
+ "loss": 2.7061,
857
+ "step": 140
858
+ },
859
+ {
860
+ "epoch": 1.89,
861
+ "learning_rate": 0.0003,
862
+ "loss": 2.7549,
863
+ "step": 141
864
+ },
865
+ {
866
+ "epoch": 1.9,
867
+ "learning_rate": 0.0003,
868
+ "loss": 2.7356,
869
+ "step": 142
870
+ },
871
+ {
872
+ "epoch": 1.91,
873
+ "learning_rate": 0.0003,
874
+ "loss": 2.6492,
875
+ "step": 143
876
+ },
877
+ {
878
+ "epoch": 1.93,
879
+ "learning_rate": 0.0003,
880
+ "loss": 2.6611,
881
+ "step": 144
882
+ },
883
+ {
884
+ "epoch": 1.94,
885
+ "learning_rate": 0.0003,
886
+ "loss": 2.7107,
887
+ "step": 145
888
+ },
889
+ {
890
+ "epoch": 1.95,
891
+ "learning_rate": 0.0003,
892
+ "loss": 2.7417,
893
+ "step": 146
894
+ },
895
+ {
896
+ "epoch": 1.97,
897
+ "learning_rate": 0.0003,
898
+ "loss": 2.6902,
899
+ "step": 147
900
+ },
901
+ {
902
+ "epoch": 1.98,
903
+ "learning_rate": 0.0003,
904
+ "loss": 2.6724,
905
+ "step": 148
906
+ },
907
+ {
908
+ "epoch": 1.99,
909
+ "learning_rate": 0.0003,
910
+ "loss": 2.7014,
911
+ "step": 149
912
+ },
913
+ {
914
+ "epoch": 1.99,
915
+ "eval_loss": 2.880859375,
916
+ "eval_runtime": 92.4687,
917
+ "eval_samples_per_second": 2.541,
918
+ "eval_steps_per_second": 1.276,
919
+ "step": 149
920
+ },
921
+ {
922
+ "epoch": 2.01,
923
+ "learning_rate": 0.0003,
924
+ "loss": 2.584,
925
+ "step": 150
926
+ },
927
+ {
928
+ "epoch": 2.02,
929
+ "learning_rate": 0.0003,
930
+ "loss": 2.552,
931
+ "step": 151
932
+ },
933
+ {
934
+ "epoch": 2.03,
935
+ "learning_rate": 0.0003,
936
+ "loss": 2.5398,
937
+ "step": 152
938
+ },
939
+ {
940
+ "epoch": 2.05,
941
+ "learning_rate": 0.0003,
942
+ "loss": 2.5303,
943
+ "step": 153
944
+ },
945
+ {
946
+ "epoch": 2.06,
947
+ "learning_rate": 0.0003,
948
+ "loss": 2.6184,
949
+ "step": 154
950
+ },
951
+ {
952
+ "epoch": 2.07,
953
+ "learning_rate": 0.0003,
954
+ "loss": 2.5503,
955
+ "step": 155
956
+ },
957
+ {
958
+ "epoch": 2.09,
959
+ "learning_rate": 0.0003,
960
+ "loss": 2.5076,
961
+ "step": 156
962
+ },
963
+ {
964
+ "epoch": 2.1,
965
+ "learning_rate": 0.0003,
966
+ "loss": 2.541,
967
+ "step": 157
968
+ },
969
+ {
970
+ "epoch": 2.11,
971
+ "learning_rate": 0.0003,
972
+ "loss": 2.5581,
973
+ "step": 158
974
+ },
975
+ {
976
+ "epoch": 2.13,
977
+ "learning_rate": 0.0003,
978
+ "loss": 2.5159,
979
+ "step": 159
980
+ },
981
+ {
982
+ "epoch": 2.14,
983
+ "learning_rate": 0.0003,
984
+ "loss": 2.5339,
985
+ "step": 160
986
+ },
987
+ {
988
+ "epoch": 2.15,
989
+ "learning_rate": 0.0003,
990
+ "loss": 2.5261,
991
+ "step": 161
992
+ },
993
+ {
994
+ "epoch": 2.17,
995
+ "learning_rate": 0.0003,
996
+ "loss": 2.4651,
997
+ "step": 162
998
+ },
999
+ {
1000
+ "epoch": 2.18,
1001
+ "learning_rate": 0.0003,
1002
+ "loss": 2.5435,
1003
+ "step": 163
1004
+ },
1005
+ {
1006
+ "epoch": 2.19,
1007
+ "learning_rate": 0.0003,
1008
+ "loss": 2.5171,
1009
+ "step": 164
1010
+ },
1011
+ {
1012
+ "epoch": 2.21,
1013
+ "learning_rate": 0.0003,
1014
+ "loss": 2.4304,
1015
+ "step": 165
1016
+ },
1017
+ {
1018
+ "epoch": 2.22,
1019
+ "learning_rate": 0.0003,
1020
+ "loss": 2.5093,
1021
+ "step": 166
1022
+ },
1023
+ {
1024
+ "epoch": 2.23,
1025
+ "learning_rate": 0.0003,
1026
+ "loss": 2.4856,
1027
+ "step": 167
1028
+ },
1029
+ {
1030
+ "epoch": 2.25,
1031
+ "learning_rate": 0.0003,
1032
+ "loss": 2.4858,
1033
+ "step": 168
1034
+ },
1035
+ {
1036
+ "epoch": 2.26,
1037
+ "learning_rate": 0.0003,
1038
+ "loss": 2.5056,
1039
+ "step": 169
1040
+ },
1041
+ {
1042
+ "epoch": 2.27,
1043
+ "learning_rate": 0.0003,
1044
+ "loss": 2.5198,
1045
+ "step": 170
1046
+ },
1047
+ {
1048
+ "epoch": 2.29,
1049
+ "learning_rate": 0.0003,
1050
+ "loss": 2.4861,
1051
+ "step": 171
1052
+ },
1053
+ {
1054
+ "epoch": 2.3,
1055
+ "learning_rate": 0.0003,
1056
+ "loss": 2.4849,
1057
+ "step": 172
1058
+ },
1059
+ {
1060
+ "epoch": 2.31,
1061
+ "learning_rate": 0.0003,
1062
+ "loss": 2.5073,
1063
+ "step": 173
1064
+ },
1065
+ {
1066
+ "epoch": 2.33,
1067
+ "learning_rate": 0.0003,
1068
+ "loss": 2.49,
1069
+ "step": 174
1070
+ },
1071
+ {
1072
+ "epoch": 2.34,
1073
+ "learning_rate": 0.0003,
1074
+ "loss": 2.5383,
1075
+ "step": 175
1076
+ },
1077
+ {
1078
+ "epoch": 2.35,
1079
+ "learning_rate": 0.0003,
1080
+ "loss": 2.48,
1081
+ "step": 176
1082
+ },
1083
+ {
1084
+ "epoch": 2.37,
1085
+ "learning_rate": 0.0003,
1086
+ "loss": 2.4902,
1087
+ "step": 177
1088
+ },
1089
+ {
1090
+ "epoch": 2.38,
1091
+ "learning_rate": 0.0003,
1092
+ "loss": 2.5698,
1093
+ "step": 178
1094
+ },
1095
+ {
1096
+ "epoch": 2.39,
1097
+ "learning_rate": 0.0003,
1098
+ "loss": 2.4888,
1099
+ "step": 179
1100
+ },
1101
+ {
1102
+ "epoch": 2.41,
1103
+ "learning_rate": 0.0003,
1104
+ "loss": 2.5122,
1105
+ "step": 180
1106
+ },
1107
+ {
1108
+ "epoch": 2.42,
1109
+ "learning_rate": 0.0003,
1110
+ "loss": 2.5344,
1111
+ "step": 181
1112
+ },
1113
+ {
1114
+ "epoch": 2.43,
1115
+ "learning_rate": 0.0003,
1116
+ "loss": 2.5466,
1117
+ "step": 182
1118
+ },
1119
+ {
1120
+ "epoch": 2.45,
1121
+ "learning_rate": 0.0003,
1122
+ "loss": 2.5459,
1123
+ "step": 183
1124
+ },
1125
+ {
1126
+ "epoch": 2.46,
1127
+ "learning_rate": 0.0003,
1128
+ "loss": 2.5022,
1129
+ "step": 184
1130
+ },
1131
+ {
1132
+ "epoch": 2.47,
1133
+ "learning_rate": 0.0003,
1134
+ "loss": 2.5464,
1135
+ "step": 185
1136
+ },
1137
+ {
1138
+ "epoch": 2.49,
1139
+ "learning_rate": 0.0003,
1140
+ "loss": 2.5015,
1141
+ "step": 186
1142
+ },
1143
+ {
1144
+ "epoch": 2.5,
1145
+ "learning_rate": 0.0003,
1146
+ "loss": 2.5337,
1147
+ "step": 187
1148
+ },
1149
+ {
1150
+ "epoch": 2.52,
1151
+ "learning_rate": 0.0003,
1152
+ "loss": 2.5454,
1153
+ "step": 188
1154
+ },
1155
+ {
1156
+ "epoch": 2.53,
1157
+ "learning_rate": 0.0003,
1158
+ "loss": 2.6106,
1159
+ "step": 189
1160
+ },
1161
+ {
1162
+ "epoch": 2.54,
1163
+ "learning_rate": 0.0003,
1164
+ "loss": 2.5547,
1165
+ "step": 190
1166
+ },
1167
+ {
1168
+ "epoch": 2.56,
1169
+ "learning_rate": 0.0003,
1170
+ "loss": 2.4438,
1171
+ "step": 191
1172
+ },
1173
+ {
1174
+ "epoch": 2.57,
1175
+ "learning_rate": 0.0003,
1176
+ "loss": 2.5503,
1177
+ "step": 192
1178
+ },
1179
+ {
1180
+ "epoch": 2.58,
1181
+ "learning_rate": 0.0003,
1182
+ "loss": 2.512,
1183
+ "step": 193
1184
+ },
1185
+ {
1186
+ "epoch": 2.6,
1187
+ "learning_rate": 0.0003,
1188
+ "loss": 2.571,
1189
+ "step": 194
1190
+ },
1191
+ {
1192
+ "epoch": 2.61,
1193
+ "learning_rate": 0.0003,
1194
+ "loss": 2.5137,
1195
+ "step": 195
1196
+ },
1197
+ {
1198
+ "epoch": 2.62,
1199
+ "learning_rate": 0.0003,
1200
+ "loss": 2.5757,
1201
+ "step": 196
1202
+ },
1203
+ {
1204
+ "epoch": 2.64,
1205
+ "learning_rate": 0.0003,
1206
+ "loss": 2.5974,
1207
+ "step": 197
1208
+ },
1209
+ {
1210
+ "epoch": 2.65,
1211
+ "learning_rate": 0.0003,
1212
+ "loss": 2.491,
1213
+ "step": 198
1214
+ },
1215
+ {
1216
+ "epoch": 2.66,
1217
+ "learning_rate": 0.0003,
1218
+ "loss": 2.5105,
1219
+ "step": 199
1220
+ },
1221
+ {
1222
+ "epoch": 2.68,
1223
+ "learning_rate": 0.0003,
1224
+ "loss": 2.533,
1225
+ "step": 200
1226
+ },
1227
+ {
1228
+ "epoch": 2.69,
1229
+ "learning_rate": 0.0003,
1230
+ "loss": 2.3655,
1231
+ "step": 201
1232
+ },
1233
+ {
1234
+ "epoch": 2.7,
1235
+ "learning_rate": 0.0003,
1236
+ "loss": 2.4854,
1237
+ "step": 202
1238
+ },
1239
+ {
1240
+ "epoch": 2.72,
1241
+ "learning_rate": 0.0003,
1242
+ "loss": 2.4832,
1243
+ "step": 203
1244
+ },
1245
+ {
1246
+ "epoch": 2.73,
1247
+ "learning_rate": 0.0003,
1248
+ "loss": 2.4731,
1249
+ "step": 204
1250
+ },
1251
+ {
1252
+ "epoch": 2.74,
1253
+ "learning_rate": 0.0003,
1254
+ "loss": 2.5583,
1255
+ "step": 205
1256
+ },
1257
+ {
1258
+ "epoch": 2.76,
1259
+ "learning_rate": 0.0003,
1260
+ "loss": 2.5283,
1261
+ "step": 206
1262
+ },
1263
+ {
1264
+ "epoch": 2.77,
1265
+ "learning_rate": 0.0003,
1266
+ "loss": 2.4526,
1267
+ "step": 207
1268
+ },
1269
+ {
1270
+ "epoch": 2.78,
1271
+ "learning_rate": 0.0003,
1272
+ "loss": 2.5413,
1273
+ "step": 208
1274
+ },
1275
+ {
1276
+ "epoch": 2.8,
1277
+ "learning_rate": 0.0003,
1278
+ "loss": 2.512,
1279
+ "step": 209
1280
+ },
1281
+ {
1282
+ "epoch": 2.81,
1283
+ "learning_rate": 0.0003,
1284
+ "loss": 2.4771,
1285
+ "step": 210
1286
+ },
1287
+ {
1288
+ "epoch": 2.82,
1289
+ "learning_rate": 0.0003,
1290
+ "loss": 2.3931,
1291
+ "step": 211
1292
+ },
1293
+ {
1294
+ "epoch": 2.84,
1295
+ "learning_rate": 0.0003,
1296
+ "loss": 2.5083,
1297
+ "step": 212
1298
+ },
1299
+ {
1300
+ "epoch": 2.85,
1301
+ "learning_rate": 0.0003,
1302
+ "loss": 2.5298,
1303
+ "step": 213
1304
+ },
1305
+ {
1306
+ "epoch": 2.86,
1307
+ "learning_rate": 0.0003,
1308
+ "loss": 2.4907,
1309
+ "step": 214
1310
+ },
1311
+ {
1312
+ "epoch": 2.88,
1313
+ "learning_rate": 0.0003,
1314
+ "loss": 2.5344,
1315
+ "step": 215
1316
+ },
1317
+ {
1318
+ "epoch": 2.89,
1319
+ "learning_rate": 0.0003,
1320
+ "loss": 2.5618,
1321
+ "step": 216
1322
+ },
1323
+ {
1324
+ "epoch": 2.9,
1325
+ "learning_rate": 0.0003,
1326
+ "loss": 2.5276,
1327
+ "step": 217
1328
+ },
1329
+ {
1330
+ "epoch": 2.92,
1331
+ "learning_rate": 0.0003,
1332
+ "loss": 2.5593,
1333
+ "step": 218
1334
+ },
1335
+ {
1336
+ "epoch": 2.93,
1337
+ "learning_rate": 0.0003,
1338
+ "loss": 2.4836,
1339
+ "step": 219
1340
+ },
1341
+ {
1342
+ "epoch": 2.94,
1343
+ "learning_rate": 0.0003,
1344
+ "loss": 2.553,
1345
+ "step": 220
1346
+ },
1347
+ {
1348
+ "epoch": 2.96,
1349
+ "learning_rate": 0.0003,
1350
+ "loss": 2.4614,
1351
+ "step": 221
1352
+ },
1353
+ {
1354
+ "epoch": 2.97,
1355
+ "learning_rate": 0.0003,
1356
+ "loss": 2.5391,
1357
+ "step": 222
1358
+ },
1359
+ {
1360
+ "epoch": 2.98,
1361
+ "learning_rate": 0.0003,
1362
+ "loss": 2.5266,
1363
+ "step": 223
1364
+ },
1365
+ {
1366
+ "epoch": 3.0,
1367
+ "learning_rate": 0.0003,
1368
+ "loss": 2.4602,
1369
+ "step": 224
1370
+ },
1371
+ {
1372
+ "epoch": 3.0,
1373
+ "eval_loss": 2.8984375,
1374
+ "eval_runtime": 92.6223,
1375
+ "eval_samples_per_second": 2.537,
1376
+ "eval_steps_per_second": 1.274,
1377
+ "step": 224
1378
+ },
1379
+ {
1380
+ "epoch": 3.01,
1381
+ "learning_rate": 0.0003,
1382
+ "loss": 2.3523,
1383
+ "step": 225
1384
+ },
1385
+ {
1386
+ "epoch": 3.02,
1387
+ "learning_rate": 0.0003,
1388
+ "loss": 2.2725,
1389
+ "step": 226
1390
+ },
1391
+ {
1392
+ "epoch": 3.04,
1393
+ "learning_rate": 0.0003,
1394
+ "loss": 2.3198,
1395
+ "step": 227
1396
+ },
1397
+ {
1398
+ "epoch": 3.05,
1399
+ "learning_rate": 0.0003,
1400
+ "loss": 2.3079,
1401
+ "step": 228
1402
+ },
1403
+ {
1404
+ "epoch": 3.06,
1405
+ "learning_rate": 0.0003,
1406
+ "loss": 2.1519,
1407
+ "step": 229
1408
+ },
1409
+ {
1410
+ "epoch": 3.08,
1411
+ "learning_rate": 0.0003,
1412
+ "loss": 2.167,
1413
+ "step": 230
1414
+ },
1415
+ {
1416
+ "epoch": 3.09,
1417
+ "learning_rate": 0.0003,
1418
+ "loss": 2.2751,
1419
+ "step": 231
1420
+ },
1421
+ {
1422
+ "epoch": 3.1,
1423
+ "learning_rate": 0.0003,
1424
+ "loss": 2.2551,
1425
+ "step": 232
1426
+ },
1427
+ {
1428
+ "epoch": 3.12,
1429
+ "learning_rate": 0.0003,
1430
+ "loss": 2.2458,
1431
+ "step": 233
1432
+ },
1433
+ {
1434
+ "epoch": 3.13,
1435
+ "learning_rate": 0.0003,
1436
+ "loss": 2.231,
1437
+ "step": 234
1438
+ },
1439
+ {
1440
+ "epoch": 3.14,
1441
+ "learning_rate": 0.0003,
1442
+ "loss": 2.196,
1443
+ "step": 235
1444
+ },
1445
+ {
1446
+ "epoch": 3.16,
1447
+ "learning_rate": 0.0003,
1448
+ "loss": 2.252,
1449
+ "step": 236
1450
+ },
1451
+ {
1452
+ "epoch": 3.17,
1453
+ "learning_rate": 0.0003,
1454
+ "loss": 2.2136,
1455
+ "step": 237
1456
+ },
1457
+ {
1458
+ "epoch": 3.18,
1459
+ "learning_rate": 0.0003,
1460
+ "loss": 2.2168,
1461
+ "step": 238
1462
+ },
1463
+ {
1464
+ "epoch": 3.2,
1465
+ "learning_rate": 0.0003,
1466
+ "loss": 2.1956,
1467
+ "step": 239
1468
+ },
1469
+ {
1470
+ "epoch": 3.21,
1471
+ "learning_rate": 0.0003,
1472
+ "loss": 2.2034,
1473
+ "step": 240
1474
+ },
1475
+ {
1476
+ "epoch": 3.22,
1477
+ "learning_rate": 0.0003,
1478
+ "loss": 2.2258,
1479
+ "step": 241
1480
+ },
1481
+ {
1482
+ "epoch": 3.24,
1483
+ "learning_rate": 0.0003,
1484
+ "loss": 2.2449,
1485
+ "step": 242
1486
+ },
1487
+ {
1488
+ "epoch": 3.25,
1489
+ "learning_rate": 0.0003,
1490
+ "loss": 2.2307,
1491
+ "step": 243
1492
+ },
1493
+ {
1494
+ "epoch": 3.26,
1495
+ "learning_rate": 0.0003,
1496
+ "loss": 2.1936,
1497
+ "step": 244
1498
+ },
1499
+ {
1500
+ "epoch": 3.28,
1501
+ "learning_rate": 0.0003,
1502
+ "loss": 2.2822,
1503
+ "step": 245
1504
+ },
1505
+ {
1506
+ "epoch": 3.29,
1507
+ "learning_rate": 0.0003,
1508
+ "loss": 2.2852,
1509
+ "step": 246
1510
+ },
1511
+ {
1512
+ "epoch": 3.3,
1513
+ "learning_rate": 0.0003,
1514
+ "loss": 2.3364,
1515
+ "step": 247
1516
+ },
1517
+ {
1518
+ "epoch": 3.32,
1519
+ "learning_rate": 0.0003,
1520
+ "loss": 2.2305,
1521
+ "step": 248
1522
+ },
1523
+ {
1524
+ "epoch": 3.33,
1525
+ "learning_rate": 0.0003,
1526
+ "loss": 2.2444,
1527
+ "step": 249
1528
+ },
1529
+ {
1530
+ "epoch": 3.34,
1531
+ "learning_rate": 0.0003,
1532
+ "loss": 2.3188,
1533
+ "step": 250
1534
+ },
1535
+ {
1536
+ "epoch": 3.36,
1537
+ "learning_rate": 0.0003,
1538
+ "loss": 2.1794,
1539
+ "step": 251
1540
+ },
1541
+ {
1542
+ "epoch": 3.37,
1543
+ "learning_rate": 0.0003,
1544
+ "loss": 2.3245,
1545
+ "step": 252
1546
+ },
1547
+ {
1548
+ "epoch": 3.38,
1549
+ "learning_rate": 0.0003,
1550
+ "loss": 2.2239,
1551
+ "step": 253
1552
+ },
1553
+ {
1554
+ "epoch": 3.4,
1555
+ "learning_rate": 0.0003,
1556
+ "loss": 2.2244,
1557
+ "step": 254
1558
+ },
1559
+ {
1560
+ "epoch": 3.41,
1561
+ "learning_rate": 0.0003,
1562
+ "loss": 2.2092,
1563
+ "step": 255
1564
+ },
1565
+ {
1566
+ "epoch": 3.42,
1567
+ "learning_rate": 0.0003,
1568
+ "loss": 2.2544,
1569
+ "step": 256
1570
+ },
1571
+ {
1572
+ "epoch": 3.44,
1573
+ "learning_rate": 0.0003,
1574
+ "loss": 2.2385,
1575
+ "step": 257
1576
+ },
1577
+ {
1578
+ "epoch": 3.45,
1579
+ "learning_rate": 0.0003,
1580
+ "loss": 2.2588,
1581
+ "step": 258
1582
+ },
1583
+ {
1584
+ "epoch": 3.46,
1585
+ "learning_rate": 0.0003,
1586
+ "loss": 2.3193,
1587
+ "step": 259
1588
+ },
1589
+ {
1590
+ "epoch": 3.48,
1591
+ "learning_rate": 0.0003,
1592
+ "loss": 2.2844,
1593
+ "step": 260
1594
+ },
1595
+ {
1596
+ "epoch": 3.49,
1597
+ "learning_rate": 0.0003,
1598
+ "loss": 2.2725,
1599
+ "step": 261
1600
+ },
1601
+ {
1602
+ "epoch": 3.51,
1603
+ "learning_rate": 0.0003,
1604
+ "loss": 2.241,
1605
+ "step": 262
1606
+ },
1607
+ {
1608
+ "epoch": 3.52,
1609
+ "learning_rate": 0.0003,
1610
+ "loss": 2.272,
1611
+ "step": 263
1612
+ },
1613
+ {
1614
+ "epoch": 3.53,
1615
+ "learning_rate": 0.0003,
1616
+ "loss": 2.292,
1617
+ "step": 264
1618
+ },
1619
+ {
1620
+ "epoch": 3.55,
1621
+ "learning_rate": 0.0003,
1622
+ "loss": 2.2366,
1623
+ "step": 265
1624
+ },
1625
+ {
1626
+ "epoch": 3.56,
1627
+ "learning_rate": 0.0003,
1628
+ "loss": 2.2412,
1629
+ "step": 266
1630
+ },
1631
+ {
1632
+ "epoch": 3.57,
1633
+ "learning_rate": 0.0003,
1634
+ "loss": 2.2478,
1635
+ "step": 267
1636
+ },
1637
+ {
1638
+ "epoch": 3.59,
1639
+ "learning_rate": 0.0003,
1640
+ "loss": 2.2139,
1641
+ "step": 268
1642
+ },
1643
+ {
1644
+ "epoch": 3.6,
1645
+ "learning_rate": 0.0003,
1646
+ "loss": 2.2808,
1647
+ "step": 269
1648
+ },
1649
+ {
1650
+ "epoch": 3.61,
1651
+ "learning_rate": 0.0003,
1652
+ "loss": 2.3083,
1653
+ "step": 270
1654
+ },
1655
+ {
1656
+ "epoch": 3.63,
1657
+ "learning_rate": 0.0003,
1658
+ "loss": 2.2112,
1659
+ "step": 271
1660
+ },
1661
+ {
1662
+ "epoch": 3.64,
1663
+ "learning_rate": 0.0003,
1664
+ "loss": 2.2676,
1665
+ "step": 272
1666
+ },
1667
+ {
1668
+ "epoch": 3.65,
1669
+ "learning_rate": 0.0003,
1670
+ "loss": 2.2532,
1671
+ "step": 273
1672
+ },
1673
+ {
1674
+ "epoch": 3.67,
1675
+ "learning_rate": 0.0003,
1676
+ "loss": 2.3318,
1677
+ "step": 274
1678
+ },
1679
+ {
1680
+ "epoch": 3.68,
1681
+ "learning_rate": 0.0003,
1682
+ "loss": 2.2227,
1683
+ "step": 275
1684
+ },
1685
+ {
1686
+ "epoch": 3.69,
1687
+ "learning_rate": 0.0003,
1688
+ "loss": 2.3018,
1689
+ "step": 276
1690
+ },
1691
+ {
1692
+ "epoch": 3.71,
1693
+ "learning_rate": 0.0003,
1694
+ "loss": 2.2874,
1695
+ "step": 277
1696
+ },
1697
+ {
1698
+ "epoch": 3.72,
1699
+ "learning_rate": 0.0003,
1700
+ "loss": 2.282,
1701
+ "step": 278
1702
+ },
1703
+ {
1704
+ "epoch": 3.73,
1705
+ "learning_rate": 0.0003,
1706
+ "loss": 2.2705,
1707
+ "step": 279
1708
+ },
1709
+ {
1710
+ "epoch": 3.75,
1711
+ "learning_rate": 0.0003,
1712
+ "loss": 2.2534,
1713
+ "step": 280
1714
+ },
1715
+ {
1716
+ "epoch": 3.76,
1717
+ "learning_rate": 0.0003,
1718
+ "loss": 2.2744,
1719
+ "step": 281
1720
+ },
1721
+ {
1722
+ "epoch": 3.77,
1723
+ "learning_rate": 0.0003,
1724
+ "loss": 2.2212,
1725
+ "step": 282
1726
+ },
1727
+ {
1728
+ "epoch": 3.79,
1729
+ "learning_rate": 0.0003,
1730
+ "loss": 2.2507,
1731
+ "step": 283
1732
+ },
1733
+ {
1734
+ "epoch": 3.8,
1735
+ "learning_rate": 0.0003,
1736
+ "loss": 2.3235,
1737
+ "step": 284
1738
+ },
1739
+ {
1740
+ "epoch": 3.81,
1741
+ "learning_rate": 0.0003,
1742
+ "loss": 2.2859,
1743
+ "step": 285
1744
+ },
1745
+ {
1746
+ "epoch": 3.83,
1747
+ "learning_rate": 0.0003,
1748
+ "loss": 2.2629,
1749
+ "step": 286
1750
+ },
1751
+ {
1752
+ "epoch": 3.84,
1753
+ "learning_rate": 0.0003,
1754
+ "loss": 2.27,
1755
+ "step": 287
1756
+ },
1757
+ {
1758
+ "epoch": 3.85,
1759
+ "learning_rate": 0.0003,
1760
+ "loss": 2.2432,
1761
+ "step": 288
1762
+ },
1763
+ {
1764
+ "epoch": 3.87,
1765
+ "learning_rate": 0.0003,
1766
+ "loss": 2.2455,
1767
+ "step": 289
1768
+ },
1769
+ {
1770
+ "epoch": 3.88,
1771
+ "learning_rate": 0.0003,
1772
+ "loss": 2.3276,
1773
+ "step": 290
1774
+ },
1775
+ {
1776
+ "epoch": 3.89,
1777
+ "learning_rate": 0.0003,
1778
+ "loss": 2.2976,
1779
+ "step": 291
1780
+ },
1781
+ {
1782
+ "epoch": 3.91,
1783
+ "learning_rate": 0.0003,
1784
+ "loss": 2.2205,
1785
+ "step": 292
1786
+ },
1787
+ {
1788
+ "epoch": 3.92,
1789
+ "learning_rate": 0.0003,
1790
+ "loss": 2.2708,
1791
+ "step": 293
1792
+ },
1793
+ {
1794
+ "epoch": 3.93,
1795
+ "learning_rate": 0.0003,
1796
+ "loss": 2.218,
1797
+ "step": 294
1798
+ },
1799
+ {
1800
+ "epoch": 3.95,
1801
+ "learning_rate": 0.0003,
1802
+ "loss": 2.2646,
1803
+ "step": 295
1804
+ },
1805
+ {
1806
+ "epoch": 3.96,
1807
+ "learning_rate": 0.0003,
1808
+ "loss": 2.2998,
1809
+ "step": 296
1810
+ },
1811
+ {
1812
+ "epoch": 3.96,
1813
+ "eval_loss": 2.978515625,
1814
+ "eval_runtime": 92.5066,
1815
+ "eval_samples_per_second": 2.54,
1816
+ "eval_steps_per_second": 1.276,
1817
+ "step": 296
1818
+ },
1819
+ {
1820
+ "epoch": 3.96,
1821
+ "step": 296,
1822
+ "total_flos": 1.523122330182615e+17,
1823
+ "train_loss": 2.6439707988017314,
1824
+ "train_runtime": 11454.487,
1825
+ "train_samples_per_second": 0.835,
1826
+ "train_steps_per_second": 0.026
1827
+ }
1828
+ ],
1829
+ "logging_steps": 1.0,
1830
+ "max_steps": 296,
1831
+ "num_input_tokens_seen": 0,
1832
+ "num_train_epochs": 4,
1833
+ "save_steps": 1000,
1834
+ "total_flos": 1.523122330182615e+17,
1835
+ "train_batch_size": 4,
1836
+ "trial_name": null,
1837
+ "trial_params": null
1838
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f69fbf06e9f3dec02c3088d13f25c92fd17ebd0b0a4b19bfb8878ecc980571d
3
+ size 6328