sizhkhy commited on
Commit
3bf05f3
·
verified ·
1 Parent(s): 320b372

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: unsloth/Llama-3.2-3B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - unsloth
9
+ - generated_from_trainer
10
+ model-index:
11
+ - name: llm3br256
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # llm3br256
19
+
20
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the spinny dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0079
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 4
43
+ - eval_batch_size: 4
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 32
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 5.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.0598 | 0.0578 | 5 | 0.0557 |
57
+ | 0.0388 | 0.1156 | 10 | 0.0346 |
58
+ | 0.0275 | 0.1734 | 15 | 0.0276 |
59
+ | 0.0218 | 0.2312 | 20 | 0.0228 |
60
+ | 0.0236 | 0.2890 | 25 | 0.0203 |
61
+ | 0.0182 | 0.3468 | 30 | 0.0179 |
62
+ | 0.019 | 0.4046 | 35 | 0.0162 |
63
+ | 0.017 | 0.4624 | 40 | 0.0147 |
64
+ | 0.0147 | 0.5202 | 45 | 0.0137 |
65
+ | 0.0118 | 0.5780 | 50 | 0.0132 |
66
+ | 0.0107 | 0.6358 | 55 | 0.0127 |
67
+ | 0.016 | 0.6936 | 60 | 0.0123 |
68
+ | 0.0144 | 0.7514 | 65 | 0.0116 |
69
+ | 0.0119 | 0.8092 | 70 | 0.0113 |
70
+ | 0.0111 | 0.8671 | 75 | 0.0109 |
71
+ | 0.012 | 0.9249 | 80 | 0.0107 |
72
+ | 0.0139 | 0.9827 | 85 | 0.0102 |
73
+ | 0.0085 | 1.0405 | 90 | 0.0104 |
74
+ | 0.01 | 1.0983 | 95 | 0.0102 |
75
+ | 0.009 | 1.1561 | 100 | 0.0099 |
76
+ | 0.0094 | 1.2139 | 105 | 0.0098 |
77
+ | 0.0069 | 1.2717 | 110 | 0.0099 |
78
+ | 0.0108 | 1.3295 | 115 | 0.0096 |
79
+ | 0.0066 | 1.3873 | 120 | 0.0095 |
80
+ | 0.0089 | 1.4451 | 125 | 0.0094 |
81
+ | 0.0084 | 1.5029 | 130 | 0.0093 |
82
+ | 0.0102 | 1.5607 | 135 | 0.0093 |
83
+ | 0.01 | 1.6185 | 140 | 0.0091 |
84
+ | 0.0098 | 1.6763 | 145 | 0.0088 |
85
+ | 0.0071 | 1.7341 | 150 | 0.0087 |
86
+ | 0.0094 | 1.7919 | 155 | 0.0086 |
87
+ | 0.008 | 1.8497 | 160 | 0.0086 |
88
+ | 0.01 | 1.9075 | 165 | 0.0085 |
89
+ | 0.0084 | 1.9653 | 170 | 0.0086 |
90
+ | 0.0058 | 2.0231 | 175 | 0.0087 |
91
+ | 0.0056 | 2.0809 | 180 | 0.0090 |
92
+ | 0.0077 | 2.1387 | 185 | 0.0086 |
93
+ | 0.0061 | 2.1965 | 190 | 0.0086 |
94
+ | 0.008 | 2.2543 | 195 | 0.0083 |
95
+ | 0.0058 | 2.3121 | 200 | 0.0083 |
96
+ | 0.0047 | 2.3699 | 205 | 0.0084 |
97
+ | 0.0066 | 2.4277 | 210 | 0.0084 |
98
+ | 0.0055 | 2.4855 | 215 | 0.0082 |
99
+ | 0.0056 | 2.5434 | 220 | 0.0083 |
100
+ | 0.005 | 2.6012 | 225 | 0.0082 |
101
+ | 0.0065 | 2.6590 | 230 | 0.0082 |
102
+ | 0.0061 | 2.7168 | 235 | 0.0081 |
103
+ | 0.0052 | 2.7746 | 240 | 0.0082 |
104
+ | 0.0053 | 2.8324 | 245 | 0.0081 |
105
+ | 0.0058 | 2.8902 | 250 | 0.0079 |
106
+ | 0.0052 | 2.9480 | 255 | 0.0078 |
107
+ | 0.0071 | 3.0058 | 260 | 0.0080 |
108
+ | 0.0051 | 3.0636 | 265 | 0.0082 |
109
+ | 0.0033 | 3.1214 | 270 | 0.0086 |
110
+ | 0.004 | 3.1792 | 275 | 0.0084 |
111
+ | 0.0032 | 3.2370 | 280 | 0.0082 |
112
+ | 0.0042 | 3.2948 | 285 | 0.0082 |
113
+ | 0.0035 | 3.3526 | 290 | 0.0082 |
114
+ | 0.0041 | 3.4104 | 295 | 0.0081 |
115
+ | 0.0048 | 3.4682 | 300 | 0.0080 |
116
+ | 0.0046 | 3.5260 | 305 | 0.0080 |
117
+ | 0.004 | 3.5838 | 310 | 0.0080 |
118
+ | 0.0032 | 3.6416 | 315 | 0.0081 |
119
+ | 0.0039 | 3.6994 | 320 | 0.0084 |
120
+ | 0.0042 | 3.7572 | 325 | 0.0083 |
121
+ | 0.0046 | 3.8150 | 330 | 0.0080 |
122
+ | 0.0035 | 3.8728 | 335 | 0.0081 |
123
+ | 0.0048 | 3.9306 | 340 | 0.0081 |
124
+ | 0.0056 | 3.9884 | 345 | 0.0080 |
125
+ | 0.0025 | 4.0462 | 350 | 0.0080 |
126
+ | 0.0035 | 4.1040 | 355 | 0.0082 |
127
+ | 0.0028 | 4.1618 | 360 | 0.0083 |
128
+ | 0.0028 | 4.2197 | 365 | 0.0084 |
129
+ | 0.003 | 4.2775 | 370 | 0.0085 |
130
+ | 0.0033 | 4.3353 | 375 | 0.0085 |
131
+ | 0.003 | 4.3931 | 380 | 0.0086 |
132
+ | 0.0022 | 4.4509 | 385 | 0.0086 |
133
+ | 0.0028 | 4.5087 | 390 | 0.0086 |
134
+ | 0.0028 | 4.5665 | 395 | 0.0085 |
135
+ | 0.0031 | 4.6243 | 400 | 0.0085 |
136
+ | 0.0038 | 4.6821 | 405 | 0.0084 |
137
+ | 0.0024 | 4.7399 | 410 | 0.0084 |
138
+ | 0.0024 | 4.7977 | 415 | 0.0084 |
139
+ | 0.0024 | 4.8555 | 420 | 0.0084 |
140
+ | 0.0026 | 4.9133 | 425 | 0.0084 |
141
+ | 0.0029 | 4.9711 | 430 | 0.0084 |
142
+
143
+
144
+ ### Framework versions
145
+
146
+ - PEFT 0.12.0
147
+ - Transformers 4.46.1
148
+ - Pytorch 2.4.0+cu121
149
+ - Datasets 3.1.0
150
+ - Tokenizers 0.20.3
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
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": 256,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 256,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "down_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:bebbf269a40455849956cb38b21f996f00ac73b950dde5df91542ce37bc4f202
3
+ size 1556140392
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.971098265895954,
3
+ "eval_loss": 0.007892867550253868,
4
+ "eval_runtime": 9.953,
5
+ "eval_samples_per_second": 5.024,
6
+ "eval_steps_per_second": 1.306,
7
+ "total_flos": 1.0207257247425331e+18,
8
+ "train_loss": 0.0087554031284526,
9
+ "train_runtime": 8412.5192,
10
+ "train_samples_per_second": 1.645,
11
+ "train_steps_per_second": 0.051
12
+ }
checkpoint-250/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Llama-3.2-3B-Instruct
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 0.12.0
checkpoint-250/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
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": 256,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 256,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-250/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bebbf269a40455849956cb38b21f996f00ac73b950dde5df91542ce37bc4f202
3
+ size 1556140392
checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e2eadf13a261de3d60d5b4a85b91bd3e5eaf7704be90c10cfcc836315fed0a
3
+ size 3112505578
checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f362e1a8fea4e1cffd5ed7fa11c32dbf4c14f359e0b86f9d7b4d7926514d2d3
3
+ size 14308
checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93d1c8dcf6e2b250fdc3ba1db5b8713fa5d5c0399e828e57c5dcf99ddeb179d
3
+ size 1064
checkpoint-250/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
checkpoint-250/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-250/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,2183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.007892865687608719,
3
+ "best_model_checkpoint": "/home/paperspace/Data/models/spinny/llm3br256/checkpoint-250",
4
+ "epoch": 2.8901734104046244,
5
+ "eval_steps": 5,
6
+ "global_step": 250,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.011560693641618497,
13
+ "grad_norm": 0.15129172801971436,
14
+ "learning_rate": 2.325581395348837e-06,
15
+ "loss": 0.068,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.023121387283236993,
20
+ "grad_norm": 0.14174357056617737,
21
+ "learning_rate": 4.651162790697674e-06,
22
+ "loss": 0.0635,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03468208092485549,
27
+ "grad_norm": 0.14430448412895203,
28
+ "learning_rate": 6.976744186046512e-06,
29
+ "loss": 0.0649,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.046242774566473986,
34
+ "grad_norm": 0.1410493552684784,
35
+ "learning_rate": 9.302325581395349e-06,
36
+ "loss": 0.063,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.057803468208092484,
41
+ "grad_norm": 0.13995003700256348,
42
+ "learning_rate": 1.1627906976744187e-05,
43
+ "loss": 0.0598,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.057803468208092484,
48
+ "eval_loss": 0.05565303936600685,
49
+ "eval_runtime": 11.8576,
50
+ "eval_samples_per_second": 4.217,
51
+ "eval_steps_per_second": 1.096,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.06936416184971098,
56
+ "grad_norm": 0.12226737290620804,
57
+ "learning_rate": 1.3953488372093024e-05,
58
+ "loss": 0.0533,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.08092485549132948,
63
+ "grad_norm": 0.10596886277198792,
64
+ "learning_rate": 1.6279069767441862e-05,
65
+ "loss": 0.0544,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.09248554913294797,
70
+ "grad_norm": 0.07781537622213364,
71
+ "learning_rate": 1.8604651162790697e-05,
72
+ "loss": 0.0448,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.10404624277456648,
77
+ "grad_norm": 0.06554879248142242,
78
+ "learning_rate": 2.0930232558139536e-05,
79
+ "loss": 0.0373,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.11560693641618497,
84
+ "grad_norm": 0.08980869501829147,
85
+ "learning_rate": 2.3255813953488374e-05,
86
+ "loss": 0.0388,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.11560693641618497,
91
+ "eval_loss": 0.034586433321237564,
92
+ "eval_runtime": 10.0247,
93
+ "eval_samples_per_second": 4.988,
94
+ "eval_steps_per_second": 1.297,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 0.12716763005780346,
99
+ "grad_norm": 0.08015415817499161,
100
+ "learning_rate": 2.5581395348837212e-05,
101
+ "loss": 0.0393,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.13872832369942195,
106
+ "grad_norm": 0.06148159131407738,
107
+ "learning_rate": 2.7906976744186048e-05,
108
+ "loss": 0.0377,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.15028901734104047,
113
+ "grad_norm": 0.04883963614702225,
114
+ "learning_rate": 3.0232558139534883e-05,
115
+ "loss": 0.0356,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.16184971098265896,
120
+ "grad_norm": 0.04954546317458153,
121
+ "learning_rate": 3.2558139534883724e-05,
122
+ "loss": 0.0363,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.17341040462427745,
127
+ "grad_norm": 0.041509971022605896,
128
+ "learning_rate": 3.488372093023256e-05,
129
+ "loss": 0.0275,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.17341040462427745,
134
+ "eval_loss": 0.027632026001811028,
135
+ "eval_runtime": 10.0235,
136
+ "eval_samples_per_second": 4.988,
137
+ "eval_steps_per_second": 1.297,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.18497109826589594,
142
+ "grad_norm": 0.041887976229190826,
143
+ "learning_rate": 3.7209302325581394e-05,
144
+ "loss": 0.0303,
145
+ "step": 16
146
+ },
147
+ {
148
+ "epoch": 0.19653179190751446,
149
+ "grad_norm": 0.03965295851230621,
150
+ "learning_rate": 3.953488372093023e-05,
151
+ "loss": 0.0284,
152
+ "step": 17
153
+ },
154
+ {
155
+ "epoch": 0.20809248554913296,
156
+ "grad_norm": 0.03458382189273834,
157
+ "learning_rate": 4.186046511627907e-05,
158
+ "loss": 0.03,
159
+ "step": 18
160
+ },
161
+ {
162
+ "epoch": 0.21965317919075145,
163
+ "grad_norm": 0.03138720989227295,
164
+ "learning_rate": 4.418604651162791e-05,
165
+ "loss": 0.0242,
166
+ "step": 19
167
+ },
168
+ {
169
+ "epoch": 0.23121387283236994,
170
+ "grad_norm": 0.02681548520922661,
171
+ "learning_rate": 4.651162790697675e-05,
172
+ "loss": 0.0218,
173
+ "step": 20
174
+ },
175
+ {
176
+ "epoch": 0.23121387283236994,
177
+ "eval_loss": 0.02280299924314022,
178
+ "eval_runtime": 10.0675,
179
+ "eval_samples_per_second": 4.967,
180
+ "eval_steps_per_second": 1.291,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.24277456647398843,
185
+ "grad_norm": 0.03174450621008873,
186
+ "learning_rate": 4.883720930232558e-05,
187
+ "loss": 0.0235,
188
+ "step": 21
189
+ },
190
+ {
191
+ "epoch": 0.2543352601156069,
192
+ "grad_norm": 0.033451005816459656,
193
+ "learning_rate": 5.1162790697674425e-05,
194
+ "loss": 0.0291,
195
+ "step": 22
196
+ },
197
+ {
198
+ "epoch": 0.2658959537572254,
199
+ "grad_norm": 0.03227928280830383,
200
+ "learning_rate": 5.348837209302326e-05,
201
+ "loss": 0.0254,
202
+ "step": 23
203
+ },
204
+ {
205
+ "epoch": 0.2774566473988439,
206
+ "grad_norm": 0.03783709928393364,
207
+ "learning_rate": 5.5813953488372095e-05,
208
+ "loss": 0.0256,
209
+ "step": 24
210
+ },
211
+ {
212
+ "epoch": 0.28901734104046245,
213
+ "grad_norm": 0.03228365629911423,
214
+ "learning_rate": 5.8139534883720933e-05,
215
+ "loss": 0.0236,
216
+ "step": 25
217
+ },
218
+ {
219
+ "epoch": 0.28901734104046245,
220
+ "eval_loss": 0.020257851108908653,
221
+ "eval_runtime": 10.0419,
222
+ "eval_samples_per_second": 4.979,
223
+ "eval_steps_per_second": 1.295,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 0.30057803468208094,
228
+ "grad_norm": 0.02823326177895069,
229
+ "learning_rate": 6.0465116279069765e-05,
230
+ "loss": 0.0229,
231
+ "step": 26
232
+ },
233
+ {
234
+ "epoch": 0.31213872832369943,
235
+ "grad_norm": 0.02882234752178192,
236
+ "learning_rate": 6.27906976744186e-05,
237
+ "loss": 0.0226,
238
+ "step": 27
239
+ },
240
+ {
241
+ "epoch": 0.3236994219653179,
242
+ "grad_norm": 0.02527730166912079,
243
+ "learning_rate": 6.511627906976745e-05,
244
+ "loss": 0.0196,
245
+ "step": 28
246
+ },
247
+ {
248
+ "epoch": 0.3352601156069364,
249
+ "grad_norm": 0.026926985010504723,
250
+ "learning_rate": 6.744186046511628e-05,
251
+ "loss": 0.0182,
252
+ "step": 29
253
+ },
254
+ {
255
+ "epoch": 0.3468208092485549,
256
+ "grad_norm": 0.02383883111178875,
257
+ "learning_rate": 6.976744186046513e-05,
258
+ "loss": 0.0182,
259
+ "step": 30
260
+ },
261
+ {
262
+ "epoch": 0.3468208092485549,
263
+ "eval_loss": 0.01791333220899105,
264
+ "eval_runtime": 10.1038,
265
+ "eval_samples_per_second": 4.949,
266
+ "eval_steps_per_second": 1.287,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 0.3583815028901734,
271
+ "grad_norm": 0.020905988290905952,
272
+ "learning_rate": 7.209302325581396e-05,
273
+ "loss": 0.0173,
274
+ "step": 31
275
+ },
276
+ {
277
+ "epoch": 0.3699421965317919,
278
+ "grad_norm": 0.021837348118424416,
279
+ "learning_rate": 7.441860465116279e-05,
280
+ "loss": 0.0186,
281
+ "step": 32
282
+ },
283
+ {
284
+ "epoch": 0.3815028901734104,
285
+ "grad_norm": 0.022534186020493507,
286
+ "learning_rate": 7.674418604651163e-05,
287
+ "loss": 0.0192,
288
+ "step": 33
289
+ },
290
+ {
291
+ "epoch": 0.3930635838150289,
292
+ "grad_norm": 0.021404536440968513,
293
+ "learning_rate": 7.906976744186047e-05,
294
+ "loss": 0.0163,
295
+ "step": 34
296
+ },
297
+ {
298
+ "epoch": 0.4046242774566474,
299
+ "grad_norm": 0.02087543159723282,
300
+ "learning_rate": 8.139534883720931e-05,
301
+ "loss": 0.019,
302
+ "step": 35
303
+ },
304
+ {
305
+ "epoch": 0.4046242774566474,
306
+ "eval_loss": 0.016155000776052475,
307
+ "eval_runtime": 10.0056,
308
+ "eval_samples_per_second": 4.997,
309
+ "eval_steps_per_second": 1.299,
310
+ "step": 35
311
+ },
312
+ {
313
+ "epoch": 0.4161849710982659,
314
+ "grad_norm": 0.023041941225528717,
315
+ "learning_rate": 8.372093023255814e-05,
316
+ "loss": 0.0157,
317
+ "step": 36
318
+ },
319
+ {
320
+ "epoch": 0.4277456647398844,
321
+ "grad_norm": 0.020684899762272835,
322
+ "learning_rate": 8.604651162790697e-05,
323
+ "loss": 0.0154,
324
+ "step": 37
325
+ },
326
+ {
327
+ "epoch": 0.4393063583815029,
328
+ "grad_norm": 0.019204530864953995,
329
+ "learning_rate": 8.837209302325582e-05,
330
+ "loss": 0.0142,
331
+ "step": 38
332
+ },
333
+ {
334
+ "epoch": 0.4508670520231214,
335
+ "grad_norm": 0.019893651828169823,
336
+ "learning_rate": 9.069767441860465e-05,
337
+ "loss": 0.0155,
338
+ "step": 39
339
+ },
340
+ {
341
+ "epoch": 0.4624277456647399,
342
+ "grad_norm": 0.022773414850234985,
343
+ "learning_rate": 9.30232558139535e-05,
344
+ "loss": 0.017,
345
+ "step": 40
346
+ },
347
+ {
348
+ "epoch": 0.4624277456647399,
349
+ "eval_loss": 0.01472202967852354,
350
+ "eval_runtime": 10.018,
351
+ "eval_samples_per_second": 4.991,
352
+ "eval_steps_per_second": 1.298,
353
+ "step": 40
354
+ },
355
+ {
356
+ "epoch": 0.47398843930635837,
357
+ "grad_norm": 0.021773461252450943,
358
+ "learning_rate": 9.534883720930233e-05,
359
+ "loss": 0.0161,
360
+ "step": 41
361
+ },
362
+ {
363
+ "epoch": 0.48554913294797686,
364
+ "grad_norm": 0.023095447570085526,
365
+ "learning_rate": 9.767441860465116e-05,
366
+ "loss": 0.0146,
367
+ "step": 42
368
+ },
369
+ {
370
+ "epoch": 0.49710982658959535,
371
+ "grad_norm": 0.0202298853546381,
372
+ "learning_rate": 0.0001,
373
+ "loss": 0.015,
374
+ "step": 43
375
+ },
376
+ {
377
+ "epoch": 0.5086705202312138,
378
+ "grad_norm": 0.01809552311897278,
379
+ "learning_rate": 9.999835253787473e-05,
380
+ "loss": 0.0149,
381
+ "step": 44
382
+ },
383
+ {
384
+ "epoch": 0.5202312138728323,
385
+ "grad_norm": 0.019870778545737267,
386
+ "learning_rate": 9.999341026006419e-05,
387
+ "loss": 0.0147,
388
+ "step": 45
389
+ },
390
+ {
391
+ "epoch": 0.5202312138728323,
392
+ "eval_loss": 0.013716931454837322,
393
+ "eval_runtime": 10.0201,
394
+ "eval_samples_per_second": 4.99,
395
+ "eval_steps_per_second": 1.297,
396
+ "step": 45
397
+ },
398
+ {
399
+ "epoch": 0.5317919075144508,
400
+ "grad_norm": 0.017238808795809746,
401
+ "learning_rate": 9.998517349225698e-05,
402
+ "loss": 0.0107,
403
+ "step": 46
404
+ },
405
+ {
406
+ "epoch": 0.5433526011560693,
407
+ "grad_norm": 0.022697314620018005,
408
+ "learning_rate": 9.997364277724361e-05,
409
+ "loss": 0.0149,
410
+ "step": 47
411
+ },
412
+ {
413
+ "epoch": 0.5549132947976878,
414
+ "grad_norm": 0.023472866043448448,
415
+ "learning_rate": 9.99588188748808e-05,
416
+ "loss": 0.0144,
417
+ "step": 48
418
+ },
419
+ {
420
+ "epoch": 0.5664739884393064,
421
+ "grad_norm": 0.017129473388195038,
422
+ "learning_rate": 9.994070276204116e-05,
423
+ "loss": 0.0126,
424
+ "step": 49
425
+ },
426
+ {
427
+ "epoch": 0.5780346820809249,
428
+ "grad_norm": 0.01756882295012474,
429
+ "learning_rate": 9.991929563254914e-05,
430
+ "loss": 0.0118,
431
+ "step": 50
432
+ },
433
+ {
434
+ "epoch": 0.5780346820809249,
435
+ "eval_loss": 0.013151152059435844,
436
+ "eval_runtime": 10.0009,
437
+ "eval_samples_per_second": 5.0,
438
+ "eval_steps_per_second": 1.3,
439
+ "step": 50
440
+ },
441
+ {
442
+ "epoch": 0.5895953757225434,
443
+ "grad_norm": 0.019612474367022514,
444
+ "learning_rate": 9.989459889710213e-05,
445
+ "loss": 0.0144,
446
+ "step": 51
447
+ },
448
+ {
449
+ "epoch": 0.6011560693641619,
450
+ "grad_norm": 0.016709089279174805,
451
+ "learning_rate": 9.986661418317759e-05,
452
+ "loss": 0.0119,
453
+ "step": 52
454
+ },
455
+ {
456
+ "epoch": 0.6127167630057804,
457
+ "grad_norm": 0.023054232820868492,
458
+ "learning_rate": 9.983534333492575e-05,
459
+ "loss": 0.0137,
460
+ "step": 53
461
+ },
462
+ {
463
+ "epoch": 0.6242774566473989,
464
+ "grad_norm": 0.02029217965900898,
465
+ "learning_rate": 9.980078841304816e-05,
466
+ "loss": 0.014,
467
+ "step": 54
468
+ },
469
+ {
470
+ "epoch": 0.6358381502890174,
471
+ "grad_norm": 0.018532264977693558,
472
+ "learning_rate": 9.976295169466178e-05,
473
+ "loss": 0.0107,
474
+ "step": 55
475
+ },
476
+ {
477
+ "epoch": 0.6358381502890174,
478
+ "eval_loss": 0.012713148258626461,
479
+ "eval_runtime": 10.0087,
480
+ "eval_samples_per_second": 4.996,
481
+ "eval_steps_per_second": 1.299,
482
+ "step": 55
483
+ },
484
+ {
485
+ "epoch": 0.6473988439306358,
486
+ "grad_norm": 0.020468739792704582,
487
+ "learning_rate": 9.97218356731491e-05,
488
+ "loss": 0.0146,
489
+ "step": 56
490
+ },
491
+ {
492
+ "epoch": 0.6589595375722543,
493
+ "grad_norm": 0.01887972466647625,
494
+ "learning_rate": 9.967744305799357e-05,
495
+ "loss": 0.0126,
496
+ "step": 57
497
+ },
498
+ {
499
+ "epoch": 0.6705202312138728,
500
+ "grad_norm": 0.02040836587548256,
501
+ "learning_rate": 9.962977677460132e-05,
502
+ "loss": 0.0126,
503
+ "step": 58
504
+ },
505
+ {
506
+ "epoch": 0.6820809248554913,
507
+ "grad_norm": 0.02685651369392872,
508
+ "learning_rate": 9.957883996410821e-05,
509
+ "loss": 0.0122,
510
+ "step": 59
511
+ },
512
+ {
513
+ "epoch": 0.6936416184971098,
514
+ "grad_norm": 0.02112666517496109,
515
+ "learning_rate": 9.952463598317285e-05,
516
+ "loss": 0.016,
517
+ "step": 60
518
+ },
519
+ {
520
+ "epoch": 0.6936416184971098,
521
+ "eval_loss": 0.012294010259211063,
522
+ "eval_runtime": 10.0073,
523
+ "eval_samples_per_second": 4.996,
524
+ "eval_steps_per_second": 1.299,
525
+ "step": 60
526
+ },
527
+ {
528
+ "epoch": 0.7052023121387283,
529
+ "grad_norm": 0.020788514986634254,
530
+ "learning_rate": 9.946716840375551e-05,
531
+ "loss": 0.0106,
532
+ "step": 61
533
+ },
534
+ {
535
+ "epoch": 0.7167630057803468,
536
+ "grad_norm": 0.01940411888062954,
537
+ "learning_rate": 9.940644101288259e-05,
538
+ "loss": 0.0098,
539
+ "step": 62
540
+ },
541
+ {
542
+ "epoch": 0.7283236994219653,
543
+ "grad_norm": 0.02072029560804367,
544
+ "learning_rate": 9.934245781239714e-05,
545
+ "loss": 0.0142,
546
+ "step": 63
547
+ },
548
+ {
549
+ "epoch": 0.7398843930635838,
550
+ "grad_norm": 0.017221063375473022,
551
+ "learning_rate": 9.927522301869515e-05,
552
+ "loss": 0.0114,
553
+ "step": 64
554
+ },
555
+ {
556
+ "epoch": 0.7514450867052023,
557
+ "grad_norm": 0.026088256388902664,
558
+ "learning_rate": 9.920474106244763e-05,
559
+ "loss": 0.0144,
560
+ "step": 65
561
+ },
562
+ {
563
+ "epoch": 0.7514450867052023,
564
+ "eval_loss": 0.011602817103266716,
565
+ "eval_runtime": 10.0191,
566
+ "eval_samples_per_second": 4.99,
567
+ "eval_steps_per_second": 1.298,
568
+ "step": 65
569
+ },
570
+ {
571
+ "epoch": 0.7630057803468208,
572
+ "grad_norm": 0.016981270164251328,
573
+ "learning_rate": 9.91310165883088e-05,
574
+ "loss": 0.0136,
575
+ "step": 66
576
+ },
577
+ {
578
+ "epoch": 0.7745664739884393,
579
+ "grad_norm": 0.017894290387630463,
580
+ "learning_rate": 9.905405445460972e-05,
581
+ "loss": 0.0113,
582
+ "step": 67
583
+ },
584
+ {
585
+ "epoch": 0.7861271676300579,
586
+ "grad_norm": 0.017901500687003136,
587
+ "learning_rate": 9.897385973303845e-05,
588
+ "loss": 0.0133,
589
+ "step": 68
590
+ },
591
+ {
592
+ "epoch": 0.7976878612716763,
593
+ "grad_norm": 0.018053261563181877,
594
+ "learning_rate": 9.889043770830566e-05,
595
+ "loss": 0.0108,
596
+ "step": 69
597
+ },
598
+ {
599
+ "epoch": 0.8092485549132948,
600
+ "grad_norm": 0.023738127201795578,
601
+ "learning_rate": 9.880379387779637e-05,
602
+ "loss": 0.0119,
603
+ "step": 70
604
+ },
605
+ {
606
+ "epoch": 0.8092485549132948,
607
+ "eval_loss": 0.011262123472988605,
608
+ "eval_runtime": 10.0281,
609
+ "eval_samples_per_second": 4.986,
610
+ "eval_steps_per_second": 1.296,
611
+ "step": 70
612
+ },
613
+ {
614
+ "epoch": 0.8208092485549133,
615
+ "grad_norm": 0.01628166250884533,
616
+ "learning_rate": 9.871393395120774e-05,
617
+ "loss": 0.014,
618
+ "step": 71
619
+ },
620
+ {
621
+ "epoch": 0.8323699421965318,
622
+ "grad_norm": 0.014171602204442024,
623
+ "learning_rate": 9.862086385017283e-05,
624
+ "loss": 0.0099,
625
+ "step": 72
626
+ },
627
+ {
628
+ "epoch": 0.8439306358381503,
629
+ "grad_norm": 0.01973879709839821,
630
+ "learning_rate": 9.852458970787026e-05,
631
+ "loss": 0.011,
632
+ "step": 73
633
+ },
634
+ {
635
+ "epoch": 0.8554913294797688,
636
+ "grad_norm": 0.015728101134300232,
637
+ "learning_rate": 9.842511786862019e-05,
638
+ "loss": 0.01,
639
+ "step": 74
640
+ },
641
+ {
642
+ "epoch": 0.8670520231213873,
643
+ "grad_norm": 0.015097449533641338,
644
+ "learning_rate": 9.832245488746611e-05,
645
+ "loss": 0.0111,
646
+ "step": 75
647
+ },
648
+ {
649
+ "epoch": 0.8670520231213873,
650
+ "eval_loss": 0.010938560590147972,
651
+ "eval_runtime": 10.0124,
652
+ "eval_samples_per_second": 4.994,
653
+ "eval_steps_per_second": 1.298,
654
+ "step": 75
655
+ },
656
+ {
657
+ "epoch": 0.8786127167630058,
658
+ "grad_norm": 0.02237934060394764,
659
+ "learning_rate": 9.821660752974293e-05,
660
+ "loss": 0.0142,
661
+ "step": 76
662
+ },
663
+ {
664
+ "epoch": 0.8901734104046243,
665
+ "grad_norm": 0.01948779821395874,
666
+ "learning_rate": 9.810758277063119e-05,
667
+ "loss": 0.0138,
668
+ "step": 77
669
+ },
670
+ {
671
+ "epoch": 0.9017341040462428,
672
+ "grad_norm": 0.022487910464406013,
673
+ "learning_rate": 9.799538779469734e-05,
674
+ "loss": 0.0151,
675
+ "step": 78
676
+ },
677
+ {
678
+ "epoch": 0.9132947976878613,
679
+ "grad_norm": 0.017546942457556725,
680
+ "learning_rate": 9.78800299954203e-05,
681
+ "loss": 0.0098,
682
+ "step": 79
683
+ },
684
+ {
685
+ "epoch": 0.9248554913294798,
686
+ "grad_norm": 0.021010980010032654,
687
+ "learning_rate": 9.77615169747043e-05,
688
+ "loss": 0.012,
689
+ "step": 80
690
+ },
691
+ {
692
+ "epoch": 0.9248554913294798,
693
+ "eval_loss": 0.010658971033990383,
694
+ "eval_runtime": 10.0307,
695
+ "eval_samples_per_second": 4.985,
696
+ "eval_steps_per_second": 1.296,
697
+ "step": 80
698
+ },
699
+ {
700
+ "epoch": 0.9364161849710982,
701
+ "grad_norm": 0.018796751275658607,
702
+ "learning_rate": 9.763985654237786e-05,
703
+ "loss": 0.0126,
704
+ "step": 81
705
+ },
706
+ {
707
+ "epoch": 0.9479768786127167,
708
+ "grad_norm": 0.020107241347432137,
709
+ "learning_rate": 9.751505671567913e-05,
710
+ "loss": 0.0129,
711
+ "step": 82
712
+ },
713
+ {
714
+ "epoch": 0.9595375722543352,
715
+ "grad_norm": 0.015596112236380577,
716
+ "learning_rate": 9.738712571872763e-05,
717
+ "loss": 0.0093,
718
+ "step": 83
719
+ },
720
+ {
721
+ "epoch": 0.9710982658959537,
722
+ "grad_norm": 0.018946580588817596,
723
+ "learning_rate": 9.725607198198227e-05,
724
+ "loss": 0.0139,
725
+ "step": 84
726
+ },
727
+ {
728
+ "epoch": 0.9826589595375722,
729
+ "grad_norm": 0.01942116767168045,
730
+ "learning_rate": 9.712190414168572e-05,
731
+ "loss": 0.0139,
732
+ "step": 85
733
+ },
734
+ {
735
+ "epoch": 0.9826589595375722,
736
+ "eval_loss": 0.010201876051723957,
737
+ "eval_runtime": 10.0325,
738
+ "eval_samples_per_second": 4.984,
739
+ "eval_steps_per_second": 1.296,
740
+ "step": 85
741
+ },
742
+ {
743
+ "epoch": 0.9942196531791907,
744
+ "grad_norm": 0.01808648556470871,
745
+ "learning_rate": 9.698463103929542e-05,
746
+ "loss": 0.0096,
747
+ "step": 86
748
+ },
749
+ {
750
+ "epoch": 1.0057803468208093,
751
+ "grad_norm": 0.033104732632637024,
752
+ "learning_rate": 9.684426172090085e-05,
753
+ "loss": 0.0208,
754
+ "step": 87
755
+ },
756
+ {
757
+ "epoch": 1.0173410404624277,
758
+ "grad_norm": 0.011730443686246872,
759
+ "learning_rate": 9.67008054366274e-05,
760
+ "loss": 0.0079,
761
+ "step": 88
762
+ },
763
+ {
764
+ "epoch": 1.0289017341040463,
765
+ "grad_norm": 0.017196012660861015,
766
+ "learning_rate": 9.65542716400269e-05,
767
+ "loss": 0.0103,
768
+ "step": 89
769
+ },
770
+ {
771
+ "epoch": 1.0404624277456647,
772
+ "grad_norm": 0.015379775315523148,
773
+ "learning_rate": 9.640466998745456e-05,
774
+ "loss": 0.0085,
775
+ "step": 90
776
+ },
777
+ {
778
+ "epoch": 1.0404624277456647,
779
+ "eval_loss": 0.01041076984256506,
780
+ "eval_runtime": 10.0354,
781
+ "eval_samples_per_second": 4.982,
782
+ "eval_steps_per_second": 1.295,
783
+ "step": 90
784
+ },
785
+ {
786
+ "epoch": 1.0520231213872833,
787
+ "grad_norm": 0.01682409830391407,
788
+ "learning_rate": 9.625201033743261e-05,
789
+ "loss": 0.0102,
790
+ "step": 91
791
+ },
792
+ {
793
+ "epoch": 1.0635838150289016,
794
+ "grad_norm": 0.017098382115364075,
795
+ "learning_rate": 9.609630275000072e-05,
796
+ "loss": 0.0081,
797
+ "step": 92
798
+ },
799
+ {
800
+ "epoch": 1.0751445086705202,
801
+ "grad_norm": 0.017288707196712494,
802
+ "learning_rate": 9.5937557486053e-05,
803
+ "loss": 0.0094,
804
+ "step": 93
805
+ },
806
+ {
807
+ "epoch": 1.0867052023121386,
808
+ "grad_norm": 0.018024342134594917,
809
+ "learning_rate": 9.577578500666187e-05,
810
+ "loss": 0.0116,
811
+ "step": 94
812
+ },
813
+ {
814
+ "epoch": 1.0982658959537572,
815
+ "grad_norm": 0.017229463905096054,
816
+ "learning_rate": 9.56109959723886e-05,
817
+ "loss": 0.01,
818
+ "step": 95
819
+ },
820
+ {
821
+ "epoch": 1.0982658959537572,
822
+ "eval_loss": 0.010240535251796246,
823
+ "eval_runtime": 10.0835,
824
+ "eval_samples_per_second": 4.959,
825
+ "eval_steps_per_second": 1.289,
826
+ "step": 95
827
+ },
828
+ {
829
+ "epoch": 1.1098265895953756,
830
+ "grad_norm": 0.015899403020739555,
831
+ "learning_rate": 9.544320124258092e-05,
832
+ "loss": 0.0099,
833
+ "step": 96
834
+ },
835
+ {
836
+ "epoch": 1.1213872832369942,
837
+ "grad_norm": 0.019960559904575348,
838
+ "learning_rate": 9.527241187465734e-05,
839
+ "loss": 0.0098,
840
+ "step": 97
841
+ },
842
+ {
843
+ "epoch": 1.1329479768786128,
844
+ "grad_norm": 0.01425469946116209,
845
+ "learning_rate": 9.509863912337842e-05,
846
+ "loss": 0.0084,
847
+ "step": 98
848
+ },
849
+ {
850
+ "epoch": 1.1445086705202312,
851
+ "grad_norm": 0.015252132900059223,
852
+ "learning_rate": 9.492189444010521e-05,
853
+ "loss": 0.01,
854
+ "step": 99
855
+ },
856
+ {
857
+ "epoch": 1.1560693641618498,
858
+ "grad_norm": 0.014408037066459656,
859
+ "learning_rate": 9.474218947204459e-05,
860
+ "loss": 0.009,
861
+ "step": 100
862
+ },
863
+ {
864
+ "epoch": 1.1560693641618498,
865
+ "eval_loss": 0.009868398308753967,
866
+ "eval_runtime": 10.0137,
867
+ "eval_samples_per_second": 4.993,
868
+ "eval_steps_per_second": 1.298,
869
+ "step": 100
870
+ },
871
+ {
872
+ "epoch": 1.1676300578034682,
873
+ "grad_norm": 0.01568921096622944,
874
+ "learning_rate": 9.455953606148172e-05,
875
+ "loss": 0.0125,
876
+ "step": 101
877
+ },
878
+ {
879
+ "epoch": 1.1791907514450868,
880
+ "grad_norm": 0.01693912222981453,
881
+ "learning_rate": 9.437394624499958e-05,
882
+ "loss": 0.0116,
883
+ "step": 102
884
+ },
885
+ {
886
+ "epoch": 1.1907514450867052,
887
+ "grad_norm": 0.018201276659965515,
888
+ "learning_rate": 9.418543225268596e-05,
889
+ "loss": 0.0117,
890
+ "step": 103
891
+ },
892
+ {
893
+ "epoch": 1.2023121387283238,
894
+ "grad_norm": 0.015434252098202705,
895
+ "learning_rate": 9.399400650732735e-05,
896
+ "loss": 0.011,
897
+ "step": 104
898
+ },
899
+ {
900
+ "epoch": 1.2138728323699421,
901
+ "grad_norm": 0.01606677658855915,
902
+ "learning_rate": 9.379968162359034e-05,
903
+ "loss": 0.0094,
904
+ "step": 105
905
+ },
906
+ {
907
+ "epoch": 1.2138728323699421,
908
+ "eval_loss": 0.009825030341744423,
909
+ "eval_runtime": 10.0305,
910
+ "eval_samples_per_second": 4.985,
911
+ "eval_steps_per_second": 1.296,
912
+ "step": 105
913
+ },
914
+ {
915
+ "epoch": 1.2254335260115607,
916
+ "grad_norm": 0.015970559790730476,
917
+ "learning_rate": 9.360247040719039e-05,
918
+ "loss": 0.0079,
919
+ "step": 106
920
+ },
921
+ {
922
+ "epoch": 1.2369942196531791,
923
+ "grad_norm": 0.01553067285567522,
924
+ "learning_rate": 9.340238585404788e-05,
925
+ "loss": 0.0077,
926
+ "step": 107
927
+ },
928
+ {
929
+ "epoch": 1.2485549132947977,
930
+ "grad_norm": 0.017365023493766785,
931
+ "learning_rate": 9.319944114943171e-05,
932
+ "loss": 0.0089,
933
+ "step": 108
934
+ },
935
+ {
936
+ "epoch": 1.260115606936416,
937
+ "grad_norm": 0.01562884822487831,
938
+ "learning_rate": 9.29936496670905e-05,
939
+ "loss": 0.0076,
940
+ "step": 109
941
+ },
942
+ {
943
+ "epoch": 1.2716763005780347,
944
+ "grad_norm": 0.016722485423088074,
945
+ "learning_rate": 9.278502496837116e-05,
946
+ "loss": 0.0069,
947
+ "step": 110
948
+ },
949
+ {
950
+ "epoch": 1.2716763005780347,
951
+ "eval_loss": 0.009917480871081352,
952
+ "eval_runtime": 9.9972,
953
+ "eval_samples_per_second": 5.001,
954
+ "eval_steps_per_second": 1.3,
955
+ "step": 110
956
+ },
957
+ {
958
+ "epoch": 1.2832369942196533,
959
+ "grad_norm": 0.019191304221749306,
960
+ "learning_rate": 9.257358080132523e-05,
961
+ "loss": 0.0108,
962
+ "step": 111
963
+ },
964
+ {
965
+ "epoch": 1.2947976878612717,
966
+ "grad_norm": 0.02037121169269085,
967
+ "learning_rate": 9.235933109980301e-05,
968
+ "loss": 0.011,
969
+ "step": 112
970
+ },
971
+ {
972
+ "epoch": 1.30635838150289,
973
+ "grad_norm": 0.016349676996469498,
974
+ "learning_rate": 9.214228998253527e-05,
975
+ "loss": 0.0084,
976
+ "step": 113
977
+ },
978
+ {
979
+ "epoch": 1.3179190751445087,
980
+ "grad_norm": 0.01671903021633625,
981
+ "learning_rate": 9.192247175220276e-05,
982
+ "loss": 0.0087,
983
+ "step": 114
984
+ },
985
+ {
986
+ "epoch": 1.3294797687861273,
987
+ "grad_norm": 0.01710616424679756,
988
+ "learning_rate": 9.16998908944939e-05,
989
+ "loss": 0.0108,
990
+ "step": 115
991
+ },
992
+ {
993
+ "epoch": 1.3294797687861273,
994
+ "eval_loss": 0.009632885456085205,
995
+ "eval_runtime": 10.0191,
996
+ "eval_samples_per_second": 4.99,
997
+ "eval_steps_per_second": 1.298,
998
+ "step": 115
999
+ },
1000
+ {
1001
+ "epoch": 1.3410404624277457,
1002
+ "grad_norm": 0.01672513224184513,
1003
+ "learning_rate": 9.147456207714997e-05,
1004
+ "loss": 0.0077,
1005
+ "step": 116
1006
+ },
1007
+ {
1008
+ "epoch": 1.352601156069364,
1009
+ "grad_norm": 0.017153792083263397,
1010
+ "learning_rate": 9.124650014899867e-05,
1011
+ "loss": 0.0101,
1012
+ "step": 117
1013
+ },
1014
+ {
1015
+ "epoch": 1.3641618497109826,
1016
+ "grad_norm": 0.018158160150051117,
1017
+ "learning_rate": 9.101572013897555e-05,
1018
+ "loss": 0.0103,
1019
+ "step": 118
1020
+ },
1021
+ {
1022
+ "epoch": 1.3757225433526012,
1023
+ "grad_norm": 0.017670975998044014,
1024
+ "learning_rate": 9.078223725513366e-05,
1025
+ "loss": 0.0112,
1026
+ "step": 119
1027
+ },
1028
+ {
1029
+ "epoch": 1.3872832369942196,
1030
+ "grad_norm": 0.013258930295705795,
1031
+ "learning_rate": 9.05460668836413e-05,
1032
+ "loss": 0.0066,
1033
+ "step": 120
1034
+ },
1035
+ {
1036
+ "epoch": 1.3872832369942196,
1037
+ "eval_loss": 0.009479235857725143,
1038
+ "eval_runtime": 10.0092,
1039
+ "eval_samples_per_second": 4.995,
1040
+ "eval_steps_per_second": 1.299,
1041
+ "step": 120
1042
+ },
1043
+ {
1044
+ "epoch": 1.3988439306358382,
1045
+ "grad_norm": 0.016367750242352486,
1046
+ "learning_rate": 9.030722458776814e-05,
1047
+ "loss": 0.0083,
1048
+ "step": 121
1049
+ },
1050
+ {
1051
+ "epoch": 1.4104046242774566,
1052
+ "grad_norm": 0.01966327428817749,
1053
+ "learning_rate": 9.006572610685968e-05,
1054
+ "loss": 0.013,
1055
+ "step": 122
1056
+ },
1057
+ {
1058
+ "epoch": 1.4219653179190752,
1059
+ "grad_norm": 0.014227735809981823,
1060
+ "learning_rate": 8.98215873552999e-05,
1061
+ "loss": 0.0081,
1062
+ "step": 123
1063
+ },
1064
+ {
1065
+ "epoch": 1.4335260115606936,
1066
+ "grad_norm": 0.0126969488337636,
1067
+ "learning_rate": 8.957482442146272e-05,
1068
+ "loss": 0.0069,
1069
+ "step": 124
1070
+ },
1071
+ {
1072
+ "epoch": 1.4450867052023122,
1073
+ "grad_norm": 0.0182335264980793,
1074
+ "learning_rate": 8.932545356665157e-05,
1075
+ "loss": 0.0089,
1076
+ "step": 125
1077
+ },
1078
+ {
1079
+ "epoch": 1.4450867052023122,
1080
+ "eval_loss": 0.009439178742468357,
1081
+ "eval_runtime": 10.0231,
1082
+ "eval_samples_per_second": 4.988,
1083
+ "eval_steps_per_second": 1.297,
1084
+ "step": 125
1085
+ },
1086
+ {
1087
+ "epoch": 1.4566473988439306,
1088
+ "grad_norm": 0.013425913639366627,
1089
+ "learning_rate": 8.907349122402801e-05,
1090
+ "loss": 0.0064,
1091
+ "step": 126
1092
+ },
1093
+ {
1094
+ "epoch": 1.4682080924855492,
1095
+ "grad_norm": 0.017706867307424545,
1096
+ "learning_rate": 8.881895399752874e-05,
1097
+ "loss": 0.0085,
1098
+ "step": 127
1099
+ },
1100
+ {
1101
+ "epoch": 1.4797687861271676,
1102
+ "grad_norm": 0.015954311937093735,
1103
+ "learning_rate": 8.856185866077129e-05,
1104
+ "loss": 0.0091,
1105
+ "step": 128
1106
+ },
1107
+ {
1108
+ "epoch": 1.4913294797687862,
1109
+ "grad_norm": 0.01800154522061348,
1110
+ "learning_rate": 8.83022221559489e-05,
1111
+ "loss": 0.0118,
1112
+ "step": 129
1113
+ },
1114
+ {
1115
+ "epoch": 1.5028901734104045,
1116
+ "grad_norm": 0.022386785596609116,
1117
+ "learning_rate": 8.80400615927139e-05,
1118
+ "loss": 0.0084,
1119
+ "step": 130
1120
+ },
1121
+ {
1122
+ "epoch": 1.5028901734104045,
1123
+ "eval_loss": 0.009285805746912956,
1124
+ "eval_runtime": 10.0195,
1125
+ "eval_samples_per_second": 4.99,
1126
+ "eval_steps_per_second": 1.297,
1127
+ "step": 130
1128
+ },
1129
+ {
1130
+ "epoch": 1.5144508670520231,
1131
+ "grad_norm": 0.015237067826092243,
1132
+ "learning_rate": 8.777539424705023e-05,
1133
+ "loss": 0.0067,
1134
+ "step": 131
1135
+ },
1136
+ {
1137
+ "epoch": 1.5260115606936417,
1138
+ "grad_norm": 0.01740083284676075,
1139
+ "learning_rate": 8.750823756013498e-05,
1140
+ "loss": 0.0111,
1141
+ "step": 132
1142
+ },
1143
+ {
1144
+ "epoch": 1.5375722543352601,
1145
+ "grad_norm": 0.01614670269191265,
1146
+ "learning_rate": 8.72386091371891e-05,
1147
+ "loss": 0.0066,
1148
+ "step": 133
1149
+ },
1150
+ {
1151
+ "epoch": 1.5491329479768785,
1152
+ "grad_norm": 0.018181053921580315,
1153
+ "learning_rate": 8.696652674631717e-05,
1154
+ "loss": 0.0089,
1155
+ "step": 134
1156
+ },
1157
+ {
1158
+ "epoch": 1.560693641618497,
1159
+ "grad_norm": 0.01898285746574402,
1160
+ "learning_rate": 8.669200831733655e-05,
1161
+ "loss": 0.0102,
1162
+ "step": 135
1163
+ },
1164
+ {
1165
+ "epoch": 1.560693641618497,
1166
+ "eval_loss": 0.00925290398299694,
1167
+ "eval_runtime": 10.0096,
1168
+ "eval_samples_per_second": 4.995,
1169
+ "eval_steps_per_second": 1.299,
1170
+ "step": 135
1171
+ },
1172
+ {
1173
+ "epoch": 1.5722543352601157,
1174
+ "grad_norm": 0.01583796739578247,
1175
+ "learning_rate": 8.641507194059579e-05,
1176
+ "loss": 0.0084,
1177
+ "step": 136
1178
+ },
1179
+ {
1180
+ "epoch": 1.583815028901734,
1181
+ "grad_norm": 0.020259637385606766,
1182
+ "learning_rate": 8.613573586578262e-05,
1183
+ "loss": 0.0097,
1184
+ "step": 137
1185
+ },
1186
+ {
1187
+ "epoch": 1.5953757225433525,
1188
+ "grad_norm": 0.0170609038323164,
1189
+ "learning_rate": 8.585401850072113e-05,
1190
+ "loss": 0.0102,
1191
+ "step": 138
1192
+ },
1193
+ {
1194
+ "epoch": 1.606936416184971,
1195
+ "grad_norm": 0.013348150067031384,
1196
+ "learning_rate": 8.55699384101589e-05,
1197
+ "loss": 0.0076,
1198
+ "step": 139
1199
+ },
1200
+ {
1201
+ "epoch": 1.6184971098265897,
1202
+ "grad_norm": 0.0179379191249609,
1203
+ "learning_rate": 8.528351431454351e-05,
1204
+ "loss": 0.01,
1205
+ "step": 140
1206
+ },
1207
+ {
1208
+ "epoch": 1.6184971098265897,
1209
+ "eval_loss": 0.009090203791856766,
1210
+ "eval_runtime": 10.0116,
1211
+ "eval_samples_per_second": 4.994,
1212
+ "eval_steps_per_second": 1.298,
1213
+ "step": 140
1214
+ },
1215
+ {
1216
+ "epoch": 1.630057803468208,
1217
+ "grad_norm": 0.014754540286958218,
1218
+ "learning_rate": 8.499476508878893e-05,
1219
+ "loss": 0.0091,
1220
+ "step": 141
1221
+ },
1222
+ {
1223
+ "epoch": 1.6416184971098264,
1224
+ "grad_norm": 0.014680921100080013,
1225
+ "learning_rate": 8.47037097610317e-05,
1226
+ "loss": 0.008,
1227
+ "step": 142
1228
+ },
1229
+ {
1230
+ "epoch": 1.653179190751445,
1231
+ "grad_norm": 0.01806177943944931,
1232
+ "learning_rate": 8.441036751137696e-05,
1233
+ "loss": 0.0122,
1234
+ "step": 143
1235
+ },
1236
+ {
1237
+ "epoch": 1.6647398843930636,
1238
+ "grad_norm": 0.014901218004524708,
1239
+ "learning_rate": 8.411475767063455e-05,
1240
+ "loss": 0.0075,
1241
+ "step": 144
1242
+ },
1243
+ {
1244
+ "epoch": 1.6763005780346822,
1245
+ "grad_norm": 0.01642463356256485,
1246
+ "learning_rate": 8.381689971904514e-05,
1247
+ "loss": 0.0098,
1248
+ "step": 145
1249
+ },
1250
+ {
1251
+ "epoch": 1.6763005780346822,
1252
+ "eval_loss": 0.008807710371911526,
1253
+ "eval_runtime": 10.0289,
1254
+ "eval_samples_per_second": 4.986,
1255
+ "eval_steps_per_second": 1.296,
1256
+ "step": 145
1257
+ },
1258
+ {
1259
+ "epoch": 1.6878612716763006,
1260
+ "grad_norm": 0.0145337525755167,
1261
+ "learning_rate": 8.35168132849965e-05,
1262
+ "loss": 0.0074,
1263
+ "step": 146
1264
+ },
1265
+ {
1266
+ "epoch": 1.699421965317919,
1267
+ "grad_norm": 0.019870057702064514,
1268
+ "learning_rate": 8.321451814372997e-05,
1269
+ "loss": 0.0111,
1270
+ "step": 147
1271
+ },
1272
+ {
1273
+ "epoch": 1.7109826589595376,
1274
+ "grad_norm": 0.015163514763116837,
1275
+ "learning_rate": 8.29100342160374e-05,
1276
+ "loss": 0.0097,
1277
+ "step": 148
1278
+ },
1279
+ {
1280
+ "epoch": 1.7225433526011562,
1281
+ "grad_norm": 0.01458723470568657,
1282
+ "learning_rate": 8.260338156694836e-05,
1283
+ "loss": 0.007,
1284
+ "step": 149
1285
+ },
1286
+ {
1287
+ "epoch": 1.7341040462427746,
1288
+ "grad_norm": 0.015452525578439236,
1289
+ "learning_rate": 8.229458040440783e-05,
1290
+ "loss": 0.0071,
1291
+ "step": 150
1292
+ },
1293
+ {
1294
+ "epoch": 1.7341040462427746,
1295
+ "eval_loss": 0.008663667365908623,
1296
+ "eval_runtime": 10.0348,
1297
+ "eval_samples_per_second": 4.983,
1298
+ "eval_steps_per_second": 1.295,
1299
+ "step": 150
1300
+ },
1301
+ {
1302
+ "epoch": 1.745664739884393,
1303
+ "grad_norm": 0.017789160832762718,
1304
+ "learning_rate": 8.198365107794457e-05,
1305
+ "loss": 0.0098,
1306
+ "step": 151
1307
+ },
1308
+ {
1309
+ "epoch": 1.7572254335260116,
1310
+ "grad_norm": 0.019878627732396126,
1311
+ "learning_rate": 8.167061407733016e-05,
1312
+ "loss": 0.0077,
1313
+ "step": 152
1314
+ },
1315
+ {
1316
+ "epoch": 1.7687861271676302,
1317
+ "grad_norm": 0.018271176144480705,
1318
+ "learning_rate": 8.135549003122871e-05,
1319
+ "loss": 0.0096,
1320
+ "step": 153
1321
+ },
1322
+ {
1323
+ "epoch": 1.7803468208092486,
1324
+ "grad_norm": 0.017175493761897087,
1325
+ "learning_rate": 8.103829970583742e-05,
1326
+ "loss": 0.0111,
1327
+ "step": 154
1328
+ },
1329
+ {
1330
+ "epoch": 1.791907514450867,
1331
+ "grad_norm": 0.014682111330330372,
1332
+ "learning_rate": 8.071906400351822e-05,
1333
+ "loss": 0.0094,
1334
+ "step": 155
1335
+ },
1336
+ {
1337
+ "epoch": 1.791907514450867,
1338
+ "eval_loss": 0.008556585758924484,
1339
+ "eval_runtime": 10.0386,
1340
+ "eval_samples_per_second": 4.981,
1341
+ "eval_steps_per_second": 1.295,
1342
+ "step": 155
1343
+ },
1344
+ {
1345
+ "epoch": 1.8034682080924855,
1346
+ "grad_norm": 0.016677409410476685,
1347
+ "learning_rate": 8.039780396142022e-05,
1348
+ "loss": 0.0079,
1349
+ "step": 156
1350
+ },
1351
+ {
1352
+ "epoch": 1.8150289017341041,
1353
+ "grad_norm": 0.01885165646672249,
1354
+ "learning_rate": 8.007454075009351e-05,
1355
+ "loss": 0.0115,
1356
+ "step": 157
1357
+ },
1358
+ {
1359
+ "epoch": 1.8265895953757225,
1360
+ "grad_norm": 0.01522767636924982,
1361
+ "learning_rate": 7.9749295672094e-05,
1362
+ "loss": 0.0076,
1363
+ "step": 158
1364
+ },
1365
+ {
1366
+ "epoch": 1.838150289017341,
1367
+ "grad_norm": 0.01811189390718937,
1368
+ "learning_rate": 7.942209016057954e-05,
1369
+ "loss": 0.01,
1370
+ "step": 159
1371
+ },
1372
+ {
1373
+ "epoch": 1.8497109826589595,
1374
+ "grad_norm": 0.01717502437531948,
1375
+ "learning_rate": 7.909294577789766e-05,
1376
+ "loss": 0.008,
1377
+ "step": 160
1378
+ },
1379
+ {
1380
+ "epoch": 1.8497109826589595,
1381
+ "eval_loss": 0.008559009060263634,
1382
+ "eval_runtime": 10.0652,
1383
+ "eval_samples_per_second": 4.968,
1384
+ "eval_steps_per_second": 1.292,
1385
+ "step": 160
1386
+ },
1387
+ {
1388
+ "epoch": 1.861271676300578,
1389
+ "grad_norm": 0.015464117750525475,
1390
+ "learning_rate": 7.876188421416449e-05,
1391
+ "loss": 0.0068,
1392
+ "step": 161
1393
+ },
1394
+ {
1395
+ "epoch": 1.8728323699421965,
1396
+ "grad_norm": 0.015217979438602924,
1397
+ "learning_rate": 7.842892728583558e-05,
1398
+ "loss": 0.0074,
1399
+ "step": 162
1400
+ },
1401
+ {
1402
+ "epoch": 1.8843930635838149,
1403
+ "grad_norm": 0.01554564293473959,
1404
+ "learning_rate": 7.809409693426803e-05,
1405
+ "loss": 0.0071,
1406
+ "step": 163
1407
+ },
1408
+ {
1409
+ "epoch": 1.8959537572254335,
1410
+ "grad_norm": 0.01914595626294613,
1411
+ "learning_rate": 7.775741522427477e-05,
1412
+ "loss": 0.009,
1413
+ "step": 164
1414
+ },
1415
+ {
1416
+ "epoch": 1.907514450867052,
1417
+ "grad_norm": 0.01934712752699852,
1418
+ "learning_rate": 7.741890434267043e-05,
1419
+ "loss": 0.01,
1420
+ "step": 165
1421
+ },
1422
+ {
1423
+ "epoch": 1.907514450867052,
1424
+ "eval_loss": 0.00854802131652832,
1425
+ "eval_runtime": 10.0226,
1426
+ "eval_samples_per_second": 4.989,
1427
+ "eval_steps_per_second": 1.297,
1428
+ "step": 165
1429
+ },
1430
+ {
1431
+ "epoch": 1.9190751445086707,
1432
+ "grad_norm": 0.01625540666282177,
1433
+ "learning_rate": 7.707858659680924e-05,
1434
+ "loss": 0.0071,
1435
+ "step": 166
1436
+ },
1437
+ {
1438
+ "epoch": 1.930635838150289,
1439
+ "grad_norm": 0.020419662818312645,
1440
+ "learning_rate": 7.673648441311508e-05,
1441
+ "loss": 0.0076,
1442
+ "step": 167
1443
+ },
1444
+ {
1445
+ "epoch": 1.9421965317919074,
1446
+ "grad_norm": 0.012187760323286057,
1447
+ "learning_rate": 7.639262033560359e-05,
1448
+ "loss": 0.0064,
1449
+ "step": 168
1450
+ },
1451
+ {
1452
+ "epoch": 1.953757225433526,
1453
+ "grad_norm": 0.015659835189580917,
1454
+ "learning_rate": 7.604701702439651e-05,
1455
+ "loss": 0.0074,
1456
+ "step": 169
1457
+ },
1458
+ {
1459
+ "epoch": 1.9653179190751446,
1460
+ "grad_norm": 0.017916489392518997,
1461
+ "learning_rate": 7.56996972542285e-05,
1462
+ "loss": 0.0084,
1463
+ "step": 170
1464
+ },
1465
+ {
1466
+ "epoch": 1.9653179190751446,
1467
+ "eval_loss": 0.008561979979276657,
1468
+ "eval_runtime": 10.0323,
1469
+ "eval_samples_per_second": 4.984,
1470
+ "eval_steps_per_second": 1.296,
1471
+ "step": 170
1472
+ },
1473
+ {
1474
+ "epoch": 1.976878612716763,
1475
+ "grad_norm": 0.018545281141996384,
1476
+ "learning_rate": 7.535068391294617e-05,
1477
+ "loss": 0.0102,
1478
+ "step": 171
1479
+ },
1480
+ {
1481
+ "epoch": 1.9884393063583814,
1482
+ "grad_norm": 0.01769687980413437,
1483
+ "learning_rate": 7.500000000000001e-05,
1484
+ "loss": 0.0086,
1485
+ "step": 172
1486
+ },
1487
+ {
1488
+ "epoch": 2.0,
1489
+ "grad_norm": 0.021417992189526558,
1490
+ "learning_rate": 7.464766862492855e-05,
1491
+ "loss": 0.0092,
1492
+ "step": 173
1493
+ },
1494
+ {
1495
+ "epoch": 2.0115606936416186,
1496
+ "grad_norm": 0.01275323610752821,
1497
+ "learning_rate": 7.42937130058357e-05,
1498
+ "loss": 0.0069,
1499
+ "step": 174
1500
+ },
1501
+ {
1502
+ "epoch": 2.023121387283237,
1503
+ "grad_norm": 0.011270470917224884,
1504
+ "learning_rate": 7.393815646786046e-05,
1505
+ "loss": 0.0058,
1506
+ "step": 175
1507
+ },
1508
+ {
1509
+ "epoch": 2.023121387283237,
1510
+ "eval_loss": 0.008691162802278996,
1511
+ "eval_runtime": 10.0831,
1512
+ "eval_samples_per_second": 4.959,
1513
+ "eval_steps_per_second": 1.289,
1514
+ "step": 175
1515
+ },
1516
+ {
1517
+ "epoch": 2.0346820809248554,
1518
+ "grad_norm": 0.014580226503312588,
1519
+ "learning_rate": 7.358102244164003e-05,
1520
+ "loss": 0.0077,
1521
+ "step": 176
1522
+ },
1523
+ {
1524
+ "epoch": 2.046242774566474,
1525
+ "grad_norm": 0.014212528243660927,
1526
+ "learning_rate": 7.322233446176571e-05,
1527
+ "loss": 0.0074,
1528
+ "step": 177
1529
+ },
1530
+ {
1531
+ "epoch": 2.0578034682080926,
1532
+ "grad_norm": 0.01766706444323063,
1533
+ "learning_rate": 7.286211616523193e-05,
1534
+ "loss": 0.007,
1535
+ "step": 178
1536
+ },
1537
+ {
1538
+ "epoch": 2.069364161849711,
1539
+ "grad_norm": 0.015258056111633778,
1540
+ "learning_rate": 7.250039128987873e-05,
1541
+ "loss": 0.0073,
1542
+ "step": 179
1543
+ },
1544
+ {
1545
+ "epoch": 2.0809248554913293,
1546
+ "grad_norm": 0.01634743995964527,
1547
+ "learning_rate": 7.213718367282737e-05,
1548
+ "loss": 0.0056,
1549
+ "step": 180
1550
+ },
1551
+ {
1552
+ "epoch": 2.0809248554913293,
1553
+ "eval_loss": 0.008958614431321621,
1554
+ "eval_runtime": 10.0215,
1555
+ "eval_samples_per_second": 4.989,
1556
+ "eval_steps_per_second": 1.297,
1557
+ "step": 180
1558
+ },
1559
+ {
1560
+ "epoch": 2.092485549132948,
1561
+ "grad_norm": 0.014233705587685108,
1562
+ "learning_rate": 7.177251724890956e-05,
1563
+ "loss": 0.0056,
1564
+ "step": 181
1565
+ },
1566
+ {
1567
+ "epoch": 2.1040462427745665,
1568
+ "grad_norm": 0.013312169350683689,
1569
+ "learning_rate": 7.14064160490902e-05,
1570
+ "loss": 0.0055,
1571
+ "step": 182
1572
+ },
1573
+ {
1574
+ "epoch": 2.115606936416185,
1575
+ "grad_norm": 0.012955575250089169,
1576
+ "learning_rate": 7.103890419888367e-05,
1577
+ "loss": 0.0053,
1578
+ "step": 183
1579
+ },
1580
+ {
1581
+ "epoch": 2.1271676300578033,
1582
+ "grad_norm": 0.018879901617765427,
1583
+ "learning_rate": 7.067000591676416e-05,
1584
+ "loss": 0.0065,
1585
+ "step": 184
1586
+ },
1587
+ {
1588
+ "epoch": 2.138728323699422,
1589
+ "grad_norm": 0.01857951283454895,
1590
+ "learning_rate": 7.029974551256956e-05,
1591
+ "loss": 0.0077,
1592
+ "step": 185
1593
+ },
1594
+ {
1595
+ "epoch": 2.138728323699422,
1596
+ "eval_loss": 0.008626853115856647,
1597
+ "eval_runtime": 10.0278,
1598
+ "eval_samples_per_second": 4.986,
1599
+ "eval_steps_per_second": 1.296,
1600
+ "step": 185
1601
+ },
1602
+ {
1603
+ "epoch": 2.1502890173410405,
1604
+ "grad_norm": 0.015720047056674957,
1605
+ "learning_rate": 6.992814738589957e-05,
1606
+ "loss": 0.0057,
1607
+ "step": 186
1608
+ },
1609
+ {
1610
+ "epoch": 2.161849710982659,
1611
+ "grad_norm": 0.016932690516114235,
1612
+ "learning_rate": 6.95552360245078e-05,
1613
+ "loss": 0.0074,
1614
+ "step": 187
1615
+ },
1616
+ {
1617
+ "epoch": 2.1734104046242773,
1618
+ "grad_norm": 0.013904884457588196,
1619
+ "learning_rate": 6.918103600268799e-05,
1620
+ "loss": 0.0054,
1621
+ "step": 188
1622
+ },
1623
+ {
1624
+ "epoch": 2.184971098265896,
1625
+ "grad_norm": 0.015230257995426655,
1626
+ "learning_rate": 6.880557197965464e-05,
1627
+ "loss": 0.0053,
1628
+ "step": 189
1629
+ },
1630
+ {
1631
+ "epoch": 2.1965317919075145,
1632
+ "grad_norm": 0.017044221982359886,
1633
+ "learning_rate": 6.842886869791809e-05,
1634
+ "loss": 0.0061,
1635
+ "step": 190
1636
+ },
1637
+ {
1638
+ "epoch": 2.1965317919075145,
1639
+ "eval_loss": 0.00858032051473856,
1640
+ "eval_runtime": 10.0219,
1641
+ "eval_samples_per_second": 4.989,
1642
+ "eval_steps_per_second": 1.297,
1643
+ "step": 190
1644
+ },
1645
+ {
1646
+ "epoch": 2.208092485549133,
1647
+ "grad_norm": 0.01593642681837082,
1648
+ "learning_rate": 6.805095098165389e-05,
1649
+ "loss": 0.0056,
1650
+ "step": 191
1651
+ },
1652
+ {
1653
+ "epoch": 2.2196531791907512,
1654
+ "grad_norm": 0.018296780064702034,
1655
+ "learning_rate": 6.767184373506697e-05,
1656
+ "loss": 0.008,
1657
+ "step": 192
1658
+ },
1659
+ {
1660
+ "epoch": 2.23121387283237,
1661
+ "grad_norm": 0.02369534969329834,
1662
+ "learning_rate": 6.729157194075057e-05,
1663
+ "loss": 0.0116,
1664
+ "step": 193
1665
+ },
1666
+ {
1667
+ "epoch": 2.2427745664739884,
1668
+ "grad_norm": 0.020556915551424026,
1669
+ "learning_rate": 6.691016065803983e-05,
1670
+ "loss": 0.0078,
1671
+ "step": 194
1672
+ },
1673
+ {
1674
+ "epoch": 2.254335260115607,
1675
+ "grad_norm": 0.01714545115828514,
1676
+ "learning_rate": 6.652763502136043e-05,
1677
+ "loss": 0.008,
1678
+ "step": 195
1679
+ },
1680
+ {
1681
+ "epoch": 2.254335260115607,
1682
+ "eval_loss": 0.008329370059072971,
1683
+ "eval_runtime": 10.0304,
1684
+ "eval_samples_per_second": 4.985,
1685
+ "eval_steps_per_second": 1.296,
1686
+ "step": 195
1687
+ },
1688
+ {
1689
+ "epoch": 2.2658959537572256,
1690
+ "grad_norm": 0.013920610770583153,
1691
+ "learning_rate": 6.614402023857232e-05,
1692
+ "loss": 0.0057,
1693
+ "step": 196
1694
+ },
1695
+ {
1696
+ "epoch": 2.277456647398844,
1697
+ "grad_norm": 0.014315689913928509,
1698
+ "learning_rate": 6.57593415893085e-05,
1699
+ "loss": 0.0062,
1700
+ "step": 197
1701
+ },
1702
+ {
1703
+ "epoch": 2.2890173410404624,
1704
+ "grad_norm": 0.01451371144503355,
1705
+ "learning_rate": 6.537362442330916e-05,
1706
+ "loss": 0.0059,
1707
+ "step": 198
1708
+ },
1709
+ {
1710
+ "epoch": 2.300578034682081,
1711
+ "grad_norm": 0.013728981837630272,
1712
+ "learning_rate": 6.498689415875121e-05,
1713
+ "loss": 0.0054,
1714
+ "step": 199
1715
+ },
1716
+ {
1717
+ "epoch": 2.3121387283236996,
1718
+ "grad_norm": 0.01417378056794405,
1719
+ "learning_rate": 6.45991762805732e-05,
1720
+ "loss": 0.0058,
1721
+ "step": 200
1722
+ },
1723
+ {
1724
+ "epoch": 2.3121387283236996,
1725
+ "eval_loss": 0.00831348542124033,
1726
+ "eval_runtime": 10.0504,
1727
+ "eval_samples_per_second": 4.975,
1728
+ "eval_steps_per_second": 1.293,
1729
+ "step": 200
1730
+ },
1731
+ {
1732
+ "epoch": 2.3236994219653178,
1733
+ "grad_norm": 0.013795462436974049,
1734
+ "learning_rate": 6.421049633879588e-05,
1735
+ "loss": 0.005,
1736
+ "step": 201
1737
+ },
1738
+ {
1739
+ "epoch": 2.3352601156069364,
1740
+ "grad_norm": 0.01878678984940052,
1741
+ "learning_rate": 6.382087994683859e-05,
1742
+ "loss": 0.0075,
1743
+ "step": 202
1744
+ },
1745
+ {
1746
+ "epoch": 2.346820809248555,
1747
+ "grad_norm": 0.01882004365324974,
1748
+ "learning_rate": 6.343035277983127e-05,
1749
+ "loss": 0.0068,
1750
+ "step": 203
1751
+ },
1752
+ {
1753
+ "epoch": 2.3583815028901736,
1754
+ "grad_norm": 0.015659485012292862,
1755
+ "learning_rate": 6.303894057292261e-05,
1756
+ "loss": 0.006,
1757
+ "step": 204
1758
+ },
1759
+ {
1760
+ "epoch": 2.3699421965317917,
1761
+ "grad_norm": 0.015219546854496002,
1762
+ "learning_rate": 6.264666911958404e-05,
1763
+ "loss": 0.0047,
1764
+ "step": 205
1765
+ },
1766
+ {
1767
+ "epoch": 2.3699421965317917,
1768
+ "eval_loss": 0.00836299266666174,
1769
+ "eval_runtime": 10.0293,
1770
+ "eval_samples_per_second": 4.985,
1771
+ "eval_steps_per_second": 1.296,
1772
+ "step": 205
1773
+ },
1774
+ {
1775
+ "epoch": 2.3815028901734103,
1776
+ "grad_norm": 0.017362525686621666,
1777
+ "learning_rate": 6.225356426991007e-05,
1778
+ "loss": 0.0069,
1779
+ "step": 206
1780
+ },
1781
+ {
1782
+ "epoch": 2.393063583815029,
1783
+ "grad_norm": 0.014902186580002308,
1784
+ "learning_rate": 6.185965192891472e-05,
1785
+ "loss": 0.0055,
1786
+ "step": 207
1787
+ },
1788
+ {
1789
+ "epoch": 2.4046242774566475,
1790
+ "grad_norm": 0.016910729929804802,
1791
+ "learning_rate": 6.146495805482451e-05,
1792
+ "loss": 0.0062,
1793
+ "step": 208
1794
+ },
1795
+ {
1796
+ "epoch": 2.416184971098266,
1797
+ "grad_norm": 0.014512901194393635,
1798
+ "learning_rate": 6.106950865736777e-05,
1799
+ "loss": 0.0052,
1800
+ "step": 209
1801
+ },
1802
+ {
1803
+ "epoch": 2.4277456647398843,
1804
+ "grad_norm": 0.017721183598041534,
1805
+ "learning_rate": 6.0673329796060686e-05,
1806
+ "loss": 0.0066,
1807
+ "step": 210
1808
+ },
1809
+ {
1810
+ "epoch": 2.4277456647398843,
1811
+ "eval_loss": 0.008446984924376011,
1812
+ "eval_runtime": 10.0239,
1813
+ "eval_samples_per_second": 4.988,
1814
+ "eval_steps_per_second": 1.297,
1815
+ "step": 210
1816
+ },
1817
+ {
1818
+ "epoch": 2.439306358381503,
1819
+ "grad_norm": 0.01806679181754589,
1820
+ "learning_rate": 6.0276447578490035e-05,
1821
+ "loss": 0.0063,
1822
+ "step": 211
1823
+ },
1824
+ {
1825
+ "epoch": 2.4508670520231215,
1826
+ "grad_norm": 0.01761380210518837,
1827
+ "learning_rate": 5.987888815859266e-05,
1828
+ "loss": 0.0058,
1829
+ "step": 212
1830
+ },
1831
+ {
1832
+ "epoch": 2.4624277456647397,
1833
+ "grad_norm": 0.015691956505179405,
1834
+ "learning_rate": 5.9480677734932045e-05,
1835
+ "loss": 0.0057,
1836
+ "step": 213
1837
+ },
1838
+ {
1839
+ "epoch": 2.4739884393063583,
1840
+ "grad_norm": 0.016050070524215698,
1841
+ "learning_rate": 5.908184254897182e-05,
1842
+ "loss": 0.0073,
1843
+ "step": 214
1844
+ },
1845
+ {
1846
+ "epoch": 2.485549132947977,
1847
+ "grad_norm": 0.013452823273837566,
1848
+ "learning_rate": 5.868240888334653e-05,
1849
+ "loss": 0.0055,
1850
+ "step": 215
1851
+ },
1852
+ {
1853
+ "epoch": 2.485549132947977,
1854
+ "eval_loss": 0.008248448371887207,
1855
+ "eval_runtime": 10.0544,
1856
+ "eval_samples_per_second": 4.973,
1857
+ "eval_steps_per_second": 1.293,
1858
+ "step": 215
1859
+ },
1860
+ {
1861
+ "epoch": 2.4971098265895955,
1862
+ "grad_norm": 0.013310995884239674,
1863
+ "learning_rate": 5.8282403060129566e-05,
1864
+ "loss": 0.0064,
1865
+ "step": 216
1866
+ },
1867
+ {
1868
+ "epoch": 2.508670520231214,
1869
+ "grad_norm": 0.016307106241583824,
1870
+ "learning_rate": 5.788185143909868e-05,
1871
+ "loss": 0.006,
1872
+ "step": 217
1873
+ },
1874
+ {
1875
+ "epoch": 2.520231213872832,
1876
+ "grad_norm": 0.014403578825294971,
1877
+ "learning_rate": 5.7480780415998906e-05,
1878
+ "loss": 0.0053,
1879
+ "step": 218
1880
+ },
1881
+ {
1882
+ "epoch": 2.531791907514451,
1883
+ "grad_norm": 0.015278173610568047,
1884
+ "learning_rate": 5.707921642080299e-05,
1885
+ "loss": 0.0067,
1886
+ "step": 219
1887
+ },
1888
+ {
1889
+ "epoch": 2.5433526011560694,
1890
+ "grad_norm": 0.01573382504284382,
1891
+ "learning_rate": 5.66771859159699e-05,
1892
+ "loss": 0.0056,
1893
+ "step": 220
1894
+ },
1895
+ {
1896
+ "epoch": 2.5433526011560694,
1897
+ "eval_loss": 0.008289137855172157,
1898
+ "eval_runtime": 10.0106,
1899
+ "eval_samples_per_second": 4.995,
1900
+ "eval_steps_per_second": 1.299,
1901
+ "step": 220
1902
+ },
1903
+ {
1904
+ "epoch": 2.5549132947976876,
1905
+ "grad_norm": 0.014673051424324512,
1906
+ "learning_rate": 5.6274715394700805e-05,
1907
+ "loss": 0.0057,
1908
+ "step": 221
1909
+ },
1910
+ {
1911
+ "epoch": 2.5664739884393066,
1912
+ "grad_norm": 0.017399994656443596,
1913
+ "learning_rate": 5.587183137919332e-05,
1914
+ "loss": 0.0066,
1915
+ "step": 222
1916
+ },
1917
+ {
1918
+ "epoch": 2.578034682080925,
1919
+ "grad_norm": 0.015570064075291157,
1920
+ "learning_rate": 5.546856041889373e-05,
1921
+ "loss": 0.0062,
1922
+ "step": 223
1923
+ },
1924
+ {
1925
+ "epoch": 2.5895953757225434,
1926
+ "grad_norm": 0.012873631902039051,
1927
+ "learning_rate": 5.5064929088747316e-05,
1928
+ "loss": 0.0048,
1929
+ "step": 224
1930
+ },
1931
+ {
1932
+ "epoch": 2.601156069364162,
1933
+ "grad_norm": 0.01452395599335432,
1934
+ "learning_rate": 5.46609639874473e-05,
1935
+ "loss": 0.005,
1936
+ "step": 225
1937
+ },
1938
+ {
1939
+ "epoch": 2.601156069364162,
1940
+ "eval_loss": 0.008248119615018368,
1941
+ "eval_runtime": 10.0518,
1942
+ "eval_samples_per_second": 4.974,
1943
+ "eval_steps_per_second": 1.293,
1944
+ "step": 225
1945
+ },
1946
+ {
1947
+ "epoch": 2.61271676300578,
1948
+ "grad_norm": 0.015882886946201324,
1949
+ "learning_rate": 5.4256691735681786e-05,
1950
+ "loss": 0.006,
1951
+ "step": 226
1952
+ },
1953
+ {
1954
+ "epoch": 2.6242774566473988,
1955
+ "grad_norm": 0.01853213645517826,
1956
+ "learning_rate": 5.385213897437975e-05,
1957
+ "loss": 0.0072,
1958
+ "step": 227
1959
+ },
1960
+ {
1961
+ "epoch": 2.6358381502890174,
1962
+ "grad_norm": 0.01727055385708809,
1963
+ "learning_rate": 5.344733236295525e-05,
1964
+ "loss": 0.0056,
1965
+ "step": 228
1966
+ },
1967
+ {
1968
+ "epoch": 2.647398843930636,
1969
+ "grad_norm": 0.01715169847011566,
1970
+ "learning_rate": 5.3042298577550696e-05,
1971
+ "loss": 0.007,
1972
+ "step": 229
1973
+ },
1974
+ {
1975
+ "epoch": 2.6589595375722546,
1976
+ "grad_norm": 0.01657768152654171,
1977
+ "learning_rate": 5.263706430927895e-05,
1978
+ "loss": 0.0065,
1979
+ "step": 230
1980
+ },
1981
+ {
1982
+ "epoch": 2.6589595375722546,
1983
+ "eval_loss": 0.00817356538027525,
1984
+ "eval_runtime": 10.0412,
1985
+ "eval_samples_per_second": 4.979,
1986
+ "eval_steps_per_second": 1.295,
1987
+ "step": 230
1988
+ },
1989
+ {
1990
+ "epoch": 2.6705202312138727,
1991
+ "grad_norm": 0.016935985535383224,
1992
+ "learning_rate": 5.223165626246432e-05,
1993
+ "loss": 0.0056,
1994
+ "step": 231
1995
+ },
1996
+ {
1997
+ "epoch": 2.6820809248554913,
1998
+ "grad_norm": 0.016983183100819588,
1999
+ "learning_rate": 5.182610115288295e-05,
2000
+ "loss": 0.0054,
2001
+ "step": 232
2002
+ },
2003
+ {
2004
+ "epoch": 2.69364161849711,
2005
+ "grad_norm": 0.014110002666711807,
2006
+ "learning_rate": 5.142042570600212e-05,
2007
+ "loss": 0.0048,
2008
+ "step": 233
2009
+ },
2010
+ {
2011
+ "epoch": 2.705202312138728,
2012
+ "grad_norm": 0.015584226697683334,
2013
+ "learning_rate": 5.1014656655219197e-05,
2014
+ "loss": 0.0074,
2015
+ "step": 234
2016
+ },
2017
+ {
2018
+ "epoch": 2.7167630057803467,
2019
+ "grad_norm": 0.015623894520103931,
2020
+ "learning_rate": 5.060882074009988e-05,
2021
+ "loss": 0.0061,
2022
+ "step": 235
2023
+ },
2024
+ {
2025
+ "epoch": 2.7167630057803467,
2026
+ "eval_loss": 0.00805756263434887,
2027
+ "eval_runtime": 10.0337,
2028
+ "eval_samples_per_second": 4.983,
2029
+ "eval_steps_per_second": 1.296,
2030
+ "step": 235
2031
+ },
2032
+ {
2033
+ "epoch": 2.7283236994219653,
2034
+ "grad_norm": 0.014514243230223656,
2035
+ "learning_rate": 5.020294470461615e-05,
2036
+ "loss": 0.005,
2037
+ "step": 236
2038
+ },
2039
+ {
2040
+ "epoch": 2.739884393063584,
2041
+ "grad_norm": 0.016889233142137527,
2042
+ "learning_rate": 4.979705529538385e-05,
2043
+ "loss": 0.0065,
2044
+ "step": 237
2045
+ },
2046
+ {
2047
+ "epoch": 2.7514450867052025,
2048
+ "grad_norm": 0.014339439570903778,
2049
+ "learning_rate": 4.9391179259900125e-05,
2050
+ "loss": 0.0047,
2051
+ "step": 238
2052
+ },
2053
+ {
2054
+ "epoch": 2.7630057803468207,
2055
+ "grad_norm": 0.019386202096939087,
2056
+ "learning_rate": 4.8985343344780815e-05,
2057
+ "loss": 0.0055,
2058
+ "step": 239
2059
+ },
2060
+ {
2061
+ "epoch": 2.7745664739884393,
2062
+ "grad_norm": 0.016825564205646515,
2063
+ "learning_rate": 4.857957429399788e-05,
2064
+ "loss": 0.0052,
2065
+ "step": 240
2066
+ },
2067
+ {
2068
+ "epoch": 2.7745664739884393,
2069
+ "eval_loss": 0.008152703754603863,
2070
+ "eval_runtime": 10.0237,
2071
+ "eval_samples_per_second": 4.988,
2072
+ "eval_steps_per_second": 1.297,
2073
+ "step": 240
2074
+ },
2075
+ {
2076
+ "epoch": 2.786127167630058,
2077
+ "grad_norm": 0.018642200157046318,
2078
+ "learning_rate": 4.817389884711705e-05,
2079
+ "loss": 0.0054,
2080
+ "step": 241
2081
+ },
2082
+ {
2083
+ "epoch": 2.7976878612716765,
2084
+ "grad_norm": 0.017443155869841576,
2085
+ "learning_rate": 4.776834373753569e-05,
2086
+ "loss": 0.0066,
2087
+ "step": 242
2088
+ },
2089
+ {
2090
+ "epoch": 2.809248554913295,
2091
+ "grad_norm": 0.017855728045105934,
2092
+ "learning_rate": 4.7362935690721076e-05,
2093
+ "loss": 0.0064,
2094
+ "step": 243
2095
+ },
2096
+ {
2097
+ "epoch": 2.820809248554913,
2098
+ "grad_norm": 0.013038886711001396,
2099
+ "learning_rate": 4.695770142244931e-05,
2100
+ "loss": 0.0054,
2101
+ "step": 244
2102
+ },
2103
+ {
2104
+ "epoch": 2.832369942196532,
2105
+ "grad_norm": 0.0145301828160882,
2106
+ "learning_rate": 4.655266763704476e-05,
2107
+ "loss": 0.0053,
2108
+ "step": 245
2109
+ },
2110
+ {
2111
+ "epoch": 2.832369942196532,
2112
+ "eval_loss": 0.008140629157423973,
2113
+ "eval_runtime": 10.0264,
2114
+ "eval_samples_per_second": 4.987,
2115
+ "eval_steps_per_second": 1.297,
2116
+ "step": 245
2117
+ },
2118
+ {
2119
+ "epoch": 2.8439306358381504,
2120
+ "grad_norm": 0.015260045416653156,
2121
+ "learning_rate": 4.614786102562026e-05,
2122
+ "loss": 0.0048,
2123
+ "step": 246
2124
+ },
2125
+ {
2126
+ "epoch": 2.8554913294797686,
2127
+ "grad_norm": 0.014731310307979584,
2128
+ "learning_rate": 4.574330826431821e-05,
2129
+ "loss": 0.005,
2130
+ "step": 247
2131
+ },
2132
+ {
2133
+ "epoch": 2.867052023121387,
2134
+ "grad_norm": 0.017430312931537628,
2135
+ "learning_rate": 4.5339036012552716e-05,
2136
+ "loss": 0.0062,
2137
+ "step": 248
2138
+ },
2139
+ {
2140
+ "epoch": 2.878612716763006,
2141
+ "grad_norm": 0.01655244641005993,
2142
+ "learning_rate": 4.493507091125269e-05,
2143
+ "loss": 0.0056,
2144
+ "step": 249
2145
+ },
2146
+ {
2147
+ "epoch": 2.8901734104046244,
2148
+ "grad_norm": 0.016315851360559464,
2149
+ "learning_rate": 4.4531439581106295e-05,
2150
+ "loss": 0.0058,
2151
+ "step": 250
2152
+ },
2153
+ {
2154
+ "epoch": 2.8901734104046244,
2155
+ "eval_loss": 0.007892865687608719,
2156
+ "eval_runtime": 10.0251,
2157
+ "eval_samples_per_second": 4.988,
2158
+ "eval_steps_per_second": 1.297,
2159
+ "step": 250
2160
+ }
2161
+ ],
2162
+ "logging_steps": 1,
2163
+ "max_steps": 430,
2164
+ "num_input_tokens_seen": 0,
2165
+ "num_train_epochs": 5,
2166
+ "save_steps": 50,
2167
+ "stateful_callbacks": {
2168
+ "TrainerControl": {
2169
+ "args": {
2170
+ "should_epoch_stop": false,
2171
+ "should_evaluate": false,
2172
+ "should_log": false,
2173
+ "should_save": true,
2174
+ "should_training_stop": false
2175
+ },
2176
+ "attributes": {}
2177
+ }
2178
+ },
2179
+ "total_flos": 5.930577893658132e+17,
2180
+ "train_batch_size": 4,
2181
+ "trial_name": null,
2182
+ "trial_params": null
2183
+ }
checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72886bedd016d1f99814720df6614c5543c0ad45208bb8f78e98bee78c53147d
3
+ size 5432
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.971098265895954,
3
+ "eval_loss": 0.007892867550253868,
4
+ "eval_runtime": 9.953,
5
+ "eval_samples_per_second": 5.024,
6
+ "eval_steps_per_second": 1.306
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.971098265895954,
3
+ "total_flos": 1.0207257247425331e+18,
4
+ "train_loss": 0.0087554031284526,
5
+ "train_runtime": 8412.5192,
6
+ "train_samples_per_second": 1.645,
7
+ "train_steps_per_second": 0.051
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,517 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 430, "loss": 0.068, "lr": 2.325581395348837e-06, "epoch": 0.011560693641618497, "percentage": 0.23, "elapsed_time": "0:00:30", "remaining_time": "3:36:07"}
2
+ {"current_steps": 2, "total_steps": 430, "loss": 0.0635, "lr": 4.651162790697674e-06, "epoch": 0.023121387283236993, "percentage": 0.47, "elapsed_time": "0:00:51", "remaining_time": "3:02:11"}
3
+ {"current_steps": 3, "total_steps": 430, "loss": 0.0649, "lr": 6.976744186046512e-06, "epoch": 0.03468208092485549, "percentage": 0.7, "elapsed_time": "0:01:08", "remaining_time": "2:42:03"}
4
+ {"current_steps": 4, "total_steps": 430, "loss": 0.063, "lr": 9.302325581395349e-06, "epoch": 0.046242774566473986, "percentage": 0.93, "elapsed_time": "0:01:26", "remaining_time": "2:34:05"}
5
+ {"current_steps": 5, "total_steps": 430, "loss": 0.0598, "lr": 1.1627906976744187e-05, "epoch": 0.057803468208092484, "percentage": 1.16, "elapsed_time": "0:01:44", "remaining_time": "2:27:39"}
6
+ {"current_steps": 5, "total_steps": 430, "eval_loss": 0.05565303936600685, "epoch": 0.057803468208092484, "percentage": 1.16, "elapsed_time": "0:01:56", "remaining_time": "2:44:28"}
7
+ {"current_steps": 6, "total_steps": 430, "loss": 0.0533, "lr": 1.3953488372093024e-05, "epoch": 0.06936416184971098, "percentage": 1.4, "elapsed_time": "0:02:16", "remaining_time": "2:40:58"}
8
+ {"current_steps": 7, "total_steps": 430, "loss": 0.0544, "lr": 1.6279069767441862e-05, "epoch": 0.08092485549132948, "percentage": 1.63, "elapsed_time": "0:02:33", "remaining_time": "2:34:20"}
9
+ {"current_steps": 8, "total_steps": 430, "loss": 0.0448, "lr": 1.8604651162790697e-05, "epoch": 0.09248554913294797, "percentage": 1.86, "elapsed_time": "0:02:49", "remaining_time": "2:29:03"}
10
+ {"current_steps": 9, "total_steps": 430, "loss": 0.0373, "lr": 2.0930232558139536e-05, "epoch": 0.10404624277456648, "percentage": 2.09, "elapsed_time": "0:03:06", "remaining_time": "2:25:22"}
11
+ {"current_steps": 10, "total_steps": 430, "loss": 0.0388, "lr": 2.3255813953488374e-05, "epoch": 0.11560693641618497, "percentage": 2.33, "elapsed_time": "0:03:23", "remaining_time": "2:22:24"}
12
+ {"current_steps": 10, "total_steps": 430, "eval_loss": 0.034586433321237564, "epoch": 0.11560693641618497, "percentage": 2.33, "elapsed_time": "0:03:33", "remaining_time": "2:29:26"}
13
+ {"current_steps": 11, "total_steps": 430, "loss": 0.0393, "lr": 2.5581395348837212e-05, "epoch": 0.12716763005780346, "percentage": 2.56, "elapsed_time": "0:03:51", "remaining_time": "2:27:06"}
14
+ {"current_steps": 12, "total_steps": 430, "loss": 0.0377, "lr": 2.7906976744186048e-05, "epoch": 0.13872832369942195, "percentage": 2.79, "elapsed_time": "0:04:09", "remaining_time": "2:24:39"}
15
+ {"current_steps": 13, "total_steps": 430, "loss": 0.0356, "lr": 3.0232558139534883e-05, "epoch": 0.15028901734104047, "percentage": 3.02, "elapsed_time": "0:04:27", "remaining_time": "2:22:52"}
16
+ {"current_steps": 14, "total_steps": 430, "loss": 0.0363, "lr": 3.2558139534883724e-05, "epoch": 0.16184971098265896, "percentage": 3.26, "elapsed_time": "0:04:45", "remaining_time": "2:21:21"}
17
+ {"current_steps": 15, "total_steps": 430, "loss": 0.0275, "lr": 3.488372093023256e-05, "epoch": 0.17341040462427745, "percentage": 3.49, "elapsed_time": "0:05:03", "remaining_time": "2:20:05"}
18
+ {"current_steps": 15, "total_steps": 430, "eval_loss": 0.027632026001811028, "epoch": 0.17341040462427745, "percentage": 3.49, "elapsed_time": "0:05:13", "remaining_time": "2:24:43"}
19
+ {"current_steps": 16, "total_steps": 430, "loss": 0.0303, "lr": 3.7209302325581394e-05, "epoch": 0.18497109826589594, "percentage": 3.72, "elapsed_time": "0:05:31", "remaining_time": "2:22:44"}
20
+ {"current_steps": 17, "total_steps": 430, "loss": 0.0284, "lr": 3.953488372093023e-05, "epoch": 0.19653179190751446, "percentage": 3.95, "elapsed_time": "0:05:48", "remaining_time": "2:21:16"}
21
+ {"current_steps": 18, "total_steps": 430, "loss": 0.03, "lr": 4.186046511627907e-05, "epoch": 0.20809248554913296, "percentage": 4.19, "elapsed_time": "0:06:06", "remaining_time": "2:19:42"}
22
+ {"current_steps": 19, "total_steps": 430, "loss": 0.0242, "lr": 4.418604651162791e-05, "epoch": 0.21965317919075145, "percentage": 4.42, "elapsed_time": "0:06:22", "remaining_time": "2:17:59"}
23
+ {"current_steps": 20, "total_steps": 430, "loss": 0.0218, "lr": 4.651162790697675e-05, "epoch": 0.23121387283236994, "percentage": 4.65, "elapsed_time": "0:06:40", "remaining_time": "2:16:47"}
24
+ {"current_steps": 20, "total_steps": 430, "eval_loss": 0.02280299924314022, "epoch": 0.23121387283236994, "percentage": 4.65, "elapsed_time": "0:06:50", "remaining_time": "2:20:15"}
25
+ {"current_steps": 21, "total_steps": 430, "loss": 0.0235, "lr": 4.883720930232558e-05, "epoch": 0.24277456647398843, "percentage": 4.88, "elapsed_time": "0:07:08", "remaining_time": "2:18:57"}
26
+ {"current_steps": 22, "total_steps": 430, "loss": 0.0291, "lr": 5.1162790697674425e-05, "epoch": 0.2543352601156069, "percentage": 5.12, "elapsed_time": "0:07:25", "remaining_time": "2:17:41"}
27
+ {"current_steps": 23, "total_steps": 430, "loss": 0.0254, "lr": 5.348837209302326e-05, "epoch": 0.2658959537572254, "percentage": 5.35, "elapsed_time": "0:07:44", "remaining_time": "2:17:00"}
28
+ {"current_steps": 24, "total_steps": 430, "loss": 0.0256, "lr": 5.5813953488372095e-05, "epoch": 0.2774566473988439, "percentage": 5.58, "elapsed_time": "0:08:01", "remaining_time": "2:15:39"}
29
+ {"current_steps": 25, "total_steps": 430, "loss": 0.0236, "lr": 5.8139534883720933e-05, "epoch": 0.28901734104046245, "percentage": 5.81, "elapsed_time": "0:08:18", "remaining_time": "2:14:41"}
30
+ {"current_steps": 25, "total_steps": 430, "eval_loss": 0.020257851108908653, "epoch": 0.28901734104046245, "percentage": 5.81, "elapsed_time": "0:08:28", "remaining_time": "2:17:24"}
31
+ {"current_steps": 26, "total_steps": 430, "loss": 0.0229, "lr": 6.0465116279069765e-05, "epoch": 0.30057803468208094, "percentage": 6.05, "elapsed_time": "0:08:46", "remaining_time": "2:16:21"}
32
+ {"current_steps": 27, "total_steps": 430, "loss": 0.0226, "lr": 6.27906976744186e-05, "epoch": 0.31213872832369943, "percentage": 6.28, "elapsed_time": "0:09:02", "remaining_time": "2:15:03"}
33
+ {"current_steps": 28, "total_steps": 430, "loss": 0.0196, "lr": 6.511627906976745e-05, "epoch": 0.3236994219653179, "percentage": 6.51, "elapsed_time": "0:09:20", "remaining_time": "2:14:05"}
34
+ {"current_steps": 29, "total_steps": 430, "loss": 0.0182, "lr": 6.744186046511628e-05, "epoch": 0.3352601156069364, "percentage": 6.74, "elapsed_time": "0:09:37", "remaining_time": "2:13:07"}
35
+ {"current_steps": 30, "total_steps": 430, "loss": 0.0182, "lr": 6.976744186046513e-05, "epoch": 0.3468208092485549, "percentage": 6.98, "elapsed_time": "0:09:55", "remaining_time": "2:12:16"}
36
+ {"current_steps": 30, "total_steps": 430, "eval_loss": 0.01791333220899105, "epoch": 0.3468208092485549, "percentage": 6.98, "elapsed_time": "0:10:05", "remaining_time": "2:14:30"}
37
+ {"current_steps": 31, "total_steps": 430, "loss": 0.0173, "lr": 7.209302325581396e-05, "epoch": 0.3583815028901734, "percentage": 7.21, "elapsed_time": "0:10:23", "remaining_time": "2:13:41"}
38
+ {"current_steps": 32, "total_steps": 430, "loss": 0.0186, "lr": 7.441860465116279e-05, "epoch": 0.3699421965317919, "percentage": 7.44, "elapsed_time": "0:10:40", "remaining_time": "2:12:42"}
39
+ {"current_steps": 33, "total_steps": 430, "loss": 0.0192, "lr": 7.674418604651163e-05, "epoch": 0.3815028901734104, "percentage": 7.67, "elapsed_time": "0:10:58", "remaining_time": "2:12:02"}
40
+ {"current_steps": 34, "total_steps": 430, "loss": 0.0163, "lr": 7.906976744186047e-05, "epoch": 0.3930635838150289, "percentage": 7.91, "elapsed_time": "0:11:14", "remaining_time": "2:10:56"}
41
+ {"current_steps": 35, "total_steps": 430, "loss": 0.019, "lr": 8.139534883720931e-05, "epoch": 0.4046242774566474, "percentage": 8.14, "elapsed_time": "0:11:32", "remaining_time": "2:10:10"}
42
+ {"current_steps": 35, "total_steps": 430, "eval_loss": 0.016155000776052475, "epoch": 0.4046242774566474, "percentage": 8.14, "elapsed_time": "0:11:42", "remaining_time": "2:12:03"}
43
+ {"current_steps": 36, "total_steps": 430, "loss": 0.0157, "lr": 8.372093023255814e-05, "epoch": 0.4161849710982659, "percentage": 8.37, "elapsed_time": "0:11:58", "remaining_time": "2:11:04"}
44
+ {"current_steps": 37, "total_steps": 430, "loss": 0.0154, "lr": 8.604651162790697e-05, "epoch": 0.4277456647398844, "percentage": 8.6, "elapsed_time": "0:12:16", "remaining_time": "2:10:20"}
45
+ {"current_steps": 38, "total_steps": 430, "loss": 0.0142, "lr": 8.837209302325582e-05, "epoch": 0.4393063583815029, "percentage": 8.84, "elapsed_time": "0:12:33", "remaining_time": "2:09:37"}
46
+ {"current_steps": 39, "total_steps": 430, "loss": 0.0155, "lr": 9.069767441860465e-05, "epoch": 0.4508670520231214, "percentage": 9.07, "elapsed_time": "0:12:51", "remaining_time": "2:08:50"}
47
+ {"current_steps": 40, "total_steps": 430, "loss": 0.017, "lr": 9.30232558139535e-05, "epoch": 0.4624277456647399, "percentage": 9.3, "elapsed_time": "0:13:08", "remaining_time": "2:08:12"}
48
+ {"current_steps": 40, "total_steps": 430, "eval_loss": 0.01472202967852354, "epoch": 0.4624277456647399, "percentage": 9.3, "elapsed_time": "0:13:19", "remaining_time": "2:09:51"}
49
+ {"current_steps": 41, "total_steps": 430, "loss": 0.0161, "lr": 9.534883720930233e-05, "epoch": 0.47398843930635837, "percentage": 9.53, "elapsed_time": "0:13:36", "remaining_time": "2:09:06"}
50
+ {"current_steps": 42, "total_steps": 430, "loss": 0.0146, "lr": 9.767441860465116e-05, "epoch": 0.48554913294797686, "percentage": 9.77, "elapsed_time": "0:13:53", "remaining_time": "2:08:18"}
51
+ {"current_steps": 43, "total_steps": 430, "loss": 0.015, "lr": 0.0001, "epoch": 0.49710982658959535, "percentage": 10.0, "elapsed_time": "0:14:11", "remaining_time": "2:07:40"}
52
+ {"current_steps": 44, "total_steps": 430, "loss": 0.0149, "lr": 9.999835253787473e-05, "epoch": 0.5086705202312138, "percentage": 10.23, "elapsed_time": "0:14:29", "remaining_time": "2:07:08"}
53
+ {"current_steps": 45, "total_steps": 430, "loss": 0.0147, "lr": 9.999341026006419e-05, "epoch": 0.5202312138728323, "percentage": 10.47, "elapsed_time": "0:14:47", "remaining_time": "2:06:29"}
54
+ {"current_steps": 45, "total_steps": 430, "eval_loss": 0.013716931454837322, "epoch": 0.5202312138728323, "percentage": 10.47, "elapsed_time": "0:14:57", "remaining_time": "2:07:55"}
55
+ {"current_steps": 46, "total_steps": 430, "loss": 0.0107, "lr": 9.998517349225698e-05, "epoch": 0.5317919075144508, "percentage": 10.7, "elapsed_time": "0:15:14", "remaining_time": "2:07:13"}
56
+ {"current_steps": 47, "total_steps": 430, "loss": 0.0149, "lr": 9.997364277724361e-05, "epoch": 0.5433526011560693, "percentage": 10.93, "elapsed_time": "0:15:31", "remaining_time": "2:06:29"}
57
+ {"current_steps": 48, "total_steps": 430, "loss": 0.0144, "lr": 9.99588188748808e-05, "epoch": 0.5549132947976878, "percentage": 11.16, "elapsed_time": "0:15:47", "remaining_time": "2:05:41"}
58
+ {"current_steps": 49, "total_steps": 430, "loss": 0.0126, "lr": 9.994070276204116e-05, "epoch": 0.5664739884393064, "percentage": 11.4, "elapsed_time": "0:16:04", "remaining_time": "2:05:00"}
59
+ {"current_steps": 50, "total_steps": 430, "loss": 0.0118, "lr": 9.991929563254914e-05, "epoch": 0.5780346820809249, "percentage": 11.63, "elapsed_time": "0:16:21", "remaining_time": "2:04:22"}
60
+ {"current_steps": 50, "total_steps": 430, "eval_loss": 0.013151152059435844, "epoch": 0.5780346820809249, "percentage": 11.63, "elapsed_time": "0:16:31", "remaining_time": "2:05:38"}
61
+ {"current_steps": 51, "total_steps": 430, "loss": 0.0144, "lr": 9.989459889710213e-05, "epoch": 0.5895953757225434, "percentage": 11.86, "elapsed_time": "0:16:58", "remaining_time": "2:06:06"}
62
+ {"current_steps": 52, "total_steps": 430, "loss": 0.0119, "lr": 9.986661418317759e-05, "epoch": 0.6011560693641619, "percentage": 12.09, "elapsed_time": "0:17:15", "remaining_time": "2:05:28"}
63
+ {"current_steps": 53, "total_steps": 430, "loss": 0.0137, "lr": 9.983534333492575e-05, "epoch": 0.6127167630057804, "percentage": 12.33, "elapsed_time": "0:17:34", "remaining_time": "2:04:57"}
64
+ {"current_steps": 54, "total_steps": 430, "loss": 0.014, "lr": 9.980078841304816e-05, "epoch": 0.6242774566473989, "percentage": 12.56, "elapsed_time": "0:17:51", "remaining_time": "2:04:22"}
65
+ {"current_steps": 55, "total_steps": 430, "loss": 0.0107, "lr": 9.976295169466178e-05, "epoch": 0.6358381502890174, "percentage": 12.79, "elapsed_time": "0:18:09", "remaining_time": "2:03:47"}
66
+ {"current_steps": 55, "total_steps": 430, "eval_loss": 0.012713148258626461, "epoch": 0.6358381502890174, "percentage": 12.79, "elapsed_time": "0:18:19", "remaining_time": "2:04:56"}
67
+ {"current_steps": 56, "total_steps": 430, "loss": 0.0146, "lr": 9.97218356731491e-05, "epoch": 0.6473988439306358, "percentage": 13.02, "elapsed_time": "0:18:36", "remaining_time": "2:04:17"}
68
+ {"current_steps": 57, "total_steps": 430, "loss": 0.0126, "lr": 9.967744305799357e-05, "epoch": 0.6589595375722543, "percentage": 13.26, "elapsed_time": "0:18:54", "remaining_time": "2:03:46"}
69
+ {"current_steps": 58, "total_steps": 430, "loss": 0.0126, "lr": 9.962977677460132e-05, "epoch": 0.6705202312138728, "percentage": 13.49, "elapsed_time": "0:19:12", "remaining_time": "2:03:14"}
70
+ {"current_steps": 59, "total_steps": 430, "loss": 0.0122, "lr": 9.957883996410821e-05, "epoch": 0.6820809248554913, "percentage": 13.72, "elapsed_time": "0:19:28", "remaining_time": "2:02:26"}
71
+ {"current_steps": 60, "total_steps": 430, "loss": 0.016, "lr": 9.952463598317285e-05, "epoch": 0.6936416184971098, "percentage": 13.95, "elapsed_time": "0:19:46", "remaining_time": "2:01:54"}
72
+ {"current_steps": 60, "total_steps": 430, "eval_loss": 0.012294010259211063, "epoch": 0.6936416184971098, "percentage": 13.95, "elapsed_time": "0:19:56", "remaining_time": "2:02:57"}
73
+ {"current_steps": 61, "total_steps": 430, "loss": 0.0106, "lr": 9.946716840375551e-05, "epoch": 0.7052023121387283, "percentage": 14.19, "elapsed_time": "0:20:14", "remaining_time": "2:02:26"}
74
+ {"current_steps": 62, "total_steps": 430, "loss": 0.0098, "lr": 9.940644101288259e-05, "epoch": 0.7167630057803468, "percentage": 14.42, "elapsed_time": "0:20:31", "remaining_time": "2:01:47"}
75
+ {"current_steps": 63, "total_steps": 430, "loss": 0.0142, "lr": 9.934245781239714e-05, "epoch": 0.7283236994219653, "percentage": 14.65, "elapsed_time": "0:20:47", "remaining_time": "2:01:09"}
76
+ {"current_steps": 64, "total_steps": 430, "loss": 0.0114, "lr": 9.927522301869515e-05, "epoch": 0.7398843930635838, "percentage": 14.88, "elapsed_time": "0:21:06", "remaining_time": "2:00:40"}
77
+ {"current_steps": 65, "total_steps": 430, "loss": 0.0144, "lr": 9.920474106244763e-05, "epoch": 0.7514450867052023, "percentage": 15.12, "elapsed_time": "0:21:22", "remaining_time": "2:00:00"}
78
+ {"current_steps": 65, "total_steps": 430, "eval_loss": 0.011602817103266716, "epoch": 0.7514450867052023, "percentage": 15.12, "elapsed_time": "0:21:32", "remaining_time": "2:00:56"}
79
+ {"current_steps": 66, "total_steps": 430, "loss": 0.0136, "lr": 9.91310165883088e-05, "epoch": 0.7630057803468208, "percentage": 15.35, "elapsed_time": "0:21:49", "remaining_time": "2:00:23"}
80
+ {"current_steps": 67, "total_steps": 430, "loss": 0.0113, "lr": 9.905405445460972e-05, "epoch": 0.7745664739884393, "percentage": 15.58, "elapsed_time": "0:22:05", "remaining_time": "1:59:43"}
81
+ {"current_steps": 68, "total_steps": 430, "loss": 0.0133, "lr": 9.897385973303845e-05, "epoch": 0.7861271676300579, "percentage": 15.81, "elapsed_time": "0:22:21", "remaining_time": "1:59:02"}
82
+ {"current_steps": 69, "total_steps": 430, "loss": 0.0108, "lr": 9.889043770830566e-05, "epoch": 0.7976878612716763, "percentage": 16.05, "elapsed_time": "0:22:37", "remaining_time": "1:58:22"}
83
+ {"current_steps": 70, "total_steps": 430, "loss": 0.0119, "lr": 9.880379387779637e-05, "epoch": 0.8092485549132948, "percentage": 16.28, "elapsed_time": "0:22:55", "remaining_time": "1:57:56"}
84
+ {"current_steps": 70, "total_steps": 430, "eval_loss": 0.011262123472988605, "epoch": 0.8092485549132948, "percentage": 16.28, "elapsed_time": "0:23:05", "remaining_time": "1:58:47"}
85
+ {"current_steps": 71, "total_steps": 430, "loss": 0.014, "lr": 9.871393395120774e-05, "epoch": 0.8208092485549133, "percentage": 16.51, "elapsed_time": "0:23:24", "remaining_time": "1:58:19"}
86
+ {"current_steps": 72, "total_steps": 430, "loss": 0.0099, "lr": 9.862086385017283e-05, "epoch": 0.8323699421965318, "percentage": 16.74, "elapsed_time": "0:23:40", "remaining_time": "1:57:44"}
87
+ {"current_steps": 73, "total_steps": 430, "loss": 0.011, "lr": 9.852458970787026e-05, "epoch": 0.8439306358381503, "percentage": 16.98, "elapsed_time": "0:23:57", "remaining_time": "1:57:08"}
88
+ {"current_steps": 74, "total_steps": 430, "loss": 0.01, "lr": 9.842511786862019e-05, "epoch": 0.8554913294797688, "percentage": 17.21, "elapsed_time": "0:24:14", "remaining_time": "1:56:36"}
89
+ {"current_steps": 75, "total_steps": 430, "loss": 0.0111, "lr": 9.832245488746611e-05, "epoch": 0.8670520231213873, "percentage": 17.44, "elapsed_time": "0:24:32", "remaining_time": "1:56:08"}
90
+ {"current_steps": 75, "total_steps": 430, "eval_loss": 0.010938560590147972, "epoch": 0.8670520231213873, "percentage": 17.44, "elapsed_time": "0:24:42", "remaining_time": "1:56:55"}
91
+ {"current_steps": 76, "total_steps": 430, "loss": 0.0142, "lr": 9.821660752974293e-05, "epoch": 0.8786127167630058, "percentage": 17.67, "elapsed_time": "0:24:59", "remaining_time": "1:56:23"}
92
+ {"current_steps": 77, "total_steps": 430, "loss": 0.0138, "lr": 9.810758277063119e-05, "epoch": 0.8901734104046243, "percentage": 17.91, "elapsed_time": "0:25:17", "remaining_time": "1:55:57"}
93
+ {"current_steps": 78, "total_steps": 430, "loss": 0.0151, "lr": 9.799538779469734e-05, "epoch": 0.9017341040462428, "percentage": 18.14, "elapsed_time": "0:25:35", "remaining_time": "1:55:27"}
94
+ {"current_steps": 79, "total_steps": 430, "loss": 0.0098, "lr": 9.78800299954203e-05, "epoch": 0.9132947976878613, "percentage": 18.37, "elapsed_time": "0:25:52", "remaining_time": "1:54:56"}
95
+ {"current_steps": 80, "total_steps": 430, "loss": 0.012, "lr": 9.77615169747043e-05, "epoch": 0.9248554913294798, "percentage": 18.6, "elapsed_time": "0:26:08", "remaining_time": "1:54:20"}
96
+ {"current_steps": 80, "total_steps": 430, "eval_loss": 0.010658971033990383, "epoch": 0.9248554913294798, "percentage": 18.6, "elapsed_time": "0:26:18", "remaining_time": "1:55:05"}
97
+ {"current_steps": 81, "total_steps": 430, "loss": 0.0126, "lr": 9.763985654237786e-05, "epoch": 0.9364161849710982, "percentage": 18.84, "elapsed_time": "0:26:35", "remaining_time": "1:54:36"}
98
+ {"current_steps": 82, "total_steps": 430, "loss": 0.0129, "lr": 9.751505671567913e-05, "epoch": 0.9479768786127167, "percentage": 19.07, "elapsed_time": "0:26:52", "remaining_time": "1:54:04"}
99
+ {"current_steps": 83, "total_steps": 430, "loss": 0.0093, "lr": 9.738712571872763e-05, "epoch": 0.9595375722543352, "percentage": 19.3, "elapsed_time": "0:27:09", "remaining_time": "1:53:30"}
100
+ {"current_steps": 84, "total_steps": 430, "loss": 0.0139, "lr": 9.725607198198227e-05, "epoch": 0.9710982658959537, "percentage": 19.53, "elapsed_time": "0:27:25", "remaining_time": "1:52:59"}
101
+ {"current_steps": 85, "total_steps": 430, "loss": 0.0139, "lr": 9.712190414168572e-05, "epoch": 0.9826589595375722, "percentage": 19.77, "elapsed_time": "0:27:44", "remaining_time": "1:52:35"}
102
+ {"current_steps": 85, "total_steps": 430, "eval_loss": 0.010201876051723957, "epoch": 0.9826589595375722, "percentage": 19.77, "elapsed_time": "0:27:54", "remaining_time": "1:53:16"}
103
+ {"current_steps": 86, "total_steps": 430, "loss": 0.0096, "lr": 9.698463103929542e-05, "epoch": 0.9942196531791907, "percentage": 20.0, "elapsed_time": "0:28:11", "remaining_time": "1:52:47"}
104
+ {"current_steps": 87, "total_steps": 430, "loss": 0.0208, "lr": 9.684426172090085e-05, "epoch": 1.0057803468208093, "percentage": 20.23, "elapsed_time": "0:28:28", "remaining_time": "1:52:14"}
105
+ {"current_steps": 88, "total_steps": 430, "loss": 0.0079, "lr": 9.67008054366274e-05, "epoch": 1.0173410404624277, "percentage": 20.47, "elapsed_time": "0:28:45", "remaining_time": "1:51:46"}
106
+ {"current_steps": 89, "total_steps": 430, "loss": 0.0103, "lr": 9.65542716400269e-05, "epoch": 1.0289017341040463, "percentage": 20.7, "elapsed_time": "0:29:03", "remaining_time": "1:51:20"}
107
+ {"current_steps": 90, "total_steps": 430, "loss": 0.0085, "lr": 9.640466998745456e-05, "epoch": 1.0404624277456647, "percentage": 20.93, "elapsed_time": "0:29:21", "remaining_time": "1:50:55"}
108
+ {"current_steps": 90, "total_steps": 430, "eval_loss": 0.01041076984256506, "epoch": 1.0404624277456647, "percentage": 20.93, "elapsed_time": "0:29:31", "remaining_time": "1:51:33"}
109
+ {"current_steps": 91, "total_steps": 430, "loss": 0.0102, "lr": 9.625201033743261e-05, "epoch": 1.0520231213872833, "percentage": 21.16, "elapsed_time": "0:29:49", "remaining_time": "1:51:06"}
110
+ {"current_steps": 92, "total_steps": 430, "loss": 0.0081, "lr": 9.609630275000072e-05, "epoch": 1.0635838150289016, "percentage": 21.4, "elapsed_time": "0:30:06", "remaining_time": "1:50:38"}
111
+ {"current_steps": 93, "total_steps": 430, "loss": 0.0094, "lr": 9.5937557486053e-05, "epoch": 1.0751445086705202, "percentage": 21.63, "elapsed_time": "0:30:24", "remaining_time": "1:50:10"}
112
+ {"current_steps": 94, "total_steps": 430, "loss": 0.0116, "lr": 9.577578500666187e-05, "epoch": 1.0867052023121386, "percentage": 21.86, "elapsed_time": "0:30:42", "remaining_time": "1:49:44"}
113
+ {"current_steps": 95, "total_steps": 430, "loss": 0.01, "lr": 9.56109959723886e-05, "epoch": 1.0982658959537572, "percentage": 22.09, "elapsed_time": "0:30:59", "remaining_time": "1:49:16"}
114
+ {"current_steps": 95, "total_steps": 430, "eval_loss": 0.010240535251796246, "epoch": 1.0982658959537572, "percentage": 22.09, "elapsed_time": "0:31:09", "remaining_time": "1:49:52"}
115
+ {"current_steps": 96, "total_steps": 430, "loss": 0.0099, "lr": 9.544320124258092e-05, "epoch": 1.1098265895953756, "percentage": 22.33, "elapsed_time": "0:31:27", "remaining_time": "1:49:25"}
116
+ {"current_steps": 97, "total_steps": 430, "loss": 0.0098, "lr": 9.527241187465734e-05, "epoch": 1.1213872832369942, "percentage": 22.56, "elapsed_time": "0:31:44", "remaining_time": "1:48:59"}
117
+ {"current_steps": 98, "total_steps": 430, "loss": 0.0084, "lr": 9.509863912337842e-05, "epoch": 1.1329479768786128, "percentage": 22.79, "elapsed_time": "0:32:02", "remaining_time": "1:48:33"}
118
+ {"current_steps": 99, "total_steps": 430, "loss": 0.01, "lr": 9.492189444010521e-05, "epoch": 1.1445086705202312, "percentage": 23.02, "elapsed_time": "0:32:19", "remaining_time": "1:48:04"}
119
+ {"current_steps": 100, "total_steps": 430, "loss": 0.009, "lr": 9.474218947204459e-05, "epoch": 1.1560693641618498, "percentage": 23.26, "elapsed_time": "0:32:36", "remaining_time": "1:47:36"}
120
+ {"current_steps": 100, "total_steps": 430, "eval_loss": 0.009868398308753967, "epoch": 1.1560693641618498, "percentage": 23.26, "elapsed_time": "0:32:46", "remaining_time": "1:48:09"}
121
+ {"current_steps": 101, "total_steps": 430, "loss": 0.0125, "lr": 9.455953606148172e-05, "epoch": 1.1676300578034682, "percentage": 23.49, "elapsed_time": "0:33:14", "remaining_time": "1:48:16"}
122
+ {"current_steps": 102, "total_steps": 430, "loss": 0.0116, "lr": 9.437394624499958e-05, "epoch": 1.1791907514450868, "percentage": 23.72, "elapsed_time": "0:33:30", "remaining_time": "1:47:46"}
123
+ {"current_steps": 103, "total_steps": 430, "loss": 0.0117, "lr": 9.418543225268596e-05, "epoch": 1.1907514450867052, "percentage": 23.95, "elapsed_time": "0:33:48", "remaining_time": "1:47:20"}
124
+ {"current_steps": 104, "total_steps": 430, "loss": 0.011, "lr": 9.399400650732735e-05, "epoch": 1.2023121387283238, "percentage": 24.19, "elapsed_time": "0:34:05", "remaining_time": "1:46:52"}
125
+ {"current_steps": 105, "total_steps": 430, "loss": 0.0094, "lr": 9.379968162359034e-05, "epoch": 1.2138728323699421, "percentage": 24.42, "elapsed_time": "0:34:22", "remaining_time": "1:46:23"}
126
+ {"current_steps": 105, "total_steps": 430, "eval_loss": 0.009825030341744423, "epoch": 1.2138728323699421, "percentage": 24.42, "elapsed_time": "0:34:32", "remaining_time": "1:46:54"}
127
+ {"current_steps": 106, "total_steps": 430, "loss": 0.0079, "lr": 9.360247040719039e-05, "epoch": 1.2254335260115607, "percentage": 24.65, "elapsed_time": "0:34:49", "remaining_time": "1:46:27"}
128
+ {"current_steps": 107, "total_steps": 430, "loss": 0.0077, "lr": 9.340238585404788e-05, "epoch": 1.2369942196531791, "percentage": 24.88, "elapsed_time": "0:35:07", "remaining_time": "1:46:02"}
129
+ {"current_steps": 108, "total_steps": 430, "loss": 0.0089, "lr": 9.319944114943171e-05, "epoch": 1.2485549132947977, "percentage": 25.12, "elapsed_time": "0:35:24", "remaining_time": "1:45:34"}
130
+ {"current_steps": 109, "total_steps": 430, "loss": 0.0076, "lr": 9.29936496670905e-05, "epoch": 1.260115606936416, "percentage": 25.35, "elapsed_time": "0:35:41", "remaining_time": "1:45:05"}
131
+ {"current_steps": 110, "total_steps": 430, "loss": 0.0069, "lr": 9.278502496837116e-05, "epoch": 1.2716763005780347, "percentage": 25.58, "elapsed_time": "0:35:57", "remaining_time": "1:44:37"}
132
+ {"current_steps": 110, "total_steps": 430, "eval_loss": 0.009917480871081352, "epoch": 1.2716763005780347, "percentage": 25.58, "elapsed_time": "0:36:07", "remaining_time": "1:45:06"}
133
+ {"current_steps": 111, "total_steps": 430, "loss": 0.0108, "lr": 9.257358080132523e-05, "epoch": 1.2832369942196533, "percentage": 25.81, "elapsed_time": "0:36:26", "remaining_time": "1:44:42"}
134
+ {"current_steps": 112, "total_steps": 430, "loss": 0.011, "lr": 9.235933109980301e-05, "epoch": 1.2947976878612717, "percentage": 26.05, "elapsed_time": "0:36:43", "remaining_time": "1:44:15"}
135
+ {"current_steps": 113, "total_steps": 430, "loss": 0.0084, "lr": 9.214228998253527e-05, "epoch": 1.30635838150289, "percentage": 26.28, "elapsed_time": "0:37:01", "remaining_time": "1:43:52"}
136
+ {"current_steps": 114, "total_steps": 430, "loss": 0.0087, "lr": 9.192247175220276e-05, "epoch": 1.3179190751445087, "percentage": 26.51, "elapsed_time": "0:37:19", "remaining_time": "1:43:26"}
137
+ {"current_steps": 115, "total_steps": 430, "loss": 0.0108, "lr": 9.16998908944939e-05, "epoch": 1.3294797687861273, "percentage": 26.74, "elapsed_time": "0:37:36", "remaining_time": "1:43:01"}
138
+ {"current_steps": 115, "total_steps": 430, "eval_loss": 0.009632885456085205, "epoch": 1.3294797687861273, "percentage": 26.74, "elapsed_time": "0:37:46", "remaining_time": "1:43:28"}
139
+ {"current_steps": 116, "total_steps": 430, "loss": 0.0077, "lr": 9.147456207714997e-05, "epoch": 1.3410404624277457, "percentage": 26.98, "elapsed_time": "0:38:04", "remaining_time": "1:43:03"}
140
+ {"current_steps": 117, "total_steps": 430, "loss": 0.0101, "lr": 9.124650014899867e-05, "epoch": 1.352601156069364, "percentage": 27.21, "elapsed_time": "0:38:22", "remaining_time": "1:42:38"}
141
+ {"current_steps": 118, "total_steps": 430, "loss": 0.0103, "lr": 9.101572013897555e-05, "epoch": 1.3641618497109826, "percentage": 27.44, "elapsed_time": "0:38:39", "remaining_time": "1:42:12"}
142
+ {"current_steps": 119, "total_steps": 430, "loss": 0.0112, "lr": 9.078223725513366e-05, "epoch": 1.3757225433526012, "percentage": 27.67, "elapsed_time": "0:38:57", "remaining_time": "1:41:49"}
143
+ {"current_steps": 120, "total_steps": 430, "loss": 0.0066, "lr": 9.05460668836413e-05, "epoch": 1.3872832369942196, "percentage": 27.91, "elapsed_time": "0:39:14", "remaining_time": "1:41:21"}
144
+ {"current_steps": 120, "total_steps": 430, "eval_loss": 0.009479235857725143, "epoch": 1.3872832369942196, "percentage": 27.91, "elapsed_time": "0:39:24", "remaining_time": "1:41:47"}
145
+ {"current_steps": 121, "total_steps": 430, "loss": 0.0083, "lr": 9.030722458776814e-05, "epoch": 1.3988439306358382, "percentage": 28.14, "elapsed_time": "0:39:40", "remaining_time": "1:41:18"}
146
+ {"current_steps": 122, "total_steps": 430, "loss": 0.013, "lr": 9.006572610685968e-05, "epoch": 1.4104046242774566, "percentage": 28.37, "elapsed_time": "0:39:58", "remaining_time": "1:40:54"}
147
+ {"current_steps": 123, "total_steps": 430, "loss": 0.0081, "lr": 8.98215873552999e-05, "epoch": 1.4219653179190752, "percentage": 28.6, "elapsed_time": "0:40:15", "remaining_time": "1:40:28"}
148
+ {"current_steps": 124, "total_steps": 430, "loss": 0.0069, "lr": 8.957482442146272e-05, "epoch": 1.4335260115606936, "percentage": 28.84, "elapsed_time": "0:40:32", "remaining_time": "1:40:03"}
149
+ {"current_steps": 125, "total_steps": 430, "loss": 0.0089, "lr": 8.932545356665157e-05, "epoch": 1.4450867052023122, "percentage": 29.07, "elapsed_time": "0:40:49", "remaining_time": "1:39:37"}
150
+ {"current_steps": 125, "total_steps": 430, "eval_loss": 0.009439178742468357, "epoch": 1.4450867052023122, "percentage": 29.07, "elapsed_time": "0:40:59", "remaining_time": "1:40:02"}
151
+ {"current_steps": 126, "total_steps": 430, "loss": 0.0064, "lr": 8.907349122402801e-05, "epoch": 1.4566473988439306, "percentage": 29.3, "elapsed_time": "0:41:16", "remaining_time": "1:39:35"}
152
+ {"current_steps": 127, "total_steps": 430, "loss": 0.0085, "lr": 8.881895399752874e-05, "epoch": 1.4682080924855492, "percentage": 29.53, "elapsed_time": "0:41:33", "remaining_time": "1:39:09"}
153
+ {"current_steps": 128, "total_steps": 430, "loss": 0.0091, "lr": 8.856185866077129e-05, "epoch": 1.4797687861271676, "percentage": 29.77, "elapsed_time": "0:41:52", "remaining_time": "1:38:46"}
154
+ {"current_steps": 129, "total_steps": 430, "loss": 0.0118, "lr": 8.83022221559489e-05, "epoch": 1.4913294797687862, "percentage": 30.0, "elapsed_time": "0:42:07", "remaining_time": "1:38:16"}
155
+ {"current_steps": 130, "total_steps": 430, "loss": 0.0084, "lr": 8.80400615927139e-05, "epoch": 1.5028901734104045, "percentage": 30.23, "elapsed_time": "0:42:22", "remaining_time": "1:37:47"}
156
+ {"current_steps": 130, "total_steps": 430, "eval_loss": 0.009285805746912956, "epoch": 1.5028901734104045, "percentage": 30.23, "elapsed_time": "0:42:32", "remaining_time": "1:38:10"}
157
+ {"current_steps": 131, "total_steps": 430, "loss": 0.0067, "lr": 8.777539424705023e-05, "epoch": 1.5144508670520231, "percentage": 30.47, "elapsed_time": "0:42:47", "remaining_time": "1:37:40"}
158
+ {"current_steps": 132, "total_steps": 430, "loss": 0.0111, "lr": 8.750823756013498e-05, "epoch": 1.5260115606936417, "percentage": 30.7, "elapsed_time": "0:43:04", "remaining_time": "1:37:14"}
159
+ {"current_steps": 133, "total_steps": 430, "loss": 0.0066, "lr": 8.72386091371891e-05, "epoch": 1.5375722543352601, "percentage": 30.93, "elapsed_time": "0:43:20", "remaining_time": "1:36:48"}
160
+ {"current_steps": 134, "total_steps": 430, "loss": 0.0089, "lr": 8.696652674631717e-05, "epoch": 1.5491329479768785, "percentage": 31.16, "elapsed_time": "0:43:38", "remaining_time": "1:36:24"}
161
+ {"current_steps": 135, "total_steps": 430, "loss": 0.0102, "lr": 8.669200831733655e-05, "epoch": 1.560693641618497, "percentage": 31.4, "elapsed_time": "0:43:55", "remaining_time": "1:35:58"}
162
+ {"current_steps": 135, "total_steps": 430, "eval_loss": 0.00925290398299694, "epoch": 1.560693641618497, "percentage": 31.4, "elapsed_time": "0:44:05", "remaining_time": "1:36:20"}
163
+ {"current_steps": 136, "total_steps": 430, "loss": 0.0084, "lr": 8.641507194059579e-05, "epoch": 1.5722543352601157, "percentage": 31.63, "elapsed_time": "0:44:21", "remaining_time": "1:35:54"}
164
+ {"current_steps": 137, "total_steps": 430, "loss": 0.0097, "lr": 8.613573586578262e-05, "epoch": 1.583815028901734, "percentage": 31.86, "elapsed_time": "0:44:39", "remaining_time": "1:35:31"}
165
+ {"current_steps": 138, "total_steps": 430, "loss": 0.0102, "lr": 8.585401850072113e-05, "epoch": 1.5953757225433525, "percentage": 32.09, "elapsed_time": "0:44:57", "remaining_time": "1:35:07"}
166
+ {"current_steps": 139, "total_steps": 430, "loss": 0.0076, "lr": 8.55699384101589e-05, "epoch": 1.606936416184971, "percentage": 32.33, "elapsed_time": "0:45:14", "remaining_time": "1:34:42"}
167
+ {"current_steps": 140, "total_steps": 430, "loss": 0.01, "lr": 8.528351431454351e-05, "epoch": 1.6184971098265897, "percentage": 32.56, "elapsed_time": "0:45:31", "remaining_time": "1:34:18"}
168
+ {"current_steps": 140, "total_steps": 430, "eval_loss": 0.009090203791856766, "epoch": 1.6184971098265897, "percentage": 32.56, "elapsed_time": "0:45:41", "remaining_time": "1:34:39"}
169
+ {"current_steps": 141, "total_steps": 430, "loss": 0.0091, "lr": 8.499476508878893e-05, "epoch": 1.630057803468208, "percentage": 32.79, "elapsed_time": "0:45:59", "remaining_time": "1:34:16"}
170
+ {"current_steps": 142, "total_steps": 430, "loss": 0.008, "lr": 8.47037097610317e-05, "epoch": 1.6416184971098264, "percentage": 33.02, "elapsed_time": "0:46:16", "remaining_time": "1:33:51"}
171
+ {"current_steps": 143, "total_steps": 430, "loss": 0.0122, "lr": 8.441036751137696e-05, "epoch": 1.653179190751445, "percentage": 33.26, "elapsed_time": "0:46:34", "remaining_time": "1:33:28"}
172
+ {"current_steps": 144, "total_steps": 430, "loss": 0.0075, "lr": 8.411475767063455e-05, "epoch": 1.6647398843930636, "percentage": 33.49, "elapsed_time": "0:46:52", "remaining_time": "1:33:05"}
173
+ {"current_steps": 145, "total_steps": 430, "loss": 0.0098, "lr": 8.381689971904514e-05, "epoch": 1.6763005780346822, "percentage": 33.72, "elapsed_time": "0:47:09", "remaining_time": "1:32:41"}
174
+ {"current_steps": 145, "total_steps": 430, "eval_loss": 0.008807710371911526, "epoch": 1.6763005780346822, "percentage": 33.72, "elapsed_time": "0:47:19", "remaining_time": "1:33:01"}
175
+ {"current_steps": 146, "total_steps": 430, "loss": 0.0074, "lr": 8.35168132849965e-05, "epoch": 1.6878612716763006, "percentage": 33.95, "elapsed_time": "0:47:36", "remaining_time": "1:32:36"}
176
+ {"current_steps": 147, "total_steps": 430, "loss": 0.0111, "lr": 8.321451814372997e-05, "epoch": 1.699421965317919, "percentage": 34.19, "elapsed_time": "0:47:53", "remaining_time": "1:32:11"}
177
+ {"current_steps": 148, "total_steps": 430, "loss": 0.0097, "lr": 8.29100342160374e-05, "epoch": 1.7109826589595376, "percentage": 34.42, "elapsed_time": "0:48:11", "remaining_time": "1:31:48"}
178
+ {"current_steps": 149, "total_steps": 430, "loss": 0.007, "lr": 8.260338156694836e-05, "epoch": 1.7225433526011562, "percentage": 34.65, "elapsed_time": "0:48:27", "remaining_time": "1:31:23"}
179
+ {"current_steps": 150, "total_steps": 430, "loss": 0.0071, "lr": 8.229458040440783e-05, "epoch": 1.7341040462427746, "percentage": 34.88, "elapsed_time": "0:48:43", "remaining_time": "1:30:56"}
180
+ {"current_steps": 150, "total_steps": 430, "eval_loss": 0.008663667365908623, "epoch": 1.7341040462427746, "percentage": 34.88, "elapsed_time": "0:48:53", "remaining_time": "1:31:15"}
181
+ {"current_steps": 151, "total_steps": 430, "loss": 0.0098, "lr": 8.198365107794457e-05, "epoch": 1.745664739884393, "percentage": 35.12, "elapsed_time": "0:49:21", "remaining_time": "1:31:11"}
182
+ {"current_steps": 152, "total_steps": 430, "loss": 0.0077, "lr": 8.167061407733016e-05, "epoch": 1.7572254335260116, "percentage": 35.35, "elapsed_time": "0:49:38", "remaining_time": "1:30:47"}
183
+ {"current_steps": 153, "total_steps": 430, "loss": 0.0096, "lr": 8.135549003122871e-05, "epoch": 1.7687861271676302, "percentage": 35.58, "elapsed_time": "0:49:55", "remaining_time": "1:30:23"}
184
+ {"current_steps": 154, "total_steps": 430, "loss": 0.0111, "lr": 8.103829970583742e-05, "epoch": 1.7803468208092486, "percentage": 35.81, "elapsed_time": "0:50:13", "remaining_time": "1:30:00"}
185
+ {"current_steps": 155, "total_steps": 430, "loss": 0.0094, "lr": 8.071906400351822e-05, "epoch": 1.791907514450867, "percentage": 36.05, "elapsed_time": "0:50:30", "remaining_time": "1:29:37"}
186
+ {"current_steps": 155, "total_steps": 430, "eval_loss": 0.008556585758924484, "epoch": 1.791907514450867, "percentage": 36.05, "elapsed_time": "0:50:40", "remaining_time": "1:29:55"}
187
+ {"current_steps": 156, "total_steps": 430, "loss": 0.0079, "lr": 8.039780396142022e-05, "epoch": 1.8034682080924855, "percentage": 36.28, "elapsed_time": "0:50:59", "remaining_time": "1:29:33"}
188
+ {"current_steps": 157, "total_steps": 430, "loss": 0.0115, "lr": 8.007454075009351e-05, "epoch": 1.8150289017341041, "percentage": 36.51, "elapsed_time": "0:51:17", "remaining_time": "1:29:10"}
189
+ {"current_steps": 158, "total_steps": 430, "loss": 0.0076, "lr": 7.9749295672094e-05, "epoch": 1.8265895953757225, "percentage": 36.74, "elapsed_time": "0:51:34", "remaining_time": "1:28:46"}
190
+ {"current_steps": 159, "total_steps": 430, "loss": 0.01, "lr": 7.942209016057954e-05, "epoch": 1.838150289017341, "percentage": 36.98, "elapsed_time": "0:51:52", "remaining_time": "1:28:24"}
191
+ {"current_steps": 160, "total_steps": 430, "loss": 0.008, "lr": 7.909294577789766e-05, "epoch": 1.8497109826589595, "percentage": 37.21, "elapsed_time": "0:52:10", "remaining_time": "1:28:02"}
192
+ {"current_steps": 160, "total_steps": 430, "eval_loss": 0.008559009060263634, "epoch": 1.8497109826589595, "percentage": 37.21, "elapsed_time": "0:52:20", "remaining_time": "1:28:19"}
193
+ {"current_steps": 161, "total_steps": 430, "loss": 0.0068, "lr": 7.876188421416449e-05, "epoch": 1.861271676300578, "percentage": 37.44, "elapsed_time": "0:52:36", "remaining_time": "1:27:54"}
194
+ {"current_steps": 162, "total_steps": 430, "loss": 0.0074, "lr": 7.842892728583558e-05, "epoch": 1.8728323699421965, "percentage": 37.67, "elapsed_time": "0:52:53", "remaining_time": "1:27:30"}
195
+ {"current_steps": 163, "total_steps": 430, "loss": 0.0071, "lr": 7.809409693426803e-05, "epoch": 1.8843930635838149, "percentage": 37.91, "elapsed_time": "0:53:10", "remaining_time": "1:27:06"}
196
+ {"current_steps": 164, "total_steps": 430, "loss": 0.009, "lr": 7.775741522427477e-05, "epoch": 1.8959537572254335, "percentage": 38.14, "elapsed_time": "0:53:28", "remaining_time": "1:26:43"}
197
+ {"current_steps": 165, "total_steps": 430, "loss": 0.01, "lr": 7.741890434267043e-05, "epoch": 1.907514450867052, "percentage": 38.37, "elapsed_time": "0:53:46", "remaining_time": "1:26:21"}
198
+ {"current_steps": 165, "total_steps": 430, "eval_loss": 0.00854802131652832, "epoch": 1.907514450867052, "percentage": 38.37, "elapsed_time": "0:53:56", "remaining_time": "1:26:37"}
199
+ {"current_steps": 166, "total_steps": 430, "loss": 0.0071, "lr": 7.707858659680924e-05, "epoch": 1.9190751445086707, "percentage": 38.6, "elapsed_time": "0:54:14", "remaining_time": "1:26:15"}
200
+ {"current_steps": 167, "total_steps": 430, "loss": 0.0076, "lr": 7.673648441311508e-05, "epoch": 1.930635838150289, "percentage": 38.84, "elapsed_time": "0:54:31", "remaining_time": "1:25:52"}
201
+ {"current_steps": 168, "total_steps": 430, "loss": 0.0064, "lr": 7.639262033560359e-05, "epoch": 1.9421965317919074, "percentage": 39.07, "elapsed_time": "0:54:49", "remaining_time": "1:25:30"}
202
+ {"current_steps": 169, "total_steps": 430, "loss": 0.0074, "lr": 7.604701702439651e-05, "epoch": 1.953757225433526, "percentage": 39.3, "elapsed_time": "0:55:06", "remaining_time": "1:25:06"}
203
+ {"current_steps": 170, "total_steps": 430, "loss": 0.0084, "lr": 7.56996972542285e-05, "epoch": 1.9653179190751446, "percentage": 39.53, "elapsed_time": "0:55:22", "remaining_time": "1:24:41"}
204
+ {"current_steps": 170, "total_steps": 430, "eval_loss": 0.008561979979276657, "epoch": 1.9653179190751446, "percentage": 39.53, "elapsed_time": "0:55:32", "remaining_time": "1:24:56"}
205
+ {"current_steps": 171, "total_steps": 430, "loss": 0.0102, "lr": 7.535068391294617e-05, "epoch": 1.976878612716763, "percentage": 39.77, "elapsed_time": "0:55:49", "remaining_time": "1:24:33"}
206
+ {"current_steps": 172, "total_steps": 430, "loss": 0.0086, "lr": 7.500000000000001e-05, "epoch": 1.9884393063583814, "percentage": 40.0, "elapsed_time": "0:56:07", "remaining_time": "1:24:11"}
207
+ {"current_steps": 173, "total_steps": 430, "loss": 0.0092, "lr": 7.464766862492855e-05, "epoch": 2.0, "percentage": 40.23, "elapsed_time": "0:56:24", "remaining_time": "1:23:47"}
208
+ {"current_steps": 174, "total_steps": 430, "loss": 0.0069, "lr": 7.42937130058357e-05, "epoch": 2.0115606936416186, "percentage": 40.47, "elapsed_time": "0:56:42", "remaining_time": "1:23:25"}
209
+ {"current_steps": 175, "total_steps": 430, "loss": 0.0058, "lr": 7.393815646786046e-05, "epoch": 2.023121387283237, "percentage": 40.7, "elapsed_time": "0:56:59", "remaining_time": "1:23:02"}
210
+ {"current_steps": 175, "total_steps": 430, "eval_loss": 0.008691162802278996, "epoch": 2.023121387283237, "percentage": 40.7, "elapsed_time": "0:57:09", "remaining_time": "1:23:17"}
211
+ {"current_steps": 176, "total_steps": 430, "loss": 0.0077, "lr": 7.358102244164003e-05, "epoch": 2.0346820809248554, "percentage": 40.93, "elapsed_time": "0:57:26", "remaining_time": "1:22:54"}
212
+ {"current_steps": 177, "total_steps": 430, "loss": 0.0074, "lr": 7.322233446176571e-05, "epoch": 2.046242774566474, "percentage": 41.16, "elapsed_time": "0:57:45", "remaining_time": "1:22:33"}
213
+ {"current_steps": 178, "total_steps": 430, "loss": 0.007, "lr": 7.286211616523193e-05, "epoch": 2.0578034682080926, "percentage": 41.4, "elapsed_time": "0:58:02", "remaining_time": "1:22:10"}
214
+ {"current_steps": 179, "total_steps": 430, "loss": 0.0073, "lr": 7.250039128987873e-05, "epoch": 2.069364161849711, "percentage": 41.63, "elapsed_time": "0:58:20", "remaining_time": "1:21:48"}
215
+ {"current_steps": 180, "total_steps": 430, "loss": 0.0056, "lr": 7.213718367282737e-05, "epoch": 2.0809248554913293, "percentage": 41.86, "elapsed_time": "0:58:37", "remaining_time": "1:21:25"}
216
+ {"current_steps": 180, "total_steps": 430, "eval_loss": 0.008958614431321621, "epoch": 2.0809248554913293, "percentage": 41.86, "elapsed_time": "0:58:47", "remaining_time": "1:21:39"}
217
+ {"current_steps": 181, "total_steps": 430, "loss": 0.0056, "lr": 7.177251724890956e-05, "epoch": 2.092485549132948, "percentage": 42.09, "elapsed_time": "0:59:04", "remaining_time": "1:21:16"}
218
+ {"current_steps": 182, "total_steps": 430, "loss": 0.0055, "lr": 7.14064160490902e-05, "epoch": 2.1040462427745665, "percentage": 42.33, "elapsed_time": "0:59:21", "remaining_time": "1:20:53"}
219
+ {"current_steps": 183, "total_steps": 430, "loss": 0.0053, "lr": 7.103890419888367e-05, "epoch": 2.115606936416185, "percentage": 42.56, "elapsed_time": "0:59:38", "remaining_time": "1:20:30"}
220
+ {"current_steps": 184, "total_steps": 430, "loss": 0.0065, "lr": 7.067000591676416e-05, "epoch": 2.1271676300578033, "percentage": 42.79, "elapsed_time": "0:59:56", "remaining_time": "1:20:08"}
221
+ {"current_steps": 185, "total_steps": 430, "loss": 0.0077, "lr": 7.029974551256956e-05, "epoch": 2.138728323699422, "percentage": 43.02, "elapsed_time": "1:00:13", "remaining_time": "1:19:45"}
222
+ {"current_steps": 185, "total_steps": 430, "eval_loss": 0.008626853115856647, "epoch": 2.138728323699422, "percentage": 43.02, "elapsed_time": "1:00:23", "remaining_time": "1:19:58"}
223
+ {"current_steps": 186, "total_steps": 430, "loss": 0.0057, "lr": 6.992814738589957e-05, "epoch": 2.1502890173410405, "percentage": 43.26, "elapsed_time": "1:00:40", "remaining_time": "1:19:35"}
224
+ {"current_steps": 187, "total_steps": 430, "loss": 0.0074, "lr": 6.95552360245078e-05, "epoch": 2.161849710982659, "percentage": 43.49, "elapsed_time": "1:00:57", "remaining_time": "1:19:13"}
225
+ {"current_steps": 188, "total_steps": 430, "loss": 0.0054, "lr": 6.918103600268799e-05, "epoch": 2.1734104046242773, "percentage": 43.72, "elapsed_time": "1:01:15", "remaining_time": "1:18:51"}
226
+ {"current_steps": 189, "total_steps": 430, "loss": 0.0053, "lr": 6.880557197965464e-05, "epoch": 2.184971098265896, "percentage": 43.95, "elapsed_time": "1:01:32", "remaining_time": "1:18:28"}
227
+ {"current_steps": 190, "total_steps": 430, "loss": 0.0061, "lr": 6.842886869791809e-05, "epoch": 2.1965317919075145, "percentage": 44.19, "elapsed_time": "1:01:50", "remaining_time": "1:18:07"}
228
+ {"current_steps": 190, "total_steps": 430, "eval_loss": 0.00858032051473856, "epoch": 2.1965317919075145, "percentage": 44.19, "elapsed_time": "1:02:00", "remaining_time": "1:18:19"}
229
+ {"current_steps": 191, "total_steps": 430, "loss": 0.0056, "lr": 6.805095098165389e-05, "epoch": 2.208092485549133, "percentage": 44.42, "elapsed_time": "1:02:17", "remaining_time": "1:17:57"}
230
+ {"current_steps": 192, "total_steps": 430, "loss": 0.008, "lr": 6.767184373506697e-05, "epoch": 2.2196531791907512, "percentage": 44.65, "elapsed_time": "1:02:35", "remaining_time": "1:17:34"}
231
+ {"current_steps": 193, "total_steps": 430, "loss": 0.0116, "lr": 6.729157194075057e-05, "epoch": 2.23121387283237, "percentage": 44.88, "elapsed_time": "1:02:52", "remaining_time": "1:17:12"}
232
+ {"current_steps": 194, "total_steps": 430, "loss": 0.0078, "lr": 6.691016065803983e-05, "epoch": 2.2427745664739884, "percentage": 45.12, "elapsed_time": "1:03:10", "remaining_time": "1:16:51"}
233
+ {"current_steps": 195, "total_steps": 430, "loss": 0.008, "lr": 6.652763502136043e-05, "epoch": 2.254335260115607, "percentage": 45.35, "elapsed_time": "1:03:27", "remaining_time": "1:16:28"}
234
+ {"current_steps": 195, "total_steps": 430, "eval_loss": 0.008329370059072971, "epoch": 2.254335260115607, "percentage": 45.35, "elapsed_time": "1:03:37", "remaining_time": "1:16:40"}
235
+ {"current_steps": 196, "total_steps": 430, "loss": 0.0057, "lr": 6.614402023857232e-05, "epoch": 2.2658959537572256, "percentage": 45.58, "elapsed_time": "1:03:55", "remaining_time": "1:16:19"}
236
+ {"current_steps": 197, "total_steps": 430, "loss": 0.0062, "lr": 6.57593415893085e-05, "epoch": 2.277456647398844, "percentage": 45.81, "elapsed_time": "1:04:13", "remaining_time": "1:15:57"}
237
+ {"current_steps": 198, "total_steps": 430, "loss": 0.0059, "lr": 6.537362442330916e-05, "epoch": 2.2890173410404624, "percentage": 46.05, "elapsed_time": "1:04:31", "remaining_time": "1:15:35"}
238
+ {"current_steps": 199, "total_steps": 430, "loss": 0.0054, "lr": 6.498689415875121e-05, "epoch": 2.300578034682081, "percentage": 46.28, "elapsed_time": "1:04:49", "remaining_time": "1:15:14"}
239
+ {"current_steps": 200, "total_steps": 430, "loss": 0.0058, "lr": 6.45991762805732e-05, "epoch": 2.3121387283236996, "percentage": 46.51, "elapsed_time": "1:05:07", "remaining_time": "1:14:53"}
240
+ {"current_steps": 200, "total_steps": 430, "eval_loss": 0.00831348542124033, "epoch": 2.3121387283236996, "percentage": 46.51, "elapsed_time": "1:05:17", "remaining_time": "1:15:04"}
241
+ {"current_steps": 201, "total_steps": 430, "loss": 0.005, "lr": 6.421049633879588e-05, "epoch": 2.3236994219653178, "percentage": 46.74, "elapsed_time": "1:05:41", "remaining_time": "1:14:50"}
242
+ {"current_steps": 202, "total_steps": 430, "loss": 0.0075, "lr": 6.382087994683859e-05, "epoch": 2.3352601156069364, "percentage": 46.98, "elapsed_time": "1:05:58", "remaining_time": "1:14:28"}
243
+ {"current_steps": 203, "total_steps": 430, "loss": 0.0068, "lr": 6.343035277983127e-05, "epoch": 2.346820809248555, "percentage": 47.21, "elapsed_time": "1:06:16", "remaining_time": "1:14:06"}
244
+ {"current_steps": 204, "total_steps": 430, "loss": 0.006, "lr": 6.303894057292261e-05, "epoch": 2.3583815028901736, "percentage": 47.44, "elapsed_time": "1:06:32", "remaining_time": "1:13:43"}
245
+ {"current_steps": 205, "total_steps": 430, "loss": 0.0047, "lr": 6.264666911958404e-05, "epoch": 2.3699421965317917, "percentage": 47.67, "elapsed_time": "1:06:48", "remaining_time": "1:13:19"}
246
+ {"current_steps": 205, "total_steps": 430, "eval_loss": 0.00836299266666174, "epoch": 2.3699421965317917, "percentage": 47.67, "elapsed_time": "1:06:58", "remaining_time": "1:13:30"}
247
+ {"current_steps": 206, "total_steps": 430, "loss": 0.0069, "lr": 6.225356426991007e-05, "epoch": 2.3815028901734103, "percentage": 47.91, "elapsed_time": "1:07:15", "remaining_time": "1:13:08"}
248
+ {"current_steps": 207, "total_steps": 430, "loss": 0.0055, "lr": 6.185965192891472e-05, "epoch": 2.393063583815029, "percentage": 48.14, "elapsed_time": "1:07:32", "remaining_time": "1:12:46"}
249
+ {"current_steps": 208, "total_steps": 430, "loss": 0.0062, "lr": 6.146495805482451e-05, "epoch": 2.4046242774566475, "percentage": 48.37, "elapsed_time": "1:07:49", "remaining_time": "1:12:23"}
250
+ {"current_steps": 209, "total_steps": 430, "loss": 0.0052, "lr": 6.106950865736777e-05, "epoch": 2.416184971098266, "percentage": 48.6, "elapsed_time": "1:08:07", "remaining_time": "1:12:01"}
251
+ {"current_steps": 210, "total_steps": 430, "loss": 0.0066, "lr": 6.0673329796060686e-05, "epoch": 2.4277456647398843, "percentage": 48.84, "elapsed_time": "1:08:25", "remaining_time": "1:11:40"}
252
+ {"current_steps": 210, "total_steps": 430, "eval_loss": 0.008446984924376011, "epoch": 2.4277456647398843, "percentage": 48.84, "elapsed_time": "1:08:35", "remaining_time": "1:11:51"}
253
+ {"current_steps": 211, "total_steps": 430, "loss": 0.0063, "lr": 6.0276447578490035e-05, "epoch": 2.439306358381503, "percentage": 49.07, "elapsed_time": "1:08:52", "remaining_time": "1:11:29"}
254
+ {"current_steps": 212, "total_steps": 430, "loss": 0.0058, "lr": 5.987888815859266e-05, "epoch": 2.4508670520231215, "percentage": 49.3, "elapsed_time": "1:09:06", "remaining_time": "1:11:04"}
255
+ {"current_steps": 213, "total_steps": 430, "loss": 0.0057, "lr": 5.9480677734932045e-05, "epoch": 2.4624277456647397, "percentage": 49.53, "elapsed_time": "1:09:23", "remaining_time": "1:10:41"}
256
+ {"current_steps": 214, "total_steps": 430, "loss": 0.0073, "lr": 5.908184254897182e-05, "epoch": 2.4739884393063583, "percentage": 49.77, "elapsed_time": "1:09:41", "remaining_time": "1:10:20"}
257
+ {"current_steps": 215, "total_steps": 430, "loss": 0.0055, "lr": 5.868240888334653e-05, "epoch": 2.485549132947977, "percentage": 50.0, "elapsed_time": "1:09:58", "remaining_time": "1:09:58"}
258
+ {"current_steps": 215, "total_steps": 430, "eval_loss": 0.008248448371887207, "epoch": 2.485549132947977, "percentage": 50.0, "elapsed_time": "1:10:08", "remaining_time": "1:10:08"}
259
+ {"current_steps": 216, "total_steps": 430, "loss": 0.0064, "lr": 5.8282403060129566e-05, "epoch": 2.4971098265895955, "percentage": 50.23, "elapsed_time": "1:10:26", "remaining_time": "1:09:47"}
260
+ {"current_steps": 217, "total_steps": 430, "loss": 0.006, "lr": 5.788185143909868e-05, "epoch": 2.508670520231214, "percentage": 50.47, "elapsed_time": "1:10:43", "remaining_time": "1:09:25"}
261
+ {"current_steps": 218, "total_steps": 430, "loss": 0.0053, "lr": 5.7480780415998906e-05, "epoch": 2.520231213872832, "percentage": 50.7, "elapsed_time": "1:11:01", "remaining_time": "1:09:03"}
262
+ {"current_steps": 219, "total_steps": 430, "loss": 0.0067, "lr": 5.707921642080299e-05, "epoch": 2.531791907514451, "percentage": 50.93, "elapsed_time": "1:11:17", "remaining_time": "1:08:41"}
263
+ {"current_steps": 220, "total_steps": 430, "loss": 0.0056, "lr": 5.66771859159699e-05, "epoch": 2.5433526011560694, "percentage": 51.16, "elapsed_time": "1:11:35", "remaining_time": "1:08:19"}
264
+ {"current_steps": 220, "total_steps": 430, "eval_loss": 0.008289137855172157, "epoch": 2.5433526011560694, "percentage": 51.16, "elapsed_time": "1:11:45", "remaining_time": "1:08:29"}
265
+ {"current_steps": 221, "total_steps": 430, "loss": 0.0057, "lr": 5.6274715394700805e-05, "epoch": 2.5549132947976876, "percentage": 51.4, "elapsed_time": "1:12:02", "remaining_time": "1:08:08"}
266
+ {"current_steps": 222, "total_steps": 430, "loss": 0.0066, "lr": 5.587183137919332e-05, "epoch": 2.5664739884393066, "percentage": 51.63, "elapsed_time": "1:12:20", "remaining_time": "1:07:46"}
267
+ {"current_steps": 223, "total_steps": 430, "loss": 0.0062, "lr": 5.546856041889373e-05, "epoch": 2.578034682080925, "percentage": 51.86, "elapsed_time": "1:12:38", "remaining_time": "1:07:25"}
268
+ {"current_steps": 224, "total_steps": 430, "loss": 0.0048, "lr": 5.5064929088747316e-05, "epoch": 2.5895953757225434, "percentage": 52.09, "elapsed_time": "1:12:56", "remaining_time": "1:07:05"}
269
+ {"current_steps": 225, "total_steps": 430, "loss": 0.005, "lr": 5.46609639874473e-05, "epoch": 2.601156069364162, "percentage": 52.33, "elapsed_time": "1:13:14", "remaining_time": "1:06:43"}
270
+ {"current_steps": 225, "total_steps": 430, "eval_loss": 0.008248119615018368, "epoch": 2.601156069364162, "percentage": 52.33, "elapsed_time": "1:13:24", "remaining_time": "1:06:52"}
271
+ {"current_steps": 226, "total_steps": 430, "loss": 0.006, "lr": 5.4256691735681786e-05, "epoch": 2.61271676300578, "percentage": 52.56, "elapsed_time": "1:13:42", "remaining_time": "1:06:31"}
272
+ {"current_steps": 227, "total_steps": 430, "loss": 0.0072, "lr": 5.385213897437975e-05, "epoch": 2.6242774566473988, "percentage": 52.79, "elapsed_time": "1:13:59", "remaining_time": "1:06:10"}
273
+ {"current_steps": 228, "total_steps": 430, "loss": 0.0056, "lr": 5.344733236295525e-05, "epoch": 2.6358381502890174, "percentage": 53.02, "elapsed_time": "1:14:16", "remaining_time": "1:05:48"}
274
+ {"current_steps": 229, "total_steps": 430, "loss": 0.007, "lr": 5.3042298577550696e-05, "epoch": 2.647398843930636, "percentage": 53.26, "elapsed_time": "1:14:34", "remaining_time": "1:05:27"}
275
+ {"current_steps": 230, "total_steps": 430, "loss": 0.0065, "lr": 5.263706430927895e-05, "epoch": 2.6589595375722546, "percentage": 53.49, "elapsed_time": "1:14:52", "remaining_time": "1:05:06"}
276
+ {"current_steps": 230, "total_steps": 430, "eval_loss": 0.00817356538027525, "epoch": 2.6589595375722546, "percentage": 53.49, "elapsed_time": "1:15:02", "remaining_time": "1:05:15"}
277
+ {"current_steps": 231, "total_steps": 430, "loss": 0.0056, "lr": 5.223165626246432e-05, "epoch": 2.6705202312138727, "percentage": 53.72, "elapsed_time": "1:15:19", "remaining_time": "1:04:53"}
278
+ {"current_steps": 232, "total_steps": 430, "loss": 0.0054, "lr": 5.182610115288295e-05, "epoch": 2.6820809248554913, "percentage": 53.95, "elapsed_time": "1:15:36", "remaining_time": "1:04:31"}
279
+ {"current_steps": 233, "total_steps": 430, "loss": 0.0048, "lr": 5.142042570600212e-05, "epoch": 2.69364161849711, "percentage": 54.19, "elapsed_time": "1:15:53", "remaining_time": "1:04:09"}
280
+ {"current_steps": 234, "total_steps": 430, "loss": 0.0074, "lr": 5.1014656655219197e-05, "epoch": 2.705202312138728, "percentage": 54.42, "elapsed_time": "1:16:10", "remaining_time": "1:03:48"}
281
+ {"current_steps": 235, "total_steps": 430, "loss": 0.0061, "lr": 5.060882074009988e-05, "epoch": 2.7167630057803467, "percentage": 54.65, "elapsed_time": "1:16:27", "remaining_time": "1:03:26"}
282
+ {"current_steps": 235, "total_steps": 430, "eval_loss": 0.00805756263434887, "epoch": 2.7167630057803467, "percentage": 54.65, "elapsed_time": "1:16:37", "remaining_time": "1:03:35"}
283
+ {"current_steps": 236, "total_steps": 430, "loss": 0.005, "lr": 5.020294470461615e-05, "epoch": 2.7283236994219653, "percentage": 54.88, "elapsed_time": "1:16:55", "remaining_time": "1:03:14"}
284
+ {"current_steps": 237, "total_steps": 430, "loss": 0.0065, "lr": 4.979705529538385e-05, "epoch": 2.739884393063584, "percentage": 55.12, "elapsed_time": "1:17:12", "remaining_time": "1:02:52"}
285
+ {"current_steps": 238, "total_steps": 430, "loss": 0.0047, "lr": 4.9391179259900125e-05, "epoch": 2.7514450867052025, "percentage": 55.35, "elapsed_time": "1:17:30", "remaining_time": "1:02:31"}
286
+ {"current_steps": 239, "total_steps": 430, "loss": 0.0055, "lr": 4.8985343344780815e-05, "epoch": 2.7630057803468207, "percentage": 55.58, "elapsed_time": "1:17:48", "remaining_time": "1:02:10"}
287
+ {"current_steps": 240, "total_steps": 430, "loss": 0.0052, "lr": 4.857957429399788e-05, "epoch": 2.7745664739884393, "percentage": 55.81, "elapsed_time": "1:18:05", "remaining_time": "1:01:49"}
288
+ {"current_steps": 240, "total_steps": 430, "eval_loss": 0.008152703754603863, "epoch": 2.7745664739884393, "percentage": 55.81, "elapsed_time": "1:18:15", "remaining_time": "1:01:57"}
289
+ {"current_steps": 241, "total_steps": 430, "loss": 0.0054, "lr": 4.817389884711705e-05, "epoch": 2.786127167630058, "percentage": 56.05, "elapsed_time": "1:18:31", "remaining_time": "1:01:34"}
290
+ {"current_steps": 242, "total_steps": 430, "loss": 0.0066, "lr": 4.776834373753569e-05, "epoch": 2.7976878612716765, "percentage": 56.28, "elapsed_time": "1:18:48", "remaining_time": "1:01:13"}
291
+ {"current_steps": 243, "total_steps": 430, "loss": 0.0064, "lr": 4.7362935690721076e-05, "epoch": 2.809248554913295, "percentage": 56.51, "elapsed_time": "1:19:05", "remaining_time": "1:00:51"}
292
+ {"current_steps": 244, "total_steps": 430, "loss": 0.0054, "lr": 4.695770142244931e-05, "epoch": 2.820809248554913, "percentage": 56.74, "elapsed_time": "1:19:22", "remaining_time": "1:00:30"}
293
+ {"current_steps": 245, "total_steps": 430, "loss": 0.0053, "lr": 4.655266763704476e-05, "epoch": 2.832369942196532, "percentage": 56.98, "elapsed_time": "1:19:40", "remaining_time": "1:00:09"}
294
+ {"current_steps": 245, "total_steps": 430, "eval_loss": 0.008140629157423973, "epoch": 2.832369942196532, "percentage": 56.98, "elapsed_time": "1:19:50", "remaining_time": "1:00:17"}
295
+ {"current_steps": 246, "total_steps": 430, "loss": 0.0048, "lr": 4.614786102562026e-05, "epoch": 2.8439306358381504, "percentage": 57.21, "elapsed_time": "1:20:08", "remaining_time": "0:59:56"}
296
+ {"current_steps": 247, "total_steps": 430, "loss": 0.005, "lr": 4.574330826431821e-05, "epoch": 2.8554913294797686, "percentage": 57.44, "elapsed_time": "1:20:25", "remaining_time": "0:59:35"}
297
+ {"current_steps": 248, "total_steps": 430, "loss": 0.0062, "lr": 4.5339036012552716e-05, "epoch": 2.867052023121387, "percentage": 57.67, "elapsed_time": "1:20:43", "remaining_time": "0:59:14"}
298
+ {"current_steps": 249, "total_steps": 430, "loss": 0.0056, "lr": 4.493507091125269e-05, "epoch": 2.878612716763006, "percentage": 57.91, "elapsed_time": "1:21:01", "remaining_time": "0:58:54"}
299
+ {"current_steps": 250, "total_steps": 430, "loss": 0.0058, "lr": 4.4531439581106295e-05, "epoch": 2.8901734104046244, "percentage": 58.14, "elapsed_time": "1:21:18", "remaining_time": "0:58:32"}
300
+ {"current_steps": 250, "total_steps": 430, "eval_loss": 0.007892865687608719, "epoch": 2.8901734104046244, "percentage": 58.14, "elapsed_time": "1:21:28", "remaining_time": "0:58:39"}
301
+ {"current_steps": 251, "total_steps": 430, "loss": 0.0064, "lr": 4.412816862080668e-05, "epoch": 2.901734104046243, "percentage": 58.37, "elapsed_time": "1:21:53", "remaining_time": "0:58:24"}
302
+ {"current_steps": 252, "total_steps": 430, "loss": 0.0057, "lr": 4.37252846052992e-05, "epoch": 2.913294797687861, "percentage": 58.6, "elapsed_time": "1:22:12", "remaining_time": "0:58:03"}
303
+ {"current_steps": 253, "total_steps": 430, "loss": 0.0056, "lr": 4.332281408403011e-05, "epoch": 2.9248554913294798, "percentage": 58.84, "elapsed_time": "1:22:27", "remaining_time": "0:57:41"}
304
+ {"current_steps": 254, "total_steps": 430, "loss": 0.0059, "lr": 4.292078357919701e-05, "epoch": 2.9364161849710984, "percentage": 59.07, "elapsed_time": "1:22:45", "remaining_time": "0:57:20"}
305
+ {"current_steps": 255, "total_steps": 430, "loss": 0.0052, "lr": 4.25192195840011e-05, "epoch": 2.9479768786127165, "percentage": 59.3, "elapsed_time": "1:23:03", "remaining_time": "0:57:00"}
306
+ {"current_steps": 255, "total_steps": 430, "eval_loss": 0.007827498018741608, "epoch": 2.9479768786127165, "percentage": 59.3, "elapsed_time": "1:23:13", "remaining_time": "0:57:07"}
307
+ {"current_steps": 256, "total_steps": 430, "loss": 0.0066, "lr": 4.2118148560901325e-05, "epoch": 2.959537572254335, "percentage": 59.53, "elapsed_time": "1:23:30", "remaining_time": "0:56:45"}
308
+ {"current_steps": 257, "total_steps": 430, "loss": 0.0062, "lr": 4.171759693987046e-05, "epoch": 2.9710982658959537, "percentage": 59.77, "elapsed_time": "1:23:47", "remaining_time": "0:56:24"}
309
+ {"current_steps": 258, "total_steps": 430, "loss": 0.0056, "lr": 4.131759111665349e-05, "epoch": 2.9826589595375723, "percentage": 60.0, "elapsed_time": "1:24:05", "remaining_time": "0:56:03"}
310
+ {"current_steps": 259, "total_steps": 430, "loss": 0.0053, "lr": 4.0918157451028185e-05, "epoch": 2.994219653179191, "percentage": 60.23, "elapsed_time": "1:24:22", "remaining_time": "0:55:42"}
311
+ {"current_steps": 260, "total_steps": 430, "loss": 0.0071, "lr": 4.051932226506797e-05, "epoch": 3.005780346820809, "percentage": 60.47, "elapsed_time": "1:24:38", "remaining_time": "0:55:20"}
312
+ {"current_steps": 260, "total_steps": 430, "eval_loss": 0.007992882281541824, "epoch": 3.005780346820809, "percentage": 60.47, "elapsed_time": "1:24:48", "remaining_time": "0:55:27"}
313
+ {"current_steps": 261, "total_steps": 430, "loss": 0.0051, "lr": 4.012111184140734e-05, "epoch": 3.0173410404624277, "percentage": 60.7, "elapsed_time": "1:25:05", "remaining_time": "0:55:06"}
314
+ {"current_steps": 262, "total_steps": 430, "loss": 0.0051, "lr": 3.972355242150998e-05, "epoch": 3.0289017341040463, "percentage": 60.93, "elapsed_time": "1:25:23", "remaining_time": "0:54:45"}
315
+ {"current_steps": 263, "total_steps": 430, "loss": 0.0039, "lr": 3.932667020393933e-05, "epoch": 3.040462427745665, "percentage": 61.16, "elapsed_time": "1:25:40", "remaining_time": "0:54:23"}
316
+ {"current_steps": 264, "total_steps": 430, "loss": 0.0035, "lr": 3.893049134263224e-05, "epoch": 3.052023121387283, "percentage": 61.4, "elapsed_time": "1:25:57", "remaining_time": "0:54:02"}
317
+ {"current_steps": 265, "total_steps": 430, "loss": 0.0051, "lr": 3.8535041945175506e-05, "epoch": 3.0635838150289016, "percentage": 61.63, "elapsed_time": "1:26:14", "remaining_time": "0:53:41"}
318
+ {"current_steps": 265, "total_steps": 430, "eval_loss": 0.008158711716532707, "epoch": 3.0635838150289016, "percentage": 61.63, "elapsed_time": "1:26:24", "remaining_time": "0:53:48"}
319
+ {"current_steps": 266, "total_steps": 430, "loss": 0.0034, "lr": 3.814034807108529e-05, "epoch": 3.0751445086705202, "percentage": 61.86, "elapsed_time": "1:26:41", "remaining_time": "0:53:26"}
320
+ {"current_steps": 267, "total_steps": 430, "loss": 0.0067, "lr": 3.774643573008995e-05, "epoch": 3.086705202312139, "percentage": 62.09, "elapsed_time": "1:26:59", "remaining_time": "0:53:06"}
321
+ {"current_steps": 268, "total_steps": 430, "loss": 0.0037, "lr": 3.735333088041596e-05, "epoch": 3.098265895953757, "percentage": 62.33, "elapsed_time": "1:27:16", "remaining_time": "0:52:45"}
322
+ {"current_steps": 269, "total_steps": 430, "loss": 0.0039, "lr": 3.69610594270774e-05, "epoch": 3.1098265895953756, "percentage": 62.56, "elapsed_time": "1:27:34", "remaining_time": "0:52:24"}
323
+ {"current_steps": 270, "total_steps": 430, "loss": 0.0033, "lr": 3.656964722016875e-05, "epoch": 3.121387283236994, "percentage": 62.79, "elapsed_time": "1:27:51", "remaining_time": "0:52:04"}
324
+ {"current_steps": 270, "total_steps": 430, "eval_loss": 0.00860854797065258, "epoch": 3.121387283236994, "percentage": 62.79, "elapsed_time": "1:28:01", "remaining_time": "0:52:09"}
325
+ {"current_steps": 271, "total_steps": 430, "loss": 0.0044, "lr": 3.6179120053161416e-05, "epoch": 3.132947976878613, "percentage": 63.02, "elapsed_time": "1:28:19", "remaining_time": "0:51:49"}
326
+ {"current_steps": 272, "total_steps": 430, "loss": 0.004, "lr": 3.578950366120414e-05, "epoch": 3.1445086705202314, "percentage": 63.26, "elapsed_time": "1:28:36", "remaining_time": "0:51:28"}
327
+ {"current_steps": 273, "total_steps": 430, "loss": 0.0038, "lr": 3.5400823719426815e-05, "epoch": 3.1560693641618496, "percentage": 63.49, "elapsed_time": "1:28:54", "remaining_time": "0:51:07"}
328
+ {"current_steps": 274, "total_steps": 430, "loss": 0.0036, "lr": 3.5013105841248795e-05, "epoch": 3.167630057803468, "percentage": 63.72, "elapsed_time": "1:29:11", "remaining_time": "0:50:47"}
329
+ {"current_steps": 275, "total_steps": 430, "loss": 0.004, "lr": 3.462637557669084e-05, "epoch": 3.179190751445087, "percentage": 63.95, "elapsed_time": "1:29:30", "remaining_time": "0:50:26"}
330
+ {"current_steps": 275, "total_steps": 430, "eval_loss": 0.008404241874814034, "epoch": 3.179190751445087, "percentage": 63.95, "elapsed_time": "1:29:40", "remaining_time": "0:50:32"}
331
+ {"current_steps": 276, "total_steps": 430, "loss": 0.0049, "lr": 3.424065841069152e-05, "epoch": 3.1907514450867054, "percentage": 64.19, "elapsed_time": "1:29:58", "remaining_time": "0:50:12"}
332
+ {"current_steps": 277, "total_steps": 430, "loss": 0.0039, "lr": 3.38559797614277e-05, "epoch": 3.2023121387283235, "percentage": 64.42, "elapsed_time": "1:30:15", "remaining_time": "0:49:51"}
333
+ {"current_steps": 278, "total_steps": 430, "loss": 0.0042, "lr": 3.347236497863957e-05, "epoch": 3.213872832369942, "percentage": 64.65, "elapsed_time": "1:30:32", "remaining_time": "0:49:30"}
334
+ {"current_steps": 279, "total_steps": 430, "loss": 0.0044, "lr": 3.308983934196018e-05, "epoch": 3.2254335260115607, "percentage": 64.88, "elapsed_time": "1:30:50", "remaining_time": "0:49:10"}
335
+ {"current_steps": 280, "total_steps": 430, "loss": 0.0032, "lr": 3.2708428059249436e-05, "epoch": 3.2369942196531793, "percentage": 65.12, "elapsed_time": "1:31:08", "remaining_time": "0:48:49"}
336
+ {"current_steps": 280, "total_steps": 430, "eval_loss": 0.008181248791515827, "epoch": 3.2369942196531793, "percentage": 65.12, "elapsed_time": "1:31:18", "remaining_time": "0:48:54"}
337
+ {"current_steps": 281, "total_steps": 430, "loss": 0.0054, "lr": 3.232815626493304e-05, "epoch": 3.2485549132947975, "percentage": 65.35, "elapsed_time": "1:31:35", "remaining_time": "0:48:34"}
338
+ {"current_steps": 282, "total_steps": 430, "loss": 0.0052, "lr": 3.1949049018346126e-05, "epoch": 3.260115606936416, "percentage": 65.58, "elapsed_time": "1:31:53", "remaining_time": "0:48:13"}
339
+ {"current_steps": 283, "total_steps": 430, "loss": 0.0049, "lr": 3.157113130208191e-05, "epoch": 3.2716763005780347, "percentage": 65.81, "elapsed_time": "1:32:09", "remaining_time": "0:47:52"}
340
+ {"current_steps": 284, "total_steps": 430, "loss": 0.0039, "lr": 3.1194428020345376e-05, "epoch": 3.2832369942196533, "percentage": 66.05, "elapsed_time": "1:32:25", "remaining_time": "0:47:31"}
341
+ {"current_steps": 285, "total_steps": 430, "loss": 0.0042, "lr": 3.081896399731202e-05, "epoch": 3.294797687861272, "percentage": 66.28, "elapsed_time": "1:32:43", "remaining_time": "0:47:10"}
342
+ {"current_steps": 285, "total_steps": 430, "eval_loss": 0.008185806684195995, "epoch": 3.294797687861272, "percentage": 66.28, "elapsed_time": "1:32:53", "remaining_time": "0:47:15"}
343
+ {"current_steps": 286, "total_steps": 430, "loss": 0.0045, "lr": 3.0444763975492208e-05, "epoch": 3.30635838150289, "percentage": 66.51, "elapsed_time": "1:33:10", "remaining_time": "0:46:54"}
344
+ {"current_steps": 287, "total_steps": 430, "loss": 0.0036, "lr": 3.0071852614100426e-05, "epoch": 3.3179190751445087, "percentage": 66.74, "elapsed_time": "1:33:29", "remaining_time": "0:46:34"}
345
+ {"current_steps": 288, "total_steps": 430, "loss": 0.0044, "lr": 2.9700254487430444e-05, "epoch": 3.3294797687861273, "percentage": 66.98, "elapsed_time": "1:33:47", "remaining_time": "0:46:14"}
346
+ {"current_steps": 289, "total_steps": 430, "loss": 0.0055, "lr": 2.9329994083235857e-05, "epoch": 3.3410404624277454, "percentage": 67.21, "elapsed_time": "1:34:04", "remaining_time": "0:45:53"}
347
+ {"current_steps": 290, "total_steps": 430, "loss": 0.0035, "lr": 2.896109580111634e-05, "epoch": 3.352601156069364, "percentage": 67.44, "elapsed_time": "1:34:21", "remaining_time": "0:45:32"}
348
+ {"current_steps": 290, "total_steps": 430, "eval_loss": 0.008166169747710228, "epoch": 3.352601156069364, "percentage": 67.44, "elapsed_time": "1:34:31", "remaining_time": "0:45:37"}
349
+ {"current_steps": 291, "total_steps": 430, "loss": 0.0042, "lr": 2.859358395090983e-05, "epoch": 3.3641618497109826, "percentage": 67.67, "elapsed_time": "1:34:49", "remaining_time": "0:45:17"}
350
+ {"current_steps": 292, "total_steps": 430, "loss": 0.0043, "lr": 2.8227482751090445e-05, "epoch": 3.3757225433526012, "percentage": 67.91, "elapsed_time": "1:35:07", "remaining_time": "0:44:57"}
351
+ {"current_steps": 293, "total_steps": 430, "loss": 0.0037, "lr": 2.7862816327172636e-05, "epoch": 3.38728323699422, "percentage": 68.14, "elapsed_time": "1:35:24", "remaining_time": "0:44:36"}
352
+ {"current_steps": 294, "total_steps": 430, "loss": 0.0042, "lr": 2.7499608710121288e-05, "epoch": 3.398843930635838, "percentage": 68.37, "elapsed_time": "1:35:40", "remaining_time": "0:44:15"}
353
+ {"current_steps": 295, "total_steps": 430, "loss": 0.0041, "lr": 2.7137883834768073e-05, "epoch": 3.4104046242774566, "percentage": 68.6, "elapsed_time": "1:35:57", "remaining_time": "0:43:54"}
354
+ {"current_steps": 295, "total_steps": 430, "eval_loss": 0.008127645589411259, "epoch": 3.4104046242774566, "percentage": 68.6, "elapsed_time": "1:36:07", "remaining_time": "0:43:59"}
355
+ {"current_steps": 296, "total_steps": 430, "loss": 0.004, "lr": 2.6777665538234293e-05, "epoch": 3.421965317919075, "percentage": 68.84, "elapsed_time": "1:36:24", "remaining_time": "0:43:38"}
356
+ {"current_steps": 297, "total_steps": 430, "loss": 0.0046, "lr": 2.641897755835997e-05, "epoch": 3.433526011560694, "percentage": 69.07, "elapsed_time": "1:36:42", "remaining_time": "0:43:18"}
357
+ {"current_steps": 298, "total_steps": 430, "loss": 0.0039, "lr": 2.606184353213956e-05, "epoch": 3.445086705202312, "percentage": 69.3, "elapsed_time": "1:36:59", "remaining_time": "0:42:57"}
358
+ {"current_steps": 299, "total_steps": 430, "loss": 0.0037, "lr": 2.5706286994164315e-05, "epoch": 3.4566473988439306, "percentage": 69.53, "elapsed_time": "1:37:17", "remaining_time": "0:42:37"}
359
+ {"current_steps": 300, "total_steps": 430, "loss": 0.0048, "lr": 2.5352331375071437e-05, "epoch": 3.468208092485549, "percentage": 69.77, "elapsed_time": "1:37:34", "remaining_time": "0:42:16"}
360
+ {"current_steps": 300, "total_steps": 430, "eval_loss": 0.007986278273165226, "epoch": 3.468208092485549, "percentage": 69.77, "elapsed_time": "1:37:44", "remaining_time": "0:42:21"}
361
+ {"current_steps": 301, "total_steps": 430, "loss": 0.0034, "lr": 2.500000000000001e-05, "epoch": 3.479768786127168, "percentage": 70.0, "elapsed_time": "1:38:08", "remaining_time": "0:42:03"}
362
+ {"current_steps": 302, "total_steps": 430, "loss": 0.0041, "lr": 2.4649316087053837e-05, "epoch": 3.491329479768786, "percentage": 70.23, "elapsed_time": "1:38:27", "remaining_time": "0:41:43"}
363
+ {"current_steps": 303, "total_steps": 430, "loss": 0.0034, "lr": 2.4300302745771507e-05, "epoch": 3.5028901734104045, "percentage": 70.47, "elapsed_time": "1:38:44", "remaining_time": "0:41:23"}
364
+ {"current_steps": 304, "total_steps": 430, "loss": 0.0043, "lr": 2.3952982975603496e-05, "epoch": 3.514450867052023, "percentage": 70.7, "elapsed_time": "1:39:03", "remaining_time": "0:41:03"}
365
+ {"current_steps": 305, "total_steps": 430, "loss": 0.0046, "lr": 2.360737966439641e-05, "epoch": 3.5260115606936417, "percentage": 70.93, "elapsed_time": "1:39:21", "remaining_time": "0:40:43"}
366
+ {"current_steps": 305, "total_steps": 430, "eval_loss": 0.00799076072871685, "epoch": 3.5260115606936417, "percentage": 70.93, "elapsed_time": "1:39:31", "remaining_time": "0:40:47"}
367
+ {"current_steps": 306, "total_steps": 430, "loss": 0.0047, "lr": 2.326351558688493e-05, "epoch": 3.5375722543352603, "percentage": 71.16, "elapsed_time": "1:39:49", "remaining_time": "0:40:27"}
368
+ {"current_steps": 307, "total_steps": 430, "loss": 0.0046, "lr": 2.2921413403190772e-05, "epoch": 3.5491329479768785, "percentage": 71.4, "elapsed_time": "1:40:07", "remaining_time": "0:40:06"}
369
+ {"current_steps": 308, "total_steps": 430, "loss": 0.0033, "lr": 2.2581095657329598e-05, "epoch": 3.560693641618497, "percentage": 71.63, "elapsed_time": "1:40:23", "remaining_time": "0:39:46"}
370
+ {"current_steps": 309, "total_steps": 430, "loss": 0.0037, "lr": 2.224258477572524e-05, "epoch": 3.5722543352601157, "percentage": 71.86, "elapsed_time": "1:40:41", "remaining_time": "0:39:25"}
371
+ {"current_steps": 310, "total_steps": 430, "loss": 0.004, "lr": 2.1905903065731974e-05, "epoch": 3.583815028901734, "percentage": 72.09, "elapsed_time": "1:40:58", "remaining_time": "0:39:05"}
372
+ {"current_steps": 310, "total_steps": 430, "eval_loss": 0.007966941222548485, "epoch": 3.583815028901734, "percentage": 72.09, "elapsed_time": "1:41:08", "remaining_time": "0:39:09"}
373
+ {"current_steps": 311, "total_steps": 430, "loss": 0.0035, "lr": 2.1571072714164443e-05, "epoch": 3.5953757225433525, "percentage": 72.33, "elapsed_time": "1:41:25", "remaining_time": "0:38:48"}
374
+ {"current_steps": 312, "total_steps": 430, "loss": 0.0056, "lr": 2.123811578583551e-05, "epoch": 3.606936416184971, "percentage": 72.56, "elapsed_time": "1:41:43", "remaining_time": "0:38:28"}
375
+ {"current_steps": 313, "total_steps": 430, "loss": 0.0043, "lr": 2.090705422210237e-05, "epoch": 3.6184971098265897, "percentage": 72.79, "elapsed_time": "1:42:00", "remaining_time": "0:38:07"}
376
+ {"current_steps": 314, "total_steps": 430, "loss": 0.0049, "lr": 2.057790983942047e-05, "epoch": 3.6300578034682083, "percentage": 73.02, "elapsed_time": "1:42:17", "remaining_time": "0:37:47"}
377
+ {"current_steps": 315, "total_steps": 430, "loss": 0.0032, "lr": 2.0250704327906024e-05, "epoch": 3.6416184971098264, "percentage": 73.26, "elapsed_time": "1:42:33", "remaining_time": "0:37:26"}
378
+ {"current_steps": 315, "total_steps": 430, "eval_loss": 0.008140211924910545, "epoch": 3.6416184971098264, "percentage": 73.26, "elapsed_time": "1:42:43", "remaining_time": "0:37:30"}
379
+ {"current_steps": 316, "total_steps": 430, "loss": 0.0037, "lr": 1.9925459249906485e-05, "epoch": 3.653179190751445, "percentage": 73.49, "elapsed_time": "1:43:01", "remaining_time": "0:37:09"}
380
+ {"current_steps": 317, "total_steps": 430, "loss": 0.0048, "lr": 1.960219603857977e-05, "epoch": 3.6647398843930636, "percentage": 73.72, "elapsed_time": "1:43:17", "remaining_time": "0:36:49"}
381
+ {"current_steps": 318, "total_steps": 430, "loss": 0.0047, "lr": 1.928093599648179e-05, "epoch": 3.6763005780346822, "percentage": 73.95, "elapsed_time": "1:43:34", "remaining_time": "0:36:28"}
382
+ {"current_steps": 319, "total_steps": 430, "loss": 0.0034, "lr": 1.8961700294162577e-05, "epoch": 3.687861271676301, "percentage": 74.19, "elapsed_time": "1:43:51", "remaining_time": "0:36:08"}
383
+ {"current_steps": 320, "total_steps": 430, "loss": 0.0039, "lr": 1.86445099687713e-05, "epoch": 3.699421965317919, "percentage": 74.42, "elapsed_time": "1:44:08", "remaining_time": "0:35:48"}
384
+ {"current_steps": 320, "total_steps": 430, "eval_loss": 0.008361711166799068, "epoch": 3.699421965317919, "percentage": 74.42, "elapsed_time": "1:44:18", "remaining_time": "0:35:51"}
385
+ {"current_steps": 321, "total_steps": 430, "loss": 0.0037, "lr": 1.832938592266984e-05, "epoch": 3.7109826589595376, "percentage": 74.65, "elapsed_time": "1:44:36", "remaining_time": "0:35:31"}
386
+ {"current_steps": 322, "total_steps": 430, "loss": 0.0041, "lr": 1.801634892205545e-05, "epoch": 3.722543352601156, "percentage": 74.88, "elapsed_time": "1:44:53", "remaining_time": "0:35:10"}
387
+ {"current_steps": 323, "total_steps": 430, "loss": 0.0037, "lr": 1.7705419595592193e-05, "epoch": 3.7341040462427744, "percentage": 75.12, "elapsed_time": "1:45:11", "remaining_time": "0:34:50"}
388
+ {"current_steps": 324, "total_steps": 430, "loss": 0.0043, "lr": 1.7396618433051647e-05, "epoch": 3.745664739884393, "percentage": 75.35, "elapsed_time": "1:45:28", "remaining_time": "0:34:30"}
389
+ {"current_steps": 325, "total_steps": 430, "loss": 0.0042, "lr": 1.7089965783962608e-05, "epoch": 3.7572254335260116, "percentage": 75.58, "elapsed_time": "1:45:46", "remaining_time": "0:34:10"}
390
+ {"current_steps": 325, "total_steps": 430, "eval_loss": 0.008260131813585758, "epoch": 3.7572254335260116, "percentage": 75.58, "elapsed_time": "1:45:56", "remaining_time": "0:34:13"}
391
+ {"current_steps": 326, "total_steps": 430, "loss": 0.0043, "lr": 1.678548185627004e-05, "epoch": 3.76878612716763, "percentage": 75.81, "elapsed_time": "1:46:14", "remaining_time": "0:33:53"}
392
+ {"current_steps": 327, "total_steps": 430, "loss": 0.0035, "lr": 1.6483186715003523e-05, "epoch": 3.7803468208092488, "percentage": 76.05, "elapsed_time": "1:46:30", "remaining_time": "0:33:32"}
393
+ {"current_steps": 328, "total_steps": 430, "loss": 0.0039, "lr": 1.618310028095486e-05, "epoch": 3.791907514450867, "percentage": 76.28, "elapsed_time": "1:46:48", "remaining_time": "0:33:12"}
394
+ {"current_steps": 329, "total_steps": 430, "loss": 0.0033, "lr": 1.5885242329365448e-05, "epoch": 3.8034682080924855, "percentage": 76.51, "elapsed_time": "1:47:05", "remaining_time": "0:32:52"}
395
+ {"current_steps": 330, "total_steps": 430, "loss": 0.0046, "lr": 1.5589632488623053e-05, "epoch": 3.815028901734104, "percentage": 76.74, "elapsed_time": "1:47:23", "remaining_time": "0:32:32"}
396
+ {"current_steps": 330, "total_steps": 430, "eval_loss": 0.008042494766414165, "epoch": 3.815028901734104, "percentage": 76.74, "elapsed_time": "1:47:34", "remaining_time": "0:32:35"}
397
+ {"current_steps": 331, "total_steps": 430, "loss": 0.0032, "lr": 1.5296290238968303e-05, "epoch": 3.8265895953757223, "percentage": 76.98, "elapsed_time": "1:47:50", "remaining_time": "0:32:15"}
398
+ {"current_steps": 332, "total_steps": 430, "loss": 0.0035, "lr": 1.500523491121108e-05, "epoch": 3.838150289017341, "percentage": 77.21, "elapsed_time": "1:48:08", "remaining_time": "0:31:55"}
399
+ {"current_steps": 333, "total_steps": 430, "loss": 0.0038, "lr": 1.47164856854565e-05, "epoch": 3.8497109826589595, "percentage": 77.44, "elapsed_time": "1:48:26", "remaining_time": "0:31:35"}
400
+ {"current_steps": 334, "total_steps": 430, "loss": 0.0034, "lr": 1.4430061589841121e-05, "epoch": 3.861271676300578, "percentage": 77.67, "elapsed_time": "1:48:43", "remaining_time": "0:31:14"}
401
+ {"current_steps": 335, "total_steps": 430, "loss": 0.0035, "lr": 1.4145981499278876e-05, "epoch": 3.8728323699421967, "percentage": 77.91, "elapsed_time": "1:49:01", "remaining_time": "0:30:54"}
402
+ {"current_steps": 335, "total_steps": 430, "eval_loss": 0.008081013336777687, "epoch": 3.8728323699421967, "percentage": 77.91, "elapsed_time": "1:49:11", "remaining_time": "0:30:57"}
403
+ {"current_steps": 336, "total_steps": 430, "loss": 0.004, "lr": 1.386426413421738e-05, "epoch": 3.884393063583815, "percentage": 78.14, "elapsed_time": "1:49:29", "remaining_time": "0:30:37"}
404
+ {"current_steps": 337, "total_steps": 430, "loss": 0.0034, "lr": 1.3584928059404205e-05, "epoch": 3.8959537572254335, "percentage": 78.37, "elapsed_time": "1:49:46", "remaining_time": "0:30:17"}
405
+ {"current_steps": 338, "total_steps": 430, "loss": 0.0031, "lr": 1.3307991682663462e-05, "epoch": 3.907514450867052, "percentage": 78.6, "elapsed_time": "1:50:01", "remaining_time": "0:29:56"}
406
+ {"current_steps": 339, "total_steps": 430, "loss": 0.0034, "lr": 1.3033473253682848e-05, "epoch": 3.9190751445086707, "percentage": 78.84, "elapsed_time": "1:50:17", "remaining_time": "0:29:36"}
407
+ {"current_steps": 340, "total_steps": 430, "loss": 0.0048, "lr": 1.2761390862810907e-05, "epoch": 3.9306358381502893, "percentage": 79.07, "elapsed_time": "1:50:34", "remaining_time": "0:29:16"}
408
+ {"current_steps": 340, "total_steps": 430, "eval_loss": 0.008075674995779991, "epoch": 3.9306358381502893, "percentage": 79.07, "elapsed_time": "1:50:44", "remaining_time": "0:29:18"}
409
+ {"current_steps": 341, "total_steps": 430, "loss": 0.003, "lr": 1.2491762439865035e-05, "epoch": 3.9421965317919074, "percentage": 79.3, "elapsed_time": "1:51:02", "remaining_time": "0:28:58"}
410
+ {"current_steps": 342, "total_steps": 430, "loss": 0.0028, "lr": 1.2224605752949786e-05, "epoch": 3.953757225433526, "percentage": 79.53, "elapsed_time": "1:51:19", "remaining_time": "0:28:38"}
411
+ {"current_steps": 343, "total_steps": 430, "loss": 0.0037, "lr": 1.1959938407286097e-05, "epoch": 3.9653179190751446, "percentage": 79.77, "elapsed_time": "1:51:37", "remaining_time": "0:28:18"}
412
+ {"current_steps": 344, "total_steps": 430, "loss": 0.0036, "lr": 1.1697777844051105e-05, "epoch": 3.976878612716763, "percentage": 80.0, "elapsed_time": "1:51:55", "remaining_time": "0:27:58"}
413
+ {"current_steps": 345, "total_steps": 430, "loss": 0.0056, "lr": 1.143814133922872e-05, "epoch": 3.9884393063583814, "percentage": 80.23, "elapsed_time": "1:52:12", "remaining_time": "0:27:38"}
414
+ {"current_steps": 345, "total_steps": 430, "eval_loss": 0.008018155582249165, "epoch": 3.9884393063583814, "percentage": 80.23, "elapsed_time": "1:52:22", "remaining_time": "0:27:41"}
415
+ {"current_steps": 346, "total_steps": 430, "loss": 0.0065, "lr": 1.118104600247129e-05, "epoch": 4.0, "percentage": 80.47, "elapsed_time": "1:52:38", "remaining_time": "0:27:20"}
416
+ {"current_steps": 347, "total_steps": 430, "loss": 0.0029, "lr": 1.0926508775971994e-05, "epoch": 4.011560693641618, "percentage": 80.7, "elapsed_time": "1:52:57", "remaining_time": "0:27:01"}
417
+ {"current_steps": 348, "total_steps": 430, "loss": 0.0028, "lr": 1.0674546433348454e-05, "epoch": 4.023121387283237, "percentage": 80.93, "elapsed_time": "1:53:15", "remaining_time": "0:26:41"}
418
+ {"current_steps": 349, "total_steps": 430, "loss": 0.0033, "lr": 1.0425175578537299e-05, "epoch": 4.034682080924855, "percentage": 81.16, "elapsed_time": "1:53:33", "remaining_time": "0:26:21"}
419
+ {"current_steps": 350, "total_steps": 430, "loss": 0.0025, "lr": 1.0178412644700092e-05, "epoch": 4.046242774566474, "percentage": 81.4, "elapsed_time": "1:53:51", "remaining_time": "0:26:01"}
420
+ {"current_steps": 350, "total_steps": 430, "eval_loss": 0.008002113550901413, "epoch": 4.046242774566474, "percentage": 81.4, "elapsed_time": "1:54:01", "remaining_time": "0:26:03"}
421
+ {"current_steps": 351, "total_steps": 430, "loss": 0.0027, "lr": 9.934273893140334e-06, "epoch": 4.057803468208093, "percentage": 81.63, "elapsed_time": "1:54:30", "remaining_time": "0:25:46"}
422
+ {"current_steps": 352, "total_steps": 430, "loss": 0.0027, "lr": 9.692775412231863e-06, "epoch": 4.069364161849711, "percentage": 81.86, "elapsed_time": "1:54:46", "remaining_time": "0:25:26"}
423
+ {"current_steps": 353, "total_steps": 430, "loss": 0.0024, "lr": 9.453933116358715e-06, "epoch": 4.08092485549133, "percentage": 82.09, "elapsed_time": "1:55:03", "remaining_time": "0:25:05"}
424
+ {"current_steps": 354, "total_steps": 430, "loss": 0.0028, "lr": 9.21776274486636e-06, "epoch": 4.092485549132948, "percentage": 82.33, "elapsed_time": "1:55:22", "remaining_time": "0:24:46"}
425
+ {"current_steps": 355, "total_steps": 430, "loss": 0.0035, "lr": 8.984279861024453e-06, "epoch": 4.104046242774566, "percentage": 82.56, "elapsed_time": "1:55:38", "remaining_time": "0:24:25"}
426
+ {"current_steps": 355, "total_steps": 430, "eval_loss": 0.008168390020728111, "epoch": 4.104046242774566, "percentage": 82.56, "elapsed_time": "1:55:48", "remaining_time": "0:24:28"}
427
+ {"current_steps": 356, "total_steps": 430, "loss": 0.0034, "lr": 8.75349985100134e-06, "epoch": 4.115606936416185, "percentage": 82.79, "elapsed_time": "1:56:05", "remaining_time": "0:24:07"}
428
+ {"current_steps": 357, "total_steps": 430, "loss": 0.0025, "lr": 8.525437922850032e-06, "epoch": 4.127167630057803, "percentage": 83.02, "elapsed_time": "1:56:22", "remaining_time": "0:23:47"}
429
+ {"current_steps": 358, "total_steps": 430, "loss": 0.0025, "lr": 8.30010910550611e-06, "epoch": 4.138728323699422, "percentage": 83.26, "elapsed_time": "1:56:39", "remaining_time": "0:23:27"}
430
+ {"current_steps": 359, "total_steps": 430, "loss": 0.0029, "lr": 8.077528247797234e-06, "epoch": 4.1502890173410405, "percentage": 83.49, "elapsed_time": "1:56:57", "remaining_time": "0:23:07"}
431
+ {"current_steps": 360, "total_steps": 430, "loss": 0.0028, "lr": 7.857710017464737e-06, "epoch": 4.161849710982659, "percentage": 83.72, "elapsed_time": "1:57:15", "remaining_time": "0:22:48"}
432
+ {"current_steps": 360, "total_steps": 430, "eval_loss": 0.00829649344086647, "epoch": 4.161849710982659, "percentage": 83.72, "elapsed_time": "1:57:25", "remaining_time": "0:22:49"}
433
+ {"current_steps": 361, "total_steps": 430, "loss": 0.0041, "lr": 7.640668900196984e-06, "epoch": 4.173410404624278, "percentage": 83.95, "elapsed_time": "1:57:43", "remaining_time": "0:22:30"}
434
+ {"current_steps": 362, "total_steps": 430, "loss": 0.0025, "lr": 7.426419198674772e-06, "epoch": 4.184971098265896, "percentage": 84.19, "elapsed_time": "1:58:00", "remaining_time": "0:22:10"}
435
+ {"current_steps": 363, "total_steps": 430, "loss": 0.0036, "lr": 7.214975031628857e-06, "epoch": 4.196531791907514, "percentage": 84.42, "elapsed_time": "1:58:17", "remaining_time": "0:21:49"}
436
+ {"current_steps": 364, "total_steps": 430, "loss": 0.0027, "lr": 7.006350332909495e-06, "epoch": 4.208092485549133, "percentage": 84.65, "elapsed_time": "1:58:35", "remaining_time": "0:21:30"}
437
+ {"current_steps": 365, "total_steps": 430, "loss": 0.0028, "lr": 6.800558850568295e-06, "epoch": 4.219653179190751, "percentage": 84.88, "elapsed_time": "1:58:53", "remaining_time": "0:21:10"}
438
+ {"current_steps": 365, "total_steps": 430, "eval_loss": 0.008427992463111877, "epoch": 4.219653179190751, "percentage": 84.88, "elapsed_time": "1:59:03", "remaining_time": "0:21:12"}
439
+ {"current_steps": 366, "total_steps": 430, "loss": 0.0026, "lr": 6.5976141459521355e-06, "epoch": 4.23121387283237, "percentage": 85.12, "elapsed_time": "1:59:19", "remaining_time": "0:20:51"}
440
+ {"current_steps": 367, "total_steps": 430, "loss": 0.0034, "lr": 6.397529592809614e-06, "epoch": 4.242774566473988, "percentage": 85.35, "elapsed_time": "1:59:36", "remaining_time": "0:20:31"}
441
+ {"current_steps": 368, "total_steps": 430, "loss": 0.0025, "lr": 6.2003183764096695e-06, "epoch": 4.254335260115607, "percentage": 85.58, "elapsed_time": "1:59:53", "remaining_time": "0:20:11"}
442
+ {"current_steps": 369, "total_steps": 430, "loss": 0.0037, "lr": 6.005993492672657e-06, "epoch": 4.265895953757226, "percentage": 85.81, "elapsed_time": "2:00:11", "remaining_time": "0:19:52"}
443
+ {"current_steps": 370, "total_steps": 430, "loss": 0.003, "lr": 5.814567747314048e-06, "epoch": 4.277456647398844, "percentage": 86.05, "elapsed_time": "2:00:28", "remaining_time": "0:19:32"}
444
+ {"current_steps": 370, "total_steps": 430, "eval_loss": 0.008522397838532925, "epoch": 4.277456647398844, "percentage": 86.05, "elapsed_time": "2:00:38", "remaining_time": "0:19:33"}
445
+ {"current_steps": 371, "total_steps": 430, "loss": 0.0021, "lr": 5.626053755000421e-06, "epoch": 4.289017341040463, "percentage": 86.28, "elapsed_time": "2:00:57", "remaining_time": "0:19:14"}
446
+ {"current_steps": 372, "total_steps": 430, "loss": 0.003, "lr": 5.440463938518303e-06, "epoch": 4.300578034682081, "percentage": 86.51, "elapsed_time": "2:01:14", "remaining_time": "0:18:54"}
447
+ {"current_steps": 373, "total_steps": 430, "loss": 0.0027, "lr": 5.257810527955409e-06, "epoch": 4.312138728323699, "percentage": 86.74, "elapsed_time": "2:01:31", "remaining_time": "0:18:34"}
448
+ {"current_steps": 374, "total_steps": 430, "loss": 0.0025, "lr": 5.078105559894791e-06, "epoch": 4.323699421965318, "percentage": 86.98, "elapsed_time": "2:01:48", "remaining_time": "0:18:14"}
449
+ {"current_steps": 375, "total_steps": 430, "loss": 0.0033, "lr": 4.901360876621597e-06, "epoch": 4.335260115606936, "percentage": 87.21, "elapsed_time": "2:02:06", "remaining_time": "0:17:54"}
450
+ {"current_steps": 375, "total_steps": 430, "eval_loss": 0.008536826819181442, "epoch": 4.335260115606936, "percentage": 87.21, "elapsed_time": "2:02:16", "remaining_time": "0:17:56"}
451
+ {"current_steps": 376, "total_steps": 430, "loss": 0.0022, "lr": 4.727588125342669e-06, "epoch": 4.3468208092485545, "percentage": 87.44, "elapsed_time": "2:02:34", "remaining_time": "0:17:36"}
452
+ {"current_steps": 377, "total_steps": 430, "loss": 0.0025, "lr": 4.556798757419068e-06, "epoch": 4.358381502890174, "percentage": 87.67, "elapsed_time": "2:02:51", "remaining_time": "0:17:16"}
453
+ {"current_steps": 378, "total_steps": 430, "loss": 0.0027, "lr": 4.389004027611404e-06, "epoch": 4.369942196531792, "percentage": 87.91, "elapsed_time": "2:03:08", "remaining_time": "0:16:56"}
454
+ {"current_steps": 379, "total_steps": 430, "loss": 0.004, "lr": 4.224214993338149e-06, "epoch": 4.381502890173411, "percentage": 88.14, "elapsed_time": "2:03:26", "remaining_time": "0:16:36"}
455
+ {"current_steps": 380, "total_steps": 430, "loss": 0.003, "lr": 4.062442513947007e-06, "epoch": 4.393063583815029, "percentage": 88.37, "elapsed_time": "2:03:43", "remaining_time": "0:16:16"}
456
+ {"current_steps": 380, "total_steps": 430, "eval_loss": 0.008570068515837193, "epoch": 4.393063583815029, "percentage": 88.37, "elapsed_time": "2:03:53", "remaining_time": "0:16:18"}
457
+ {"current_steps": 381, "total_steps": 430, "loss": 0.0031, "lr": 3.903697249999289e-06, "epoch": 4.404624277456647, "percentage": 88.6, "elapsed_time": "2:04:10", "remaining_time": "0:15:58"}
458
+ {"current_steps": 382, "total_steps": 430, "loss": 0.0026, "lr": 3.7479896625674027e-06, "epoch": 4.416184971098266, "percentage": 88.84, "elapsed_time": "2:04:27", "remaining_time": "0:15:38"}
459
+ {"current_steps": 383, "total_steps": 430, "loss": 0.0026, "lr": 3.595330012545445e-06, "epoch": 4.427745664739884, "percentage": 89.07, "elapsed_time": "2:04:44", "remaining_time": "0:15:18"}
460
+ {"current_steps": 384, "total_steps": 430, "loss": 0.0029, "lr": 3.445728359973094e-06, "epoch": 4.4393063583815024, "percentage": 89.3, "elapsed_time": "2:05:02", "remaining_time": "0:14:58"}
461
+ {"current_steps": 385, "total_steps": 430, "loss": 0.0022, "lr": 3.299194563372604e-06, "epoch": 4.4508670520231215, "percentage": 89.53, "elapsed_time": "2:05:19", "remaining_time": "0:14:38"}
462
+ {"current_steps": 385, "total_steps": 430, "eval_loss": 0.008573681116104126, "epoch": 4.4508670520231215, "percentage": 89.53, "elapsed_time": "2:05:29", "remaining_time": "0:14:40"}
463
+ {"current_steps": 386, "total_steps": 430, "loss": 0.0026, "lr": 3.1557382790991687e-06, "epoch": 4.46242774566474, "percentage": 89.77, "elapsed_time": "2:05:46", "remaining_time": "0:14:20"}
464
+ {"current_steps": 387, "total_steps": 430, "loss": 0.0025, "lr": 3.0153689607045845e-06, "epoch": 4.473988439306359, "percentage": 90.0, "elapsed_time": "2:06:03", "remaining_time": "0:14:00"}
465
+ {"current_steps": 388, "total_steps": 430, "loss": 0.0027, "lr": 2.878095858314278e-06, "epoch": 4.485549132947977, "percentage": 90.23, "elapsed_time": "2:06:20", "remaining_time": "0:13:40"}
466
+ {"current_steps": 389, "total_steps": 430, "loss": 0.0025, "lr": 2.743928018017744e-06, "epoch": 4.497109826589595, "percentage": 90.47, "elapsed_time": "2:06:37", "remaining_time": "0:13:20"}
467
+ {"current_steps": 390, "total_steps": 430, "loss": 0.0028, "lr": 2.6128742812723704e-06, "epoch": 4.508670520231214, "percentage": 90.7, "elapsed_time": "2:06:54", "remaining_time": "0:13:00"}
468
+ {"current_steps": 390, "total_steps": 430, "eval_loss": 0.008553516119718552, "epoch": 4.508670520231214, "percentage": 90.7, "elapsed_time": "2:07:04", "remaining_time": "0:13:01"}
469
+ {"current_steps": 391, "total_steps": 430, "loss": 0.0033, "lr": 2.4849432843208785e-06, "epoch": 4.520231213872832, "percentage": 90.93, "elapsed_time": "2:07:20", "remaining_time": "0:12:42"}
470
+ {"current_steps": 392, "total_steps": 430, "loss": 0.0029, "lr": 2.3601434576221546e-06, "epoch": 4.531791907514451, "percentage": 91.16, "elapsed_time": "2:07:38", "remaining_time": "0:12:22"}
471
+ {"current_steps": 393, "total_steps": 430, "loss": 0.0031, "lr": 2.238483025295707e-06, "epoch": 4.543352601156069, "percentage": 91.4, "elapsed_time": "2:07:55", "remaining_time": "0:12:02"}
472
+ {"current_steps": 394, "total_steps": 430, "loss": 0.0027, "lr": 2.1199700045797077e-06, "epoch": 4.554913294797688, "percentage": 91.63, "elapsed_time": "2:08:13", "remaining_time": "0:11:42"}
473
+ {"current_steps": 395, "total_steps": 430, "loss": 0.0028, "lr": 2.0046122053026694e-06, "epoch": 4.566473988439307, "percentage": 91.86, "elapsed_time": "2:08:30", "remaining_time": "0:11:23"}
474
+ {"current_steps": 395, "total_steps": 430, "eval_loss": 0.008501513861119747, "epoch": 4.566473988439307, "percentage": 91.86, "elapsed_time": "2:08:40", "remaining_time": "0:11:24"}
475
+ {"current_steps": 396, "total_steps": 430, "loss": 0.0032, "lr": 1.8924172293688147e-06, "epoch": 4.578034682080925, "percentage": 92.09, "elapsed_time": "2:08:57", "remaining_time": "0:11:04"}
476
+ {"current_steps": 397, "total_steps": 430, "loss": 0.0035, "lr": 1.7833924702570725e-06, "epoch": 4.589595375722544, "percentage": 92.33, "elapsed_time": "2:09:15", "remaining_time": "0:10:44"}
477
+ {"current_steps": 398, "total_steps": 430, "loss": 0.0025, "lr": 1.6775451125338959e-06, "epoch": 4.601156069364162, "percentage": 92.56, "elapsed_time": "2:09:33", "remaining_time": "0:10:24"}
478
+ {"current_steps": 399, "total_steps": 430, "loss": 0.0024, "lr": 1.5748821313798124e-06, "epoch": 4.61271676300578, "percentage": 92.79, "elapsed_time": "2:09:51", "remaining_time": "0:10:05"}
479
+ {"current_steps": 400, "total_steps": 430, "loss": 0.0031, "lr": 1.4754102921297364e-06, "epoch": 4.624277456647399, "percentage": 93.02, "elapsed_time": "2:10:09", "remaining_time": "0:09:45"}
480
+ {"current_steps": 400, "total_steps": 430, "eval_loss": 0.008478561416268349, "epoch": 4.624277456647399, "percentage": 93.02, "elapsed_time": "2:10:19", "remaining_time": "0:09:46"}
481
+ {"current_steps": 401, "total_steps": 430, "loss": 0.0024, "lr": 1.3791361498271705e-06, "epoch": 4.635838150289017, "percentage": 93.26, "elapsed_time": "2:10:44", "remaining_time": "0:09:27"}
482
+ {"current_steps": 402, "total_steps": 430, "loss": 0.0023, "lr": 1.2860660487922616e-06, "epoch": 4.6473988439306355, "percentage": 93.49, "elapsed_time": "2:11:02", "remaining_time": "0:09:07"}
483
+ {"current_steps": 403, "total_steps": 430, "loss": 0.0024, "lr": 1.196206122203647e-06, "epoch": 4.658959537572255, "percentage": 93.72, "elapsed_time": "2:11:18", "remaining_time": "0:08:47"}
484
+ {"current_steps": 404, "total_steps": 430, "loss": 0.0033, "lr": 1.1095622916943494e-06, "epoch": 4.670520231213873, "percentage": 93.95, "elapsed_time": "2:11:35", "remaining_time": "0:08:28"}
485
+ {"current_steps": 405, "total_steps": 430, "loss": 0.0038, "lr": 1.0261402669615505e-06, "epoch": 4.682080924855491, "percentage": 94.19, "elapsed_time": "2:11:53", "remaining_time": "0:08:08"}
486
+ {"current_steps": 405, "total_steps": 430, "eval_loss": 0.00843281950801611, "epoch": 4.682080924855491, "percentage": 94.19, "elapsed_time": "2:12:03", "remaining_time": "0:08:09"}
487
+ {"current_steps": 406, "total_steps": 430, "loss": 0.0024, "lr": 9.459455453902866e-07, "epoch": 4.69364161849711, "percentage": 94.42, "elapsed_time": "2:12:20", "remaining_time": "0:07:49"}
488
+ {"current_steps": 407, "total_steps": 430, "loss": 0.0029, "lr": 8.68983411691221e-07, "epoch": 4.705202312138728, "percentage": 94.65, "elapsed_time": "2:12:38", "remaining_time": "0:07:29"}
489
+ {"current_steps": 408, "total_steps": 430, "loss": 0.0028, "lr": 7.952589375523567e-07, "epoch": 4.716763005780347, "percentage": 94.88, "elapsed_time": "2:12:56", "remaining_time": "0:07:10"}
490
+ {"current_steps": 409, "total_steps": 430, "loss": 0.0025, "lr": 7.247769813048644e-07, "epoch": 4.728323699421965, "percentage": 95.12, "elapsed_time": "2:13:12", "remaining_time": "0:06:50"}
491
+ {"current_steps": 410, "total_steps": 430, "loss": 0.0024, "lr": 6.57542187602872e-07, "epoch": 4.7398843930635834, "percentage": 95.35, "elapsed_time": "2:13:30", "remaining_time": "0:06:30"}
492
+ {"current_steps": 410, "total_steps": 430, "eval_loss": 0.00842086412012577, "epoch": 4.7398843930635834, "percentage": 95.35, "elapsed_time": "2:13:40", "remaining_time": "0:06:31"}
493
+ {"current_steps": 411, "total_steps": 430, "loss": 0.0028, "lr": 5.935589871174208e-07, "epoch": 4.7514450867052025, "percentage": 95.58, "elapsed_time": "2:13:58", "remaining_time": "0:06:11"}
494
+ {"current_steps": 412, "total_steps": 430, "loss": 0.0029, "lr": 5.328315962444874e-07, "epoch": 4.763005780346821, "percentage": 95.81, "elapsed_time": "2:14:13", "remaining_time": "0:05:51"}
495
+ {"current_steps": 413, "total_steps": 430, "loss": 0.0029, "lr": 4.753640168271456e-07, "epoch": 4.77456647398844, "percentage": 96.05, "elapsed_time": "2:14:30", "remaining_time": "0:05:32"}
496
+ {"current_steps": 414, "total_steps": 430, "loss": 0.0024, "lr": 4.2116003589179887e-07, "epoch": 4.786127167630058, "percentage": 96.28, "elapsed_time": "2:14:46", "remaining_time": "0:05:12"}
497
+ {"current_steps": 415, "total_steps": 430, "loss": 0.0024, "lr": 3.702232253986804e-07, "epoch": 4.797687861271676, "percentage": 96.51, "elapsed_time": "2:15:02", "remaining_time": "0:04:52"}
498
+ {"current_steps": 415, "total_steps": 430, "eval_loss": 0.008439392782747746, "epoch": 4.797687861271676, "percentage": 96.51, "elapsed_time": "2:15:12", "remaining_time": "0:04:53"}
499
+ {"current_steps": 416, "total_steps": 430, "loss": 0.0027, "lr": 3.2255694200643006e-07, "epoch": 4.809248554913295, "percentage": 96.74, "elapsed_time": "2:15:30", "remaining_time": "0:04:33"}
500
+ {"current_steps": 417, "total_steps": 430, "loss": 0.0023, "lr": 2.78164326850916e-07, "epoch": 4.820809248554913, "percentage": 96.98, "elapsed_time": "2:15:48", "remaining_time": "0:04:14"}
501
+ {"current_steps": 418, "total_steps": 430, "loss": 0.0031, "lr": 2.3704830533821108e-07, "epoch": 4.832369942196532, "percentage": 97.21, "elapsed_time": "2:16:05", "remaining_time": "0:03:54"}
502
+ {"current_steps": 419, "total_steps": 430, "loss": 0.0026, "lr": 1.9921158695184738e-07, "epoch": 4.84393063583815, "percentage": 97.44, "elapsed_time": "2:16:22", "remaining_time": "0:03:34"}
503
+ {"current_steps": 420, "total_steps": 430, "loss": 0.0024, "lr": 1.6465666507425315e-07, "epoch": 4.855491329479769, "percentage": 97.67, "elapsed_time": "2:16:41", "remaining_time": "0:03:15"}
504
+ {"current_steps": 420, "total_steps": 430, "eval_loss": 0.008424060419201851, "epoch": 4.855491329479769, "percentage": 97.67, "elapsed_time": "2:16:51", "remaining_time": "0:03:15"}
505
+ {"current_steps": 421, "total_steps": 430, "loss": 0.0027, "lr": 1.333858168224178e-07, "epoch": 4.867052023121388, "percentage": 97.91, "elapsed_time": "2:17:09", "remaining_time": "0:02:55"}
506
+ {"current_steps": 422, "total_steps": 430, "loss": 0.0032, "lr": 1.0540110289786742e-07, "epoch": 4.878612716763006, "percentage": 98.14, "elapsed_time": "2:17:24", "remaining_time": "0:02:36"}
507
+ {"current_steps": 423, "total_steps": 430, "loss": 0.0024, "lr": 8.07043674508623e-08, "epoch": 4.890173410404624, "percentage": 98.37, "elapsed_time": "2:17:41", "remaining_time": "0:02:16"}
508
+ {"current_steps": 424, "total_steps": 430, "loss": 0.0029, "lr": 5.929723795884967e-08, "epoch": 4.901734104046243, "percentage": 98.6, "elapsed_time": "2:17:57", "remaining_time": "0:01:57"}
509
+ {"current_steps": 425, "total_steps": 430, "loss": 0.0026, "lr": 4.1181125119221787e-08, "epoch": 4.913294797687861, "percentage": 98.84, "elapsed_time": "2:18:15", "remaining_time": "0:01:37"}
510
+ {"current_steps": 425, "total_steps": 430, "eval_loss": 0.008420780301094055, "epoch": 4.913294797687861, "percentage": 98.84, "elapsed_time": "2:18:25", "remaining_time": "0:01:37"}
511
+ {"current_steps": 426, "total_steps": 430, "loss": 0.0025, "lr": 2.6357222756384636e-08, "epoch": 4.924855491329479, "percentage": 99.07, "elapsed_time": "2:18:42", "remaining_time": "0:01:18"}
512
+ {"current_steps": 427, "total_steps": 430, "loss": 0.0028, "lr": 1.482650774303207e-08, "epoch": 4.936416184971098, "percentage": 99.3, "elapsed_time": "2:18:59", "remaining_time": "0:00:58"}
513
+ {"current_steps": 428, "total_steps": 430, "loss": 0.0033, "lr": 6.589739935819461e-09, "epoch": 4.9479768786127165, "percentage": 99.53, "elapsed_time": "2:19:16", "remaining_time": "0:00:39"}
514
+ {"current_steps": 429, "total_steps": 430, "loss": 0.0031, "lr": 1.6474621252704493e-09, "epoch": 4.959537572254336, "percentage": 99.77, "elapsed_time": "2:19:33", "remaining_time": "0:00:19"}
515
+ {"current_steps": 430, "total_steps": 430, "loss": 0.0029, "lr": 0.0, "epoch": 4.971098265895954, "percentage": 100.0, "elapsed_time": "2:19:51", "remaining_time": "0:00:00"}
516
+ {"current_steps": 430, "total_steps": 430, "eval_loss": 0.008429310284554958, "epoch": 4.971098265895954, "percentage": 100.0, "elapsed_time": "2:20:01", "remaining_time": "0:00:00"}
517
+ {"current_steps": 430, "total_steps": 430, "epoch": 4.971098265895954, "percentage": 100.0, "elapsed_time": "2:20:10", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,3740 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.007892865687608719,
3
+ "best_model_checkpoint": "/home/paperspace/Data/models/spinny/llm3br256/checkpoint-250",
4
+ "epoch": 4.971098265895954,
5
+ "eval_steps": 5,
6
+ "global_step": 430,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.011560693641618497,
13
+ "grad_norm": 0.15129172801971436,
14
+ "learning_rate": 2.325581395348837e-06,
15
+ "loss": 0.068,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.023121387283236993,
20
+ "grad_norm": 0.14174357056617737,
21
+ "learning_rate": 4.651162790697674e-06,
22
+ "loss": 0.0635,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03468208092485549,
27
+ "grad_norm": 0.14430448412895203,
28
+ "learning_rate": 6.976744186046512e-06,
29
+ "loss": 0.0649,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.046242774566473986,
34
+ "grad_norm": 0.1410493552684784,
35
+ "learning_rate": 9.302325581395349e-06,
36
+ "loss": 0.063,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.057803468208092484,
41
+ "grad_norm": 0.13995003700256348,
42
+ "learning_rate": 1.1627906976744187e-05,
43
+ "loss": 0.0598,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.057803468208092484,
48
+ "eval_loss": 0.05565303936600685,
49
+ "eval_runtime": 11.8576,
50
+ "eval_samples_per_second": 4.217,
51
+ "eval_steps_per_second": 1.096,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.06936416184971098,
56
+ "grad_norm": 0.12226737290620804,
57
+ "learning_rate": 1.3953488372093024e-05,
58
+ "loss": 0.0533,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.08092485549132948,
63
+ "grad_norm": 0.10596886277198792,
64
+ "learning_rate": 1.6279069767441862e-05,
65
+ "loss": 0.0544,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.09248554913294797,
70
+ "grad_norm": 0.07781537622213364,
71
+ "learning_rate": 1.8604651162790697e-05,
72
+ "loss": 0.0448,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.10404624277456648,
77
+ "grad_norm": 0.06554879248142242,
78
+ "learning_rate": 2.0930232558139536e-05,
79
+ "loss": 0.0373,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.11560693641618497,
84
+ "grad_norm": 0.08980869501829147,
85
+ "learning_rate": 2.3255813953488374e-05,
86
+ "loss": 0.0388,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.11560693641618497,
91
+ "eval_loss": 0.034586433321237564,
92
+ "eval_runtime": 10.0247,
93
+ "eval_samples_per_second": 4.988,
94
+ "eval_steps_per_second": 1.297,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 0.12716763005780346,
99
+ "grad_norm": 0.08015415817499161,
100
+ "learning_rate": 2.5581395348837212e-05,
101
+ "loss": 0.0393,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.13872832369942195,
106
+ "grad_norm": 0.06148159131407738,
107
+ "learning_rate": 2.7906976744186048e-05,
108
+ "loss": 0.0377,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.15028901734104047,
113
+ "grad_norm": 0.04883963614702225,
114
+ "learning_rate": 3.0232558139534883e-05,
115
+ "loss": 0.0356,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.16184971098265896,
120
+ "grad_norm": 0.04954546317458153,
121
+ "learning_rate": 3.2558139534883724e-05,
122
+ "loss": 0.0363,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.17341040462427745,
127
+ "grad_norm": 0.041509971022605896,
128
+ "learning_rate": 3.488372093023256e-05,
129
+ "loss": 0.0275,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.17341040462427745,
134
+ "eval_loss": 0.027632026001811028,
135
+ "eval_runtime": 10.0235,
136
+ "eval_samples_per_second": 4.988,
137
+ "eval_steps_per_second": 1.297,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.18497109826589594,
142
+ "grad_norm": 0.041887976229190826,
143
+ "learning_rate": 3.7209302325581394e-05,
144
+ "loss": 0.0303,
145
+ "step": 16
146
+ },
147
+ {
148
+ "epoch": 0.19653179190751446,
149
+ "grad_norm": 0.03965295851230621,
150
+ "learning_rate": 3.953488372093023e-05,
151
+ "loss": 0.0284,
152
+ "step": 17
153
+ },
154
+ {
155
+ "epoch": 0.20809248554913296,
156
+ "grad_norm": 0.03458382189273834,
157
+ "learning_rate": 4.186046511627907e-05,
158
+ "loss": 0.03,
159
+ "step": 18
160
+ },
161
+ {
162
+ "epoch": 0.21965317919075145,
163
+ "grad_norm": 0.03138720989227295,
164
+ "learning_rate": 4.418604651162791e-05,
165
+ "loss": 0.0242,
166
+ "step": 19
167
+ },
168
+ {
169
+ "epoch": 0.23121387283236994,
170
+ "grad_norm": 0.02681548520922661,
171
+ "learning_rate": 4.651162790697675e-05,
172
+ "loss": 0.0218,
173
+ "step": 20
174
+ },
175
+ {
176
+ "epoch": 0.23121387283236994,
177
+ "eval_loss": 0.02280299924314022,
178
+ "eval_runtime": 10.0675,
179
+ "eval_samples_per_second": 4.967,
180
+ "eval_steps_per_second": 1.291,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.24277456647398843,
185
+ "grad_norm": 0.03174450621008873,
186
+ "learning_rate": 4.883720930232558e-05,
187
+ "loss": 0.0235,
188
+ "step": 21
189
+ },
190
+ {
191
+ "epoch": 0.2543352601156069,
192
+ "grad_norm": 0.033451005816459656,
193
+ "learning_rate": 5.1162790697674425e-05,
194
+ "loss": 0.0291,
195
+ "step": 22
196
+ },
197
+ {
198
+ "epoch": 0.2658959537572254,
199
+ "grad_norm": 0.03227928280830383,
200
+ "learning_rate": 5.348837209302326e-05,
201
+ "loss": 0.0254,
202
+ "step": 23
203
+ },
204
+ {
205
+ "epoch": 0.2774566473988439,
206
+ "grad_norm": 0.03783709928393364,
207
+ "learning_rate": 5.5813953488372095e-05,
208
+ "loss": 0.0256,
209
+ "step": 24
210
+ },
211
+ {
212
+ "epoch": 0.28901734104046245,
213
+ "grad_norm": 0.03228365629911423,
214
+ "learning_rate": 5.8139534883720933e-05,
215
+ "loss": 0.0236,
216
+ "step": 25
217
+ },
218
+ {
219
+ "epoch": 0.28901734104046245,
220
+ "eval_loss": 0.020257851108908653,
221
+ "eval_runtime": 10.0419,
222
+ "eval_samples_per_second": 4.979,
223
+ "eval_steps_per_second": 1.295,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 0.30057803468208094,
228
+ "grad_norm": 0.02823326177895069,
229
+ "learning_rate": 6.0465116279069765e-05,
230
+ "loss": 0.0229,
231
+ "step": 26
232
+ },
233
+ {
234
+ "epoch": 0.31213872832369943,
235
+ "grad_norm": 0.02882234752178192,
236
+ "learning_rate": 6.27906976744186e-05,
237
+ "loss": 0.0226,
238
+ "step": 27
239
+ },
240
+ {
241
+ "epoch": 0.3236994219653179,
242
+ "grad_norm": 0.02527730166912079,
243
+ "learning_rate": 6.511627906976745e-05,
244
+ "loss": 0.0196,
245
+ "step": 28
246
+ },
247
+ {
248
+ "epoch": 0.3352601156069364,
249
+ "grad_norm": 0.026926985010504723,
250
+ "learning_rate": 6.744186046511628e-05,
251
+ "loss": 0.0182,
252
+ "step": 29
253
+ },
254
+ {
255
+ "epoch": 0.3468208092485549,
256
+ "grad_norm": 0.02383883111178875,
257
+ "learning_rate": 6.976744186046513e-05,
258
+ "loss": 0.0182,
259
+ "step": 30
260
+ },
261
+ {
262
+ "epoch": 0.3468208092485549,
263
+ "eval_loss": 0.01791333220899105,
264
+ "eval_runtime": 10.1038,
265
+ "eval_samples_per_second": 4.949,
266
+ "eval_steps_per_second": 1.287,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 0.3583815028901734,
271
+ "grad_norm": 0.020905988290905952,
272
+ "learning_rate": 7.209302325581396e-05,
273
+ "loss": 0.0173,
274
+ "step": 31
275
+ },
276
+ {
277
+ "epoch": 0.3699421965317919,
278
+ "grad_norm": 0.021837348118424416,
279
+ "learning_rate": 7.441860465116279e-05,
280
+ "loss": 0.0186,
281
+ "step": 32
282
+ },
283
+ {
284
+ "epoch": 0.3815028901734104,
285
+ "grad_norm": 0.022534186020493507,
286
+ "learning_rate": 7.674418604651163e-05,
287
+ "loss": 0.0192,
288
+ "step": 33
289
+ },
290
+ {
291
+ "epoch": 0.3930635838150289,
292
+ "grad_norm": 0.021404536440968513,
293
+ "learning_rate": 7.906976744186047e-05,
294
+ "loss": 0.0163,
295
+ "step": 34
296
+ },
297
+ {
298
+ "epoch": 0.4046242774566474,
299
+ "grad_norm": 0.02087543159723282,
300
+ "learning_rate": 8.139534883720931e-05,
301
+ "loss": 0.019,
302
+ "step": 35
303
+ },
304
+ {
305
+ "epoch": 0.4046242774566474,
306
+ "eval_loss": 0.016155000776052475,
307
+ "eval_runtime": 10.0056,
308
+ "eval_samples_per_second": 4.997,
309
+ "eval_steps_per_second": 1.299,
310
+ "step": 35
311
+ },
312
+ {
313
+ "epoch": 0.4161849710982659,
314
+ "grad_norm": 0.023041941225528717,
315
+ "learning_rate": 8.372093023255814e-05,
316
+ "loss": 0.0157,
317
+ "step": 36
318
+ },
319
+ {
320
+ "epoch": 0.4277456647398844,
321
+ "grad_norm": 0.020684899762272835,
322
+ "learning_rate": 8.604651162790697e-05,
323
+ "loss": 0.0154,
324
+ "step": 37
325
+ },
326
+ {
327
+ "epoch": 0.4393063583815029,
328
+ "grad_norm": 0.019204530864953995,
329
+ "learning_rate": 8.837209302325582e-05,
330
+ "loss": 0.0142,
331
+ "step": 38
332
+ },
333
+ {
334
+ "epoch": 0.4508670520231214,
335
+ "grad_norm": 0.019893651828169823,
336
+ "learning_rate": 9.069767441860465e-05,
337
+ "loss": 0.0155,
338
+ "step": 39
339
+ },
340
+ {
341
+ "epoch": 0.4624277456647399,
342
+ "grad_norm": 0.022773414850234985,
343
+ "learning_rate": 9.30232558139535e-05,
344
+ "loss": 0.017,
345
+ "step": 40
346
+ },
347
+ {
348
+ "epoch": 0.4624277456647399,
349
+ "eval_loss": 0.01472202967852354,
350
+ "eval_runtime": 10.018,
351
+ "eval_samples_per_second": 4.991,
352
+ "eval_steps_per_second": 1.298,
353
+ "step": 40
354
+ },
355
+ {
356
+ "epoch": 0.47398843930635837,
357
+ "grad_norm": 0.021773461252450943,
358
+ "learning_rate": 9.534883720930233e-05,
359
+ "loss": 0.0161,
360
+ "step": 41
361
+ },
362
+ {
363
+ "epoch": 0.48554913294797686,
364
+ "grad_norm": 0.023095447570085526,
365
+ "learning_rate": 9.767441860465116e-05,
366
+ "loss": 0.0146,
367
+ "step": 42
368
+ },
369
+ {
370
+ "epoch": 0.49710982658959535,
371
+ "grad_norm": 0.0202298853546381,
372
+ "learning_rate": 0.0001,
373
+ "loss": 0.015,
374
+ "step": 43
375
+ },
376
+ {
377
+ "epoch": 0.5086705202312138,
378
+ "grad_norm": 0.01809552311897278,
379
+ "learning_rate": 9.999835253787473e-05,
380
+ "loss": 0.0149,
381
+ "step": 44
382
+ },
383
+ {
384
+ "epoch": 0.5202312138728323,
385
+ "grad_norm": 0.019870778545737267,
386
+ "learning_rate": 9.999341026006419e-05,
387
+ "loss": 0.0147,
388
+ "step": 45
389
+ },
390
+ {
391
+ "epoch": 0.5202312138728323,
392
+ "eval_loss": 0.013716931454837322,
393
+ "eval_runtime": 10.0201,
394
+ "eval_samples_per_second": 4.99,
395
+ "eval_steps_per_second": 1.297,
396
+ "step": 45
397
+ },
398
+ {
399
+ "epoch": 0.5317919075144508,
400
+ "grad_norm": 0.017238808795809746,
401
+ "learning_rate": 9.998517349225698e-05,
402
+ "loss": 0.0107,
403
+ "step": 46
404
+ },
405
+ {
406
+ "epoch": 0.5433526011560693,
407
+ "grad_norm": 0.022697314620018005,
408
+ "learning_rate": 9.997364277724361e-05,
409
+ "loss": 0.0149,
410
+ "step": 47
411
+ },
412
+ {
413
+ "epoch": 0.5549132947976878,
414
+ "grad_norm": 0.023472866043448448,
415
+ "learning_rate": 9.99588188748808e-05,
416
+ "loss": 0.0144,
417
+ "step": 48
418
+ },
419
+ {
420
+ "epoch": 0.5664739884393064,
421
+ "grad_norm": 0.017129473388195038,
422
+ "learning_rate": 9.994070276204116e-05,
423
+ "loss": 0.0126,
424
+ "step": 49
425
+ },
426
+ {
427
+ "epoch": 0.5780346820809249,
428
+ "grad_norm": 0.01756882295012474,
429
+ "learning_rate": 9.991929563254914e-05,
430
+ "loss": 0.0118,
431
+ "step": 50
432
+ },
433
+ {
434
+ "epoch": 0.5780346820809249,
435
+ "eval_loss": 0.013151152059435844,
436
+ "eval_runtime": 10.0009,
437
+ "eval_samples_per_second": 5.0,
438
+ "eval_steps_per_second": 1.3,
439
+ "step": 50
440
+ },
441
+ {
442
+ "epoch": 0.5895953757225434,
443
+ "grad_norm": 0.019612474367022514,
444
+ "learning_rate": 9.989459889710213e-05,
445
+ "loss": 0.0144,
446
+ "step": 51
447
+ },
448
+ {
449
+ "epoch": 0.6011560693641619,
450
+ "grad_norm": 0.016709089279174805,
451
+ "learning_rate": 9.986661418317759e-05,
452
+ "loss": 0.0119,
453
+ "step": 52
454
+ },
455
+ {
456
+ "epoch": 0.6127167630057804,
457
+ "grad_norm": 0.023054232820868492,
458
+ "learning_rate": 9.983534333492575e-05,
459
+ "loss": 0.0137,
460
+ "step": 53
461
+ },
462
+ {
463
+ "epoch": 0.6242774566473989,
464
+ "grad_norm": 0.02029217965900898,
465
+ "learning_rate": 9.980078841304816e-05,
466
+ "loss": 0.014,
467
+ "step": 54
468
+ },
469
+ {
470
+ "epoch": 0.6358381502890174,
471
+ "grad_norm": 0.018532264977693558,
472
+ "learning_rate": 9.976295169466178e-05,
473
+ "loss": 0.0107,
474
+ "step": 55
475
+ },
476
+ {
477
+ "epoch": 0.6358381502890174,
478
+ "eval_loss": 0.012713148258626461,
479
+ "eval_runtime": 10.0087,
480
+ "eval_samples_per_second": 4.996,
481
+ "eval_steps_per_second": 1.299,
482
+ "step": 55
483
+ },
484
+ {
485
+ "epoch": 0.6473988439306358,
486
+ "grad_norm": 0.020468739792704582,
487
+ "learning_rate": 9.97218356731491e-05,
488
+ "loss": 0.0146,
489
+ "step": 56
490
+ },
491
+ {
492
+ "epoch": 0.6589595375722543,
493
+ "grad_norm": 0.01887972466647625,
494
+ "learning_rate": 9.967744305799357e-05,
495
+ "loss": 0.0126,
496
+ "step": 57
497
+ },
498
+ {
499
+ "epoch": 0.6705202312138728,
500
+ "grad_norm": 0.02040836587548256,
501
+ "learning_rate": 9.962977677460132e-05,
502
+ "loss": 0.0126,
503
+ "step": 58
504
+ },
505
+ {
506
+ "epoch": 0.6820809248554913,
507
+ "grad_norm": 0.02685651369392872,
508
+ "learning_rate": 9.957883996410821e-05,
509
+ "loss": 0.0122,
510
+ "step": 59
511
+ },
512
+ {
513
+ "epoch": 0.6936416184971098,
514
+ "grad_norm": 0.02112666517496109,
515
+ "learning_rate": 9.952463598317285e-05,
516
+ "loss": 0.016,
517
+ "step": 60
518
+ },
519
+ {
520
+ "epoch": 0.6936416184971098,
521
+ "eval_loss": 0.012294010259211063,
522
+ "eval_runtime": 10.0073,
523
+ "eval_samples_per_second": 4.996,
524
+ "eval_steps_per_second": 1.299,
525
+ "step": 60
526
+ },
527
+ {
528
+ "epoch": 0.7052023121387283,
529
+ "grad_norm": 0.020788514986634254,
530
+ "learning_rate": 9.946716840375551e-05,
531
+ "loss": 0.0106,
532
+ "step": 61
533
+ },
534
+ {
535
+ "epoch": 0.7167630057803468,
536
+ "grad_norm": 0.01940411888062954,
537
+ "learning_rate": 9.940644101288259e-05,
538
+ "loss": 0.0098,
539
+ "step": 62
540
+ },
541
+ {
542
+ "epoch": 0.7283236994219653,
543
+ "grad_norm": 0.02072029560804367,
544
+ "learning_rate": 9.934245781239714e-05,
545
+ "loss": 0.0142,
546
+ "step": 63
547
+ },
548
+ {
549
+ "epoch": 0.7398843930635838,
550
+ "grad_norm": 0.017221063375473022,
551
+ "learning_rate": 9.927522301869515e-05,
552
+ "loss": 0.0114,
553
+ "step": 64
554
+ },
555
+ {
556
+ "epoch": 0.7514450867052023,
557
+ "grad_norm": 0.026088256388902664,
558
+ "learning_rate": 9.920474106244763e-05,
559
+ "loss": 0.0144,
560
+ "step": 65
561
+ },
562
+ {
563
+ "epoch": 0.7514450867052023,
564
+ "eval_loss": 0.011602817103266716,
565
+ "eval_runtime": 10.0191,
566
+ "eval_samples_per_second": 4.99,
567
+ "eval_steps_per_second": 1.298,
568
+ "step": 65
569
+ },
570
+ {
571
+ "epoch": 0.7630057803468208,
572
+ "grad_norm": 0.016981270164251328,
573
+ "learning_rate": 9.91310165883088e-05,
574
+ "loss": 0.0136,
575
+ "step": 66
576
+ },
577
+ {
578
+ "epoch": 0.7745664739884393,
579
+ "grad_norm": 0.017894290387630463,
580
+ "learning_rate": 9.905405445460972e-05,
581
+ "loss": 0.0113,
582
+ "step": 67
583
+ },
584
+ {
585
+ "epoch": 0.7861271676300579,
586
+ "grad_norm": 0.017901500687003136,
587
+ "learning_rate": 9.897385973303845e-05,
588
+ "loss": 0.0133,
589
+ "step": 68
590
+ },
591
+ {
592
+ "epoch": 0.7976878612716763,
593
+ "grad_norm": 0.018053261563181877,
594
+ "learning_rate": 9.889043770830566e-05,
595
+ "loss": 0.0108,
596
+ "step": 69
597
+ },
598
+ {
599
+ "epoch": 0.8092485549132948,
600
+ "grad_norm": 0.023738127201795578,
601
+ "learning_rate": 9.880379387779637e-05,
602
+ "loss": 0.0119,
603
+ "step": 70
604
+ },
605
+ {
606
+ "epoch": 0.8092485549132948,
607
+ "eval_loss": 0.011262123472988605,
608
+ "eval_runtime": 10.0281,
609
+ "eval_samples_per_second": 4.986,
610
+ "eval_steps_per_second": 1.296,
611
+ "step": 70
612
+ },
613
+ {
614
+ "epoch": 0.8208092485549133,
615
+ "grad_norm": 0.01628166250884533,
616
+ "learning_rate": 9.871393395120774e-05,
617
+ "loss": 0.014,
618
+ "step": 71
619
+ },
620
+ {
621
+ "epoch": 0.8323699421965318,
622
+ "grad_norm": 0.014171602204442024,
623
+ "learning_rate": 9.862086385017283e-05,
624
+ "loss": 0.0099,
625
+ "step": 72
626
+ },
627
+ {
628
+ "epoch": 0.8439306358381503,
629
+ "grad_norm": 0.01973879709839821,
630
+ "learning_rate": 9.852458970787026e-05,
631
+ "loss": 0.011,
632
+ "step": 73
633
+ },
634
+ {
635
+ "epoch": 0.8554913294797688,
636
+ "grad_norm": 0.015728101134300232,
637
+ "learning_rate": 9.842511786862019e-05,
638
+ "loss": 0.01,
639
+ "step": 74
640
+ },
641
+ {
642
+ "epoch": 0.8670520231213873,
643
+ "grad_norm": 0.015097449533641338,
644
+ "learning_rate": 9.832245488746611e-05,
645
+ "loss": 0.0111,
646
+ "step": 75
647
+ },
648
+ {
649
+ "epoch": 0.8670520231213873,
650
+ "eval_loss": 0.010938560590147972,
651
+ "eval_runtime": 10.0124,
652
+ "eval_samples_per_second": 4.994,
653
+ "eval_steps_per_second": 1.298,
654
+ "step": 75
655
+ },
656
+ {
657
+ "epoch": 0.8786127167630058,
658
+ "grad_norm": 0.02237934060394764,
659
+ "learning_rate": 9.821660752974293e-05,
660
+ "loss": 0.0142,
661
+ "step": 76
662
+ },
663
+ {
664
+ "epoch": 0.8901734104046243,
665
+ "grad_norm": 0.01948779821395874,
666
+ "learning_rate": 9.810758277063119e-05,
667
+ "loss": 0.0138,
668
+ "step": 77
669
+ },
670
+ {
671
+ "epoch": 0.9017341040462428,
672
+ "grad_norm": 0.022487910464406013,
673
+ "learning_rate": 9.799538779469734e-05,
674
+ "loss": 0.0151,
675
+ "step": 78
676
+ },
677
+ {
678
+ "epoch": 0.9132947976878613,
679
+ "grad_norm": 0.017546942457556725,
680
+ "learning_rate": 9.78800299954203e-05,
681
+ "loss": 0.0098,
682
+ "step": 79
683
+ },
684
+ {
685
+ "epoch": 0.9248554913294798,
686
+ "grad_norm": 0.021010980010032654,
687
+ "learning_rate": 9.77615169747043e-05,
688
+ "loss": 0.012,
689
+ "step": 80
690
+ },
691
+ {
692
+ "epoch": 0.9248554913294798,
693
+ "eval_loss": 0.010658971033990383,
694
+ "eval_runtime": 10.0307,
695
+ "eval_samples_per_second": 4.985,
696
+ "eval_steps_per_second": 1.296,
697
+ "step": 80
698
+ },
699
+ {
700
+ "epoch": 0.9364161849710982,
701
+ "grad_norm": 0.018796751275658607,
702
+ "learning_rate": 9.763985654237786e-05,
703
+ "loss": 0.0126,
704
+ "step": 81
705
+ },
706
+ {
707
+ "epoch": 0.9479768786127167,
708
+ "grad_norm": 0.020107241347432137,
709
+ "learning_rate": 9.751505671567913e-05,
710
+ "loss": 0.0129,
711
+ "step": 82
712
+ },
713
+ {
714
+ "epoch": 0.9595375722543352,
715
+ "grad_norm": 0.015596112236380577,
716
+ "learning_rate": 9.738712571872763e-05,
717
+ "loss": 0.0093,
718
+ "step": 83
719
+ },
720
+ {
721
+ "epoch": 0.9710982658959537,
722
+ "grad_norm": 0.018946580588817596,
723
+ "learning_rate": 9.725607198198227e-05,
724
+ "loss": 0.0139,
725
+ "step": 84
726
+ },
727
+ {
728
+ "epoch": 0.9826589595375722,
729
+ "grad_norm": 0.01942116767168045,
730
+ "learning_rate": 9.712190414168572e-05,
731
+ "loss": 0.0139,
732
+ "step": 85
733
+ },
734
+ {
735
+ "epoch": 0.9826589595375722,
736
+ "eval_loss": 0.010201876051723957,
737
+ "eval_runtime": 10.0325,
738
+ "eval_samples_per_second": 4.984,
739
+ "eval_steps_per_second": 1.296,
740
+ "step": 85
741
+ },
742
+ {
743
+ "epoch": 0.9942196531791907,
744
+ "grad_norm": 0.01808648556470871,
745
+ "learning_rate": 9.698463103929542e-05,
746
+ "loss": 0.0096,
747
+ "step": 86
748
+ },
749
+ {
750
+ "epoch": 1.0057803468208093,
751
+ "grad_norm": 0.033104732632637024,
752
+ "learning_rate": 9.684426172090085e-05,
753
+ "loss": 0.0208,
754
+ "step": 87
755
+ },
756
+ {
757
+ "epoch": 1.0173410404624277,
758
+ "grad_norm": 0.011730443686246872,
759
+ "learning_rate": 9.67008054366274e-05,
760
+ "loss": 0.0079,
761
+ "step": 88
762
+ },
763
+ {
764
+ "epoch": 1.0289017341040463,
765
+ "grad_norm": 0.017196012660861015,
766
+ "learning_rate": 9.65542716400269e-05,
767
+ "loss": 0.0103,
768
+ "step": 89
769
+ },
770
+ {
771
+ "epoch": 1.0404624277456647,
772
+ "grad_norm": 0.015379775315523148,
773
+ "learning_rate": 9.640466998745456e-05,
774
+ "loss": 0.0085,
775
+ "step": 90
776
+ },
777
+ {
778
+ "epoch": 1.0404624277456647,
779
+ "eval_loss": 0.01041076984256506,
780
+ "eval_runtime": 10.0354,
781
+ "eval_samples_per_second": 4.982,
782
+ "eval_steps_per_second": 1.295,
783
+ "step": 90
784
+ },
785
+ {
786
+ "epoch": 1.0520231213872833,
787
+ "grad_norm": 0.01682409830391407,
788
+ "learning_rate": 9.625201033743261e-05,
789
+ "loss": 0.0102,
790
+ "step": 91
791
+ },
792
+ {
793
+ "epoch": 1.0635838150289016,
794
+ "grad_norm": 0.017098382115364075,
795
+ "learning_rate": 9.609630275000072e-05,
796
+ "loss": 0.0081,
797
+ "step": 92
798
+ },
799
+ {
800
+ "epoch": 1.0751445086705202,
801
+ "grad_norm": 0.017288707196712494,
802
+ "learning_rate": 9.5937557486053e-05,
803
+ "loss": 0.0094,
804
+ "step": 93
805
+ },
806
+ {
807
+ "epoch": 1.0867052023121386,
808
+ "grad_norm": 0.018024342134594917,
809
+ "learning_rate": 9.577578500666187e-05,
810
+ "loss": 0.0116,
811
+ "step": 94
812
+ },
813
+ {
814
+ "epoch": 1.0982658959537572,
815
+ "grad_norm": 0.017229463905096054,
816
+ "learning_rate": 9.56109959723886e-05,
817
+ "loss": 0.01,
818
+ "step": 95
819
+ },
820
+ {
821
+ "epoch": 1.0982658959537572,
822
+ "eval_loss": 0.010240535251796246,
823
+ "eval_runtime": 10.0835,
824
+ "eval_samples_per_second": 4.959,
825
+ "eval_steps_per_second": 1.289,
826
+ "step": 95
827
+ },
828
+ {
829
+ "epoch": 1.1098265895953756,
830
+ "grad_norm": 0.015899403020739555,
831
+ "learning_rate": 9.544320124258092e-05,
832
+ "loss": 0.0099,
833
+ "step": 96
834
+ },
835
+ {
836
+ "epoch": 1.1213872832369942,
837
+ "grad_norm": 0.019960559904575348,
838
+ "learning_rate": 9.527241187465734e-05,
839
+ "loss": 0.0098,
840
+ "step": 97
841
+ },
842
+ {
843
+ "epoch": 1.1329479768786128,
844
+ "grad_norm": 0.01425469946116209,
845
+ "learning_rate": 9.509863912337842e-05,
846
+ "loss": 0.0084,
847
+ "step": 98
848
+ },
849
+ {
850
+ "epoch": 1.1445086705202312,
851
+ "grad_norm": 0.015252132900059223,
852
+ "learning_rate": 9.492189444010521e-05,
853
+ "loss": 0.01,
854
+ "step": 99
855
+ },
856
+ {
857
+ "epoch": 1.1560693641618498,
858
+ "grad_norm": 0.014408037066459656,
859
+ "learning_rate": 9.474218947204459e-05,
860
+ "loss": 0.009,
861
+ "step": 100
862
+ },
863
+ {
864
+ "epoch": 1.1560693641618498,
865
+ "eval_loss": 0.009868398308753967,
866
+ "eval_runtime": 10.0137,
867
+ "eval_samples_per_second": 4.993,
868
+ "eval_steps_per_second": 1.298,
869
+ "step": 100
870
+ },
871
+ {
872
+ "epoch": 1.1676300578034682,
873
+ "grad_norm": 0.01568921096622944,
874
+ "learning_rate": 9.455953606148172e-05,
875
+ "loss": 0.0125,
876
+ "step": 101
877
+ },
878
+ {
879
+ "epoch": 1.1791907514450868,
880
+ "grad_norm": 0.01693912222981453,
881
+ "learning_rate": 9.437394624499958e-05,
882
+ "loss": 0.0116,
883
+ "step": 102
884
+ },
885
+ {
886
+ "epoch": 1.1907514450867052,
887
+ "grad_norm": 0.018201276659965515,
888
+ "learning_rate": 9.418543225268596e-05,
889
+ "loss": 0.0117,
890
+ "step": 103
891
+ },
892
+ {
893
+ "epoch": 1.2023121387283238,
894
+ "grad_norm": 0.015434252098202705,
895
+ "learning_rate": 9.399400650732735e-05,
896
+ "loss": 0.011,
897
+ "step": 104
898
+ },
899
+ {
900
+ "epoch": 1.2138728323699421,
901
+ "grad_norm": 0.01606677658855915,
902
+ "learning_rate": 9.379968162359034e-05,
903
+ "loss": 0.0094,
904
+ "step": 105
905
+ },
906
+ {
907
+ "epoch": 1.2138728323699421,
908
+ "eval_loss": 0.009825030341744423,
909
+ "eval_runtime": 10.0305,
910
+ "eval_samples_per_second": 4.985,
911
+ "eval_steps_per_second": 1.296,
912
+ "step": 105
913
+ },
914
+ {
915
+ "epoch": 1.2254335260115607,
916
+ "grad_norm": 0.015970559790730476,
917
+ "learning_rate": 9.360247040719039e-05,
918
+ "loss": 0.0079,
919
+ "step": 106
920
+ },
921
+ {
922
+ "epoch": 1.2369942196531791,
923
+ "grad_norm": 0.01553067285567522,
924
+ "learning_rate": 9.340238585404788e-05,
925
+ "loss": 0.0077,
926
+ "step": 107
927
+ },
928
+ {
929
+ "epoch": 1.2485549132947977,
930
+ "grad_norm": 0.017365023493766785,
931
+ "learning_rate": 9.319944114943171e-05,
932
+ "loss": 0.0089,
933
+ "step": 108
934
+ },
935
+ {
936
+ "epoch": 1.260115606936416,
937
+ "grad_norm": 0.01562884822487831,
938
+ "learning_rate": 9.29936496670905e-05,
939
+ "loss": 0.0076,
940
+ "step": 109
941
+ },
942
+ {
943
+ "epoch": 1.2716763005780347,
944
+ "grad_norm": 0.016722485423088074,
945
+ "learning_rate": 9.278502496837116e-05,
946
+ "loss": 0.0069,
947
+ "step": 110
948
+ },
949
+ {
950
+ "epoch": 1.2716763005780347,
951
+ "eval_loss": 0.009917480871081352,
952
+ "eval_runtime": 9.9972,
953
+ "eval_samples_per_second": 5.001,
954
+ "eval_steps_per_second": 1.3,
955
+ "step": 110
956
+ },
957
+ {
958
+ "epoch": 1.2832369942196533,
959
+ "grad_norm": 0.019191304221749306,
960
+ "learning_rate": 9.257358080132523e-05,
961
+ "loss": 0.0108,
962
+ "step": 111
963
+ },
964
+ {
965
+ "epoch": 1.2947976878612717,
966
+ "grad_norm": 0.02037121169269085,
967
+ "learning_rate": 9.235933109980301e-05,
968
+ "loss": 0.011,
969
+ "step": 112
970
+ },
971
+ {
972
+ "epoch": 1.30635838150289,
973
+ "grad_norm": 0.016349676996469498,
974
+ "learning_rate": 9.214228998253527e-05,
975
+ "loss": 0.0084,
976
+ "step": 113
977
+ },
978
+ {
979
+ "epoch": 1.3179190751445087,
980
+ "grad_norm": 0.01671903021633625,
981
+ "learning_rate": 9.192247175220276e-05,
982
+ "loss": 0.0087,
983
+ "step": 114
984
+ },
985
+ {
986
+ "epoch": 1.3294797687861273,
987
+ "grad_norm": 0.01710616424679756,
988
+ "learning_rate": 9.16998908944939e-05,
989
+ "loss": 0.0108,
990
+ "step": 115
991
+ },
992
+ {
993
+ "epoch": 1.3294797687861273,
994
+ "eval_loss": 0.009632885456085205,
995
+ "eval_runtime": 10.0191,
996
+ "eval_samples_per_second": 4.99,
997
+ "eval_steps_per_second": 1.298,
998
+ "step": 115
999
+ },
1000
+ {
1001
+ "epoch": 1.3410404624277457,
1002
+ "grad_norm": 0.01672513224184513,
1003
+ "learning_rate": 9.147456207714997e-05,
1004
+ "loss": 0.0077,
1005
+ "step": 116
1006
+ },
1007
+ {
1008
+ "epoch": 1.352601156069364,
1009
+ "grad_norm": 0.017153792083263397,
1010
+ "learning_rate": 9.124650014899867e-05,
1011
+ "loss": 0.0101,
1012
+ "step": 117
1013
+ },
1014
+ {
1015
+ "epoch": 1.3641618497109826,
1016
+ "grad_norm": 0.018158160150051117,
1017
+ "learning_rate": 9.101572013897555e-05,
1018
+ "loss": 0.0103,
1019
+ "step": 118
1020
+ },
1021
+ {
1022
+ "epoch": 1.3757225433526012,
1023
+ "grad_norm": 0.017670975998044014,
1024
+ "learning_rate": 9.078223725513366e-05,
1025
+ "loss": 0.0112,
1026
+ "step": 119
1027
+ },
1028
+ {
1029
+ "epoch": 1.3872832369942196,
1030
+ "grad_norm": 0.013258930295705795,
1031
+ "learning_rate": 9.05460668836413e-05,
1032
+ "loss": 0.0066,
1033
+ "step": 120
1034
+ },
1035
+ {
1036
+ "epoch": 1.3872832369942196,
1037
+ "eval_loss": 0.009479235857725143,
1038
+ "eval_runtime": 10.0092,
1039
+ "eval_samples_per_second": 4.995,
1040
+ "eval_steps_per_second": 1.299,
1041
+ "step": 120
1042
+ },
1043
+ {
1044
+ "epoch": 1.3988439306358382,
1045
+ "grad_norm": 0.016367750242352486,
1046
+ "learning_rate": 9.030722458776814e-05,
1047
+ "loss": 0.0083,
1048
+ "step": 121
1049
+ },
1050
+ {
1051
+ "epoch": 1.4104046242774566,
1052
+ "grad_norm": 0.01966327428817749,
1053
+ "learning_rate": 9.006572610685968e-05,
1054
+ "loss": 0.013,
1055
+ "step": 122
1056
+ },
1057
+ {
1058
+ "epoch": 1.4219653179190752,
1059
+ "grad_norm": 0.014227735809981823,
1060
+ "learning_rate": 8.98215873552999e-05,
1061
+ "loss": 0.0081,
1062
+ "step": 123
1063
+ },
1064
+ {
1065
+ "epoch": 1.4335260115606936,
1066
+ "grad_norm": 0.0126969488337636,
1067
+ "learning_rate": 8.957482442146272e-05,
1068
+ "loss": 0.0069,
1069
+ "step": 124
1070
+ },
1071
+ {
1072
+ "epoch": 1.4450867052023122,
1073
+ "grad_norm": 0.0182335264980793,
1074
+ "learning_rate": 8.932545356665157e-05,
1075
+ "loss": 0.0089,
1076
+ "step": 125
1077
+ },
1078
+ {
1079
+ "epoch": 1.4450867052023122,
1080
+ "eval_loss": 0.009439178742468357,
1081
+ "eval_runtime": 10.0231,
1082
+ "eval_samples_per_second": 4.988,
1083
+ "eval_steps_per_second": 1.297,
1084
+ "step": 125
1085
+ },
1086
+ {
1087
+ "epoch": 1.4566473988439306,
1088
+ "grad_norm": 0.013425913639366627,
1089
+ "learning_rate": 8.907349122402801e-05,
1090
+ "loss": 0.0064,
1091
+ "step": 126
1092
+ },
1093
+ {
1094
+ "epoch": 1.4682080924855492,
1095
+ "grad_norm": 0.017706867307424545,
1096
+ "learning_rate": 8.881895399752874e-05,
1097
+ "loss": 0.0085,
1098
+ "step": 127
1099
+ },
1100
+ {
1101
+ "epoch": 1.4797687861271676,
1102
+ "grad_norm": 0.015954311937093735,
1103
+ "learning_rate": 8.856185866077129e-05,
1104
+ "loss": 0.0091,
1105
+ "step": 128
1106
+ },
1107
+ {
1108
+ "epoch": 1.4913294797687862,
1109
+ "grad_norm": 0.01800154522061348,
1110
+ "learning_rate": 8.83022221559489e-05,
1111
+ "loss": 0.0118,
1112
+ "step": 129
1113
+ },
1114
+ {
1115
+ "epoch": 1.5028901734104045,
1116
+ "grad_norm": 0.022386785596609116,
1117
+ "learning_rate": 8.80400615927139e-05,
1118
+ "loss": 0.0084,
1119
+ "step": 130
1120
+ },
1121
+ {
1122
+ "epoch": 1.5028901734104045,
1123
+ "eval_loss": 0.009285805746912956,
1124
+ "eval_runtime": 10.0195,
1125
+ "eval_samples_per_second": 4.99,
1126
+ "eval_steps_per_second": 1.297,
1127
+ "step": 130
1128
+ },
1129
+ {
1130
+ "epoch": 1.5144508670520231,
1131
+ "grad_norm": 0.015237067826092243,
1132
+ "learning_rate": 8.777539424705023e-05,
1133
+ "loss": 0.0067,
1134
+ "step": 131
1135
+ },
1136
+ {
1137
+ "epoch": 1.5260115606936417,
1138
+ "grad_norm": 0.01740083284676075,
1139
+ "learning_rate": 8.750823756013498e-05,
1140
+ "loss": 0.0111,
1141
+ "step": 132
1142
+ },
1143
+ {
1144
+ "epoch": 1.5375722543352601,
1145
+ "grad_norm": 0.01614670269191265,
1146
+ "learning_rate": 8.72386091371891e-05,
1147
+ "loss": 0.0066,
1148
+ "step": 133
1149
+ },
1150
+ {
1151
+ "epoch": 1.5491329479768785,
1152
+ "grad_norm": 0.018181053921580315,
1153
+ "learning_rate": 8.696652674631717e-05,
1154
+ "loss": 0.0089,
1155
+ "step": 134
1156
+ },
1157
+ {
1158
+ "epoch": 1.560693641618497,
1159
+ "grad_norm": 0.01898285746574402,
1160
+ "learning_rate": 8.669200831733655e-05,
1161
+ "loss": 0.0102,
1162
+ "step": 135
1163
+ },
1164
+ {
1165
+ "epoch": 1.560693641618497,
1166
+ "eval_loss": 0.00925290398299694,
1167
+ "eval_runtime": 10.0096,
1168
+ "eval_samples_per_second": 4.995,
1169
+ "eval_steps_per_second": 1.299,
1170
+ "step": 135
1171
+ },
1172
+ {
1173
+ "epoch": 1.5722543352601157,
1174
+ "grad_norm": 0.01583796739578247,
1175
+ "learning_rate": 8.641507194059579e-05,
1176
+ "loss": 0.0084,
1177
+ "step": 136
1178
+ },
1179
+ {
1180
+ "epoch": 1.583815028901734,
1181
+ "grad_norm": 0.020259637385606766,
1182
+ "learning_rate": 8.613573586578262e-05,
1183
+ "loss": 0.0097,
1184
+ "step": 137
1185
+ },
1186
+ {
1187
+ "epoch": 1.5953757225433525,
1188
+ "grad_norm": 0.0170609038323164,
1189
+ "learning_rate": 8.585401850072113e-05,
1190
+ "loss": 0.0102,
1191
+ "step": 138
1192
+ },
1193
+ {
1194
+ "epoch": 1.606936416184971,
1195
+ "grad_norm": 0.013348150067031384,
1196
+ "learning_rate": 8.55699384101589e-05,
1197
+ "loss": 0.0076,
1198
+ "step": 139
1199
+ },
1200
+ {
1201
+ "epoch": 1.6184971098265897,
1202
+ "grad_norm": 0.0179379191249609,
1203
+ "learning_rate": 8.528351431454351e-05,
1204
+ "loss": 0.01,
1205
+ "step": 140
1206
+ },
1207
+ {
1208
+ "epoch": 1.6184971098265897,
1209
+ "eval_loss": 0.009090203791856766,
1210
+ "eval_runtime": 10.0116,
1211
+ "eval_samples_per_second": 4.994,
1212
+ "eval_steps_per_second": 1.298,
1213
+ "step": 140
1214
+ },
1215
+ {
1216
+ "epoch": 1.630057803468208,
1217
+ "grad_norm": 0.014754540286958218,
1218
+ "learning_rate": 8.499476508878893e-05,
1219
+ "loss": 0.0091,
1220
+ "step": 141
1221
+ },
1222
+ {
1223
+ "epoch": 1.6416184971098264,
1224
+ "grad_norm": 0.014680921100080013,
1225
+ "learning_rate": 8.47037097610317e-05,
1226
+ "loss": 0.008,
1227
+ "step": 142
1228
+ },
1229
+ {
1230
+ "epoch": 1.653179190751445,
1231
+ "grad_norm": 0.01806177943944931,
1232
+ "learning_rate": 8.441036751137696e-05,
1233
+ "loss": 0.0122,
1234
+ "step": 143
1235
+ },
1236
+ {
1237
+ "epoch": 1.6647398843930636,
1238
+ "grad_norm": 0.014901218004524708,
1239
+ "learning_rate": 8.411475767063455e-05,
1240
+ "loss": 0.0075,
1241
+ "step": 144
1242
+ },
1243
+ {
1244
+ "epoch": 1.6763005780346822,
1245
+ "grad_norm": 0.01642463356256485,
1246
+ "learning_rate": 8.381689971904514e-05,
1247
+ "loss": 0.0098,
1248
+ "step": 145
1249
+ },
1250
+ {
1251
+ "epoch": 1.6763005780346822,
1252
+ "eval_loss": 0.008807710371911526,
1253
+ "eval_runtime": 10.0289,
1254
+ "eval_samples_per_second": 4.986,
1255
+ "eval_steps_per_second": 1.296,
1256
+ "step": 145
1257
+ },
1258
+ {
1259
+ "epoch": 1.6878612716763006,
1260
+ "grad_norm": 0.0145337525755167,
1261
+ "learning_rate": 8.35168132849965e-05,
1262
+ "loss": 0.0074,
1263
+ "step": 146
1264
+ },
1265
+ {
1266
+ "epoch": 1.699421965317919,
1267
+ "grad_norm": 0.019870057702064514,
1268
+ "learning_rate": 8.321451814372997e-05,
1269
+ "loss": 0.0111,
1270
+ "step": 147
1271
+ },
1272
+ {
1273
+ "epoch": 1.7109826589595376,
1274
+ "grad_norm": 0.015163514763116837,
1275
+ "learning_rate": 8.29100342160374e-05,
1276
+ "loss": 0.0097,
1277
+ "step": 148
1278
+ },
1279
+ {
1280
+ "epoch": 1.7225433526011562,
1281
+ "grad_norm": 0.01458723470568657,
1282
+ "learning_rate": 8.260338156694836e-05,
1283
+ "loss": 0.007,
1284
+ "step": 149
1285
+ },
1286
+ {
1287
+ "epoch": 1.7341040462427746,
1288
+ "grad_norm": 0.015452525578439236,
1289
+ "learning_rate": 8.229458040440783e-05,
1290
+ "loss": 0.0071,
1291
+ "step": 150
1292
+ },
1293
+ {
1294
+ "epoch": 1.7341040462427746,
1295
+ "eval_loss": 0.008663667365908623,
1296
+ "eval_runtime": 10.0348,
1297
+ "eval_samples_per_second": 4.983,
1298
+ "eval_steps_per_second": 1.295,
1299
+ "step": 150
1300
+ },
1301
+ {
1302
+ "epoch": 1.745664739884393,
1303
+ "grad_norm": 0.017789160832762718,
1304
+ "learning_rate": 8.198365107794457e-05,
1305
+ "loss": 0.0098,
1306
+ "step": 151
1307
+ },
1308
+ {
1309
+ "epoch": 1.7572254335260116,
1310
+ "grad_norm": 0.019878627732396126,
1311
+ "learning_rate": 8.167061407733016e-05,
1312
+ "loss": 0.0077,
1313
+ "step": 152
1314
+ },
1315
+ {
1316
+ "epoch": 1.7687861271676302,
1317
+ "grad_norm": 0.018271176144480705,
1318
+ "learning_rate": 8.135549003122871e-05,
1319
+ "loss": 0.0096,
1320
+ "step": 153
1321
+ },
1322
+ {
1323
+ "epoch": 1.7803468208092486,
1324
+ "grad_norm": 0.017175493761897087,
1325
+ "learning_rate": 8.103829970583742e-05,
1326
+ "loss": 0.0111,
1327
+ "step": 154
1328
+ },
1329
+ {
1330
+ "epoch": 1.791907514450867,
1331
+ "grad_norm": 0.014682111330330372,
1332
+ "learning_rate": 8.071906400351822e-05,
1333
+ "loss": 0.0094,
1334
+ "step": 155
1335
+ },
1336
+ {
1337
+ "epoch": 1.791907514450867,
1338
+ "eval_loss": 0.008556585758924484,
1339
+ "eval_runtime": 10.0386,
1340
+ "eval_samples_per_second": 4.981,
1341
+ "eval_steps_per_second": 1.295,
1342
+ "step": 155
1343
+ },
1344
+ {
1345
+ "epoch": 1.8034682080924855,
1346
+ "grad_norm": 0.016677409410476685,
1347
+ "learning_rate": 8.039780396142022e-05,
1348
+ "loss": 0.0079,
1349
+ "step": 156
1350
+ },
1351
+ {
1352
+ "epoch": 1.8150289017341041,
1353
+ "grad_norm": 0.01885165646672249,
1354
+ "learning_rate": 8.007454075009351e-05,
1355
+ "loss": 0.0115,
1356
+ "step": 157
1357
+ },
1358
+ {
1359
+ "epoch": 1.8265895953757225,
1360
+ "grad_norm": 0.01522767636924982,
1361
+ "learning_rate": 7.9749295672094e-05,
1362
+ "loss": 0.0076,
1363
+ "step": 158
1364
+ },
1365
+ {
1366
+ "epoch": 1.838150289017341,
1367
+ "grad_norm": 0.01811189390718937,
1368
+ "learning_rate": 7.942209016057954e-05,
1369
+ "loss": 0.01,
1370
+ "step": 159
1371
+ },
1372
+ {
1373
+ "epoch": 1.8497109826589595,
1374
+ "grad_norm": 0.01717502437531948,
1375
+ "learning_rate": 7.909294577789766e-05,
1376
+ "loss": 0.008,
1377
+ "step": 160
1378
+ },
1379
+ {
1380
+ "epoch": 1.8497109826589595,
1381
+ "eval_loss": 0.008559009060263634,
1382
+ "eval_runtime": 10.0652,
1383
+ "eval_samples_per_second": 4.968,
1384
+ "eval_steps_per_second": 1.292,
1385
+ "step": 160
1386
+ },
1387
+ {
1388
+ "epoch": 1.861271676300578,
1389
+ "grad_norm": 0.015464117750525475,
1390
+ "learning_rate": 7.876188421416449e-05,
1391
+ "loss": 0.0068,
1392
+ "step": 161
1393
+ },
1394
+ {
1395
+ "epoch": 1.8728323699421965,
1396
+ "grad_norm": 0.015217979438602924,
1397
+ "learning_rate": 7.842892728583558e-05,
1398
+ "loss": 0.0074,
1399
+ "step": 162
1400
+ },
1401
+ {
1402
+ "epoch": 1.8843930635838149,
1403
+ "grad_norm": 0.01554564293473959,
1404
+ "learning_rate": 7.809409693426803e-05,
1405
+ "loss": 0.0071,
1406
+ "step": 163
1407
+ },
1408
+ {
1409
+ "epoch": 1.8959537572254335,
1410
+ "grad_norm": 0.01914595626294613,
1411
+ "learning_rate": 7.775741522427477e-05,
1412
+ "loss": 0.009,
1413
+ "step": 164
1414
+ },
1415
+ {
1416
+ "epoch": 1.907514450867052,
1417
+ "grad_norm": 0.01934712752699852,
1418
+ "learning_rate": 7.741890434267043e-05,
1419
+ "loss": 0.01,
1420
+ "step": 165
1421
+ },
1422
+ {
1423
+ "epoch": 1.907514450867052,
1424
+ "eval_loss": 0.00854802131652832,
1425
+ "eval_runtime": 10.0226,
1426
+ "eval_samples_per_second": 4.989,
1427
+ "eval_steps_per_second": 1.297,
1428
+ "step": 165
1429
+ },
1430
+ {
1431
+ "epoch": 1.9190751445086707,
1432
+ "grad_norm": 0.01625540666282177,
1433
+ "learning_rate": 7.707858659680924e-05,
1434
+ "loss": 0.0071,
1435
+ "step": 166
1436
+ },
1437
+ {
1438
+ "epoch": 1.930635838150289,
1439
+ "grad_norm": 0.020419662818312645,
1440
+ "learning_rate": 7.673648441311508e-05,
1441
+ "loss": 0.0076,
1442
+ "step": 167
1443
+ },
1444
+ {
1445
+ "epoch": 1.9421965317919074,
1446
+ "grad_norm": 0.012187760323286057,
1447
+ "learning_rate": 7.639262033560359e-05,
1448
+ "loss": 0.0064,
1449
+ "step": 168
1450
+ },
1451
+ {
1452
+ "epoch": 1.953757225433526,
1453
+ "grad_norm": 0.015659835189580917,
1454
+ "learning_rate": 7.604701702439651e-05,
1455
+ "loss": 0.0074,
1456
+ "step": 169
1457
+ },
1458
+ {
1459
+ "epoch": 1.9653179190751446,
1460
+ "grad_norm": 0.017916489392518997,
1461
+ "learning_rate": 7.56996972542285e-05,
1462
+ "loss": 0.0084,
1463
+ "step": 170
1464
+ },
1465
+ {
1466
+ "epoch": 1.9653179190751446,
1467
+ "eval_loss": 0.008561979979276657,
1468
+ "eval_runtime": 10.0323,
1469
+ "eval_samples_per_second": 4.984,
1470
+ "eval_steps_per_second": 1.296,
1471
+ "step": 170
1472
+ },
1473
+ {
1474
+ "epoch": 1.976878612716763,
1475
+ "grad_norm": 0.018545281141996384,
1476
+ "learning_rate": 7.535068391294617e-05,
1477
+ "loss": 0.0102,
1478
+ "step": 171
1479
+ },
1480
+ {
1481
+ "epoch": 1.9884393063583814,
1482
+ "grad_norm": 0.01769687980413437,
1483
+ "learning_rate": 7.500000000000001e-05,
1484
+ "loss": 0.0086,
1485
+ "step": 172
1486
+ },
1487
+ {
1488
+ "epoch": 2.0,
1489
+ "grad_norm": 0.021417992189526558,
1490
+ "learning_rate": 7.464766862492855e-05,
1491
+ "loss": 0.0092,
1492
+ "step": 173
1493
+ },
1494
+ {
1495
+ "epoch": 2.0115606936416186,
1496
+ "grad_norm": 0.01275323610752821,
1497
+ "learning_rate": 7.42937130058357e-05,
1498
+ "loss": 0.0069,
1499
+ "step": 174
1500
+ },
1501
+ {
1502
+ "epoch": 2.023121387283237,
1503
+ "grad_norm": 0.011270470917224884,
1504
+ "learning_rate": 7.393815646786046e-05,
1505
+ "loss": 0.0058,
1506
+ "step": 175
1507
+ },
1508
+ {
1509
+ "epoch": 2.023121387283237,
1510
+ "eval_loss": 0.008691162802278996,
1511
+ "eval_runtime": 10.0831,
1512
+ "eval_samples_per_second": 4.959,
1513
+ "eval_steps_per_second": 1.289,
1514
+ "step": 175
1515
+ },
1516
+ {
1517
+ "epoch": 2.0346820809248554,
1518
+ "grad_norm": 0.014580226503312588,
1519
+ "learning_rate": 7.358102244164003e-05,
1520
+ "loss": 0.0077,
1521
+ "step": 176
1522
+ },
1523
+ {
1524
+ "epoch": 2.046242774566474,
1525
+ "grad_norm": 0.014212528243660927,
1526
+ "learning_rate": 7.322233446176571e-05,
1527
+ "loss": 0.0074,
1528
+ "step": 177
1529
+ },
1530
+ {
1531
+ "epoch": 2.0578034682080926,
1532
+ "grad_norm": 0.01766706444323063,
1533
+ "learning_rate": 7.286211616523193e-05,
1534
+ "loss": 0.007,
1535
+ "step": 178
1536
+ },
1537
+ {
1538
+ "epoch": 2.069364161849711,
1539
+ "grad_norm": 0.015258056111633778,
1540
+ "learning_rate": 7.250039128987873e-05,
1541
+ "loss": 0.0073,
1542
+ "step": 179
1543
+ },
1544
+ {
1545
+ "epoch": 2.0809248554913293,
1546
+ "grad_norm": 0.01634743995964527,
1547
+ "learning_rate": 7.213718367282737e-05,
1548
+ "loss": 0.0056,
1549
+ "step": 180
1550
+ },
1551
+ {
1552
+ "epoch": 2.0809248554913293,
1553
+ "eval_loss": 0.008958614431321621,
1554
+ "eval_runtime": 10.0215,
1555
+ "eval_samples_per_second": 4.989,
1556
+ "eval_steps_per_second": 1.297,
1557
+ "step": 180
1558
+ },
1559
+ {
1560
+ "epoch": 2.092485549132948,
1561
+ "grad_norm": 0.014233705587685108,
1562
+ "learning_rate": 7.177251724890956e-05,
1563
+ "loss": 0.0056,
1564
+ "step": 181
1565
+ },
1566
+ {
1567
+ "epoch": 2.1040462427745665,
1568
+ "grad_norm": 0.013312169350683689,
1569
+ "learning_rate": 7.14064160490902e-05,
1570
+ "loss": 0.0055,
1571
+ "step": 182
1572
+ },
1573
+ {
1574
+ "epoch": 2.115606936416185,
1575
+ "grad_norm": 0.012955575250089169,
1576
+ "learning_rate": 7.103890419888367e-05,
1577
+ "loss": 0.0053,
1578
+ "step": 183
1579
+ },
1580
+ {
1581
+ "epoch": 2.1271676300578033,
1582
+ "grad_norm": 0.018879901617765427,
1583
+ "learning_rate": 7.067000591676416e-05,
1584
+ "loss": 0.0065,
1585
+ "step": 184
1586
+ },
1587
+ {
1588
+ "epoch": 2.138728323699422,
1589
+ "grad_norm": 0.01857951283454895,
1590
+ "learning_rate": 7.029974551256956e-05,
1591
+ "loss": 0.0077,
1592
+ "step": 185
1593
+ },
1594
+ {
1595
+ "epoch": 2.138728323699422,
1596
+ "eval_loss": 0.008626853115856647,
1597
+ "eval_runtime": 10.0278,
1598
+ "eval_samples_per_second": 4.986,
1599
+ "eval_steps_per_second": 1.296,
1600
+ "step": 185
1601
+ },
1602
+ {
1603
+ "epoch": 2.1502890173410405,
1604
+ "grad_norm": 0.015720047056674957,
1605
+ "learning_rate": 6.992814738589957e-05,
1606
+ "loss": 0.0057,
1607
+ "step": 186
1608
+ },
1609
+ {
1610
+ "epoch": 2.161849710982659,
1611
+ "grad_norm": 0.016932690516114235,
1612
+ "learning_rate": 6.95552360245078e-05,
1613
+ "loss": 0.0074,
1614
+ "step": 187
1615
+ },
1616
+ {
1617
+ "epoch": 2.1734104046242773,
1618
+ "grad_norm": 0.013904884457588196,
1619
+ "learning_rate": 6.918103600268799e-05,
1620
+ "loss": 0.0054,
1621
+ "step": 188
1622
+ },
1623
+ {
1624
+ "epoch": 2.184971098265896,
1625
+ "grad_norm": 0.015230257995426655,
1626
+ "learning_rate": 6.880557197965464e-05,
1627
+ "loss": 0.0053,
1628
+ "step": 189
1629
+ },
1630
+ {
1631
+ "epoch": 2.1965317919075145,
1632
+ "grad_norm": 0.017044221982359886,
1633
+ "learning_rate": 6.842886869791809e-05,
1634
+ "loss": 0.0061,
1635
+ "step": 190
1636
+ },
1637
+ {
1638
+ "epoch": 2.1965317919075145,
1639
+ "eval_loss": 0.00858032051473856,
1640
+ "eval_runtime": 10.0219,
1641
+ "eval_samples_per_second": 4.989,
1642
+ "eval_steps_per_second": 1.297,
1643
+ "step": 190
1644
+ },
1645
+ {
1646
+ "epoch": 2.208092485549133,
1647
+ "grad_norm": 0.01593642681837082,
1648
+ "learning_rate": 6.805095098165389e-05,
1649
+ "loss": 0.0056,
1650
+ "step": 191
1651
+ },
1652
+ {
1653
+ "epoch": 2.2196531791907512,
1654
+ "grad_norm": 0.018296780064702034,
1655
+ "learning_rate": 6.767184373506697e-05,
1656
+ "loss": 0.008,
1657
+ "step": 192
1658
+ },
1659
+ {
1660
+ "epoch": 2.23121387283237,
1661
+ "grad_norm": 0.02369534969329834,
1662
+ "learning_rate": 6.729157194075057e-05,
1663
+ "loss": 0.0116,
1664
+ "step": 193
1665
+ },
1666
+ {
1667
+ "epoch": 2.2427745664739884,
1668
+ "grad_norm": 0.020556915551424026,
1669
+ "learning_rate": 6.691016065803983e-05,
1670
+ "loss": 0.0078,
1671
+ "step": 194
1672
+ },
1673
+ {
1674
+ "epoch": 2.254335260115607,
1675
+ "grad_norm": 0.01714545115828514,
1676
+ "learning_rate": 6.652763502136043e-05,
1677
+ "loss": 0.008,
1678
+ "step": 195
1679
+ },
1680
+ {
1681
+ "epoch": 2.254335260115607,
1682
+ "eval_loss": 0.008329370059072971,
1683
+ "eval_runtime": 10.0304,
1684
+ "eval_samples_per_second": 4.985,
1685
+ "eval_steps_per_second": 1.296,
1686
+ "step": 195
1687
+ },
1688
+ {
1689
+ "epoch": 2.2658959537572256,
1690
+ "grad_norm": 0.013920610770583153,
1691
+ "learning_rate": 6.614402023857232e-05,
1692
+ "loss": 0.0057,
1693
+ "step": 196
1694
+ },
1695
+ {
1696
+ "epoch": 2.277456647398844,
1697
+ "grad_norm": 0.014315689913928509,
1698
+ "learning_rate": 6.57593415893085e-05,
1699
+ "loss": 0.0062,
1700
+ "step": 197
1701
+ },
1702
+ {
1703
+ "epoch": 2.2890173410404624,
1704
+ "grad_norm": 0.01451371144503355,
1705
+ "learning_rate": 6.537362442330916e-05,
1706
+ "loss": 0.0059,
1707
+ "step": 198
1708
+ },
1709
+ {
1710
+ "epoch": 2.300578034682081,
1711
+ "grad_norm": 0.013728981837630272,
1712
+ "learning_rate": 6.498689415875121e-05,
1713
+ "loss": 0.0054,
1714
+ "step": 199
1715
+ },
1716
+ {
1717
+ "epoch": 2.3121387283236996,
1718
+ "grad_norm": 0.01417378056794405,
1719
+ "learning_rate": 6.45991762805732e-05,
1720
+ "loss": 0.0058,
1721
+ "step": 200
1722
+ },
1723
+ {
1724
+ "epoch": 2.3121387283236996,
1725
+ "eval_loss": 0.00831348542124033,
1726
+ "eval_runtime": 10.0504,
1727
+ "eval_samples_per_second": 4.975,
1728
+ "eval_steps_per_second": 1.293,
1729
+ "step": 200
1730
+ },
1731
+ {
1732
+ "epoch": 2.3236994219653178,
1733
+ "grad_norm": 0.013795462436974049,
1734
+ "learning_rate": 6.421049633879588e-05,
1735
+ "loss": 0.005,
1736
+ "step": 201
1737
+ },
1738
+ {
1739
+ "epoch": 2.3352601156069364,
1740
+ "grad_norm": 0.01878678984940052,
1741
+ "learning_rate": 6.382087994683859e-05,
1742
+ "loss": 0.0075,
1743
+ "step": 202
1744
+ },
1745
+ {
1746
+ "epoch": 2.346820809248555,
1747
+ "grad_norm": 0.01882004365324974,
1748
+ "learning_rate": 6.343035277983127e-05,
1749
+ "loss": 0.0068,
1750
+ "step": 203
1751
+ },
1752
+ {
1753
+ "epoch": 2.3583815028901736,
1754
+ "grad_norm": 0.015659485012292862,
1755
+ "learning_rate": 6.303894057292261e-05,
1756
+ "loss": 0.006,
1757
+ "step": 204
1758
+ },
1759
+ {
1760
+ "epoch": 2.3699421965317917,
1761
+ "grad_norm": 0.015219546854496002,
1762
+ "learning_rate": 6.264666911958404e-05,
1763
+ "loss": 0.0047,
1764
+ "step": 205
1765
+ },
1766
+ {
1767
+ "epoch": 2.3699421965317917,
1768
+ "eval_loss": 0.00836299266666174,
1769
+ "eval_runtime": 10.0293,
1770
+ "eval_samples_per_second": 4.985,
1771
+ "eval_steps_per_second": 1.296,
1772
+ "step": 205
1773
+ },
1774
+ {
1775
+ "epoch": 2.3815028901734103,
1776
+ "grad_norm": 0.017362525686621666,
1777
+ "learning_rate": 6.225356426991007e-05,
1778
+ "loss": 0.0069,
1779
+ "step": 206
1780
+ },
1781
+ {
1782
+ "epoch": 2.393063583815029,
1783
+ "grad_norm": 0.014902186580002308,
1784
+ "learning_rate": 6.185965192891472e-05,
1785
+ "loss": 0.0055,
1786
+ "step": 207
1787
+ },
1788
+ {
1789
+ "epoch": 2.4046242774566475,
1790
+ "grad_norm": 0.016910729929804802,
1791
+ "learning_rate": 6.146495805482451e-05,
1792
+ "loss": 0.0062,
1793
+ "step": 208
1794
+ },
1795
+ {
1796
+ "epoch": 2.416184971098266,
1797
+ "grad_norm": 0.014512901194393635,
1798
+ "learning_rate": 6.106950865736777e-05,
1799
+ "loss": 0.0052,
1800
+ "step": 209
1801
+ },
1802
+ {
1803
+ "epoch": 2.4277456647398843,
1804
+ "grad_norm": 0.017721183598041534,
1805
+ "learning_rate": 6.0673329796060686e-05,
1806
+ "loss": 0.0066,
1807
+ "step": 210
1808
+ },
1809
+ {
1810
+ "epoch": 2.4277456647398843,
1811
+ "eval_loss": 0.008446984924376011,
1812
+ "eval_runtime": 10.0239,
1813
+ "eval_samples_per_second": 4.988,
1814
+ "eval_steps_per_second": 1.297,
1815
+ "step": 210
1816
+ },
1817
+ {
1818
+ "epoch": 2.439306358381503,
1819
+ "grad_norm": 0.01806679181754589,
1820
+ "learning_rate": 6.0276447578490035e-05,
1821
+ "loss": 0.0063,
1822
+ "step": 211
1823
+ },
1824
+ {
1825
+ "epoch": 2.4508670520231215,
1826
+ "grad_norm": 0.01761380210518837,
1827
+ "learning_rate": 5.987888815859266e-05,
1828
+ "loss": 0.0058,
1829
+ "step": 212
1830
+ },
1831
+ {
1832
+ "epoch": 2.4624277456647397,
1833
+ "grad_norm": 0.015691956505179405,
1834
+ "learning_rate": 5.9480677734932045e-05,
1835
+ "loss": 0.0057,
1836
+ "step": 213
1837
+ },
1838
+ {
1839
+ "epoch": 2.4739884393063583,
1840
+ "grad_norm": 0.016050070524215698,
1841
+ "learning_rate": 5.908184254897182e-05,
1842
+ "loss": 0.0073,
1843
+ "step": 214
1844
+ },
1845
+ {
1846
+ "epoch": 2.485549132947977,
1847
+ "grad_norm": 0.013452823273837566,
1848
+ "learning_rate": 5.868240888334653e-05,
1849
+ "loss": 0.0055,
1850
+ "step": 215
1851
+ },
1852
+ {
1853
+ "epoch": 2.485549132947977,
1854
+ "eval_loss": 0.008248448371887207,
1855
+ "eval_runtime": 10.0544,
1856
+ "eval_samples_per_second": 4.973,
1857
+ "eval_steps_per_second": 1.293,
1858
+ "step": 215
1859
+ },
1860
+ {
1861
+ "epoch": 2.4971098265895955,
1862
+ "grad_norm": 0.013310995884239674,
1863
+ "learning_rate": 5.8282403060129566e-05,
1864
+ "loss": 0.0064,
1865
+ "step": 216
1866
+ },
1867
+ {
1868
+ "epoch": 2.508670520231214,
1869
+ "grad_norm": 0.016307106241583824,
1870
+ "learning_rate": 5.788185143909868e-05,
1871
+ "loss": 0.006,
1872
+ "step": 217
1873
+ },
1874
+ {
1875
+ "epoch": 2.520231213872832,
1876
+ "grad_norm": 0.014403578825294971,
1877
+ "learning_rate": 5.7480780415998906e-05,
1878
+ "loss": 0.0053,
1879
+ "step": 218
1880
+ },
1881
+ {
1882
+ "epoch": 2.531791907514451,
1883
+ "grad_norm": 0.015278173610568047,
1884
+ "learning_rate": 5.707921642080299e-05,
1885
+ "loss": 0.0067,
1886
+ "step": 219
1887
+ },
1888
+ {
1889
+ "epoch": 2.5433526011560694,
1890
+ "grad_norm": 0.01573382504284382,
1891
+ "learning_rate": 5.66771859159699e-05,
1892
+ "loss": 0.0056,
1893
+ "step": 220
1894
+ },
1895
+ {
1896
+ "epoch": 2.5433526011560694,
1897
+ "eval_loss": 0.008289137855172157,
1898
+ "eval_runtime": 10.0106,
1899
+ "eval_samples_per_second": 4.995,
1900
+ "eval_steps_per_second": 1.299,
1901
+ "step": 220
1902
+ },
1903
+ {
1904
+ "epoch": 2.5549132947976876,
1905
+ "grad_norm": 0.014673051424324512,
1906
+ "learning_rate": 5.6274715394700805e-05,
1907
+ "loss": 0.0057,
1908
+ "step": 221
1909
+ },
1910
+ {
1911
+ "epoch": 2.5664739884393066,
1912
+ "grad_norm": 0.017399994656443596,
1913
+ "learning_rate": 5.587183137919332e-05,
1914
+ "loss": 0.0066,
1915
+ "step": 222
1916
+ },
1917
+ {
1918
+ "epoch": 2.578034682080925,
1919
+ "grad_norm": 0.015570064075291157,
1920
+ "learning_rate": 5.546856041889373e-05,
1921
+ "loss": 0.0062,
1922
+ "step": 223
1923
+ },
1924
+ {
1925
+ "epoch": 2.5895953757225434,
1926
+ "grad_norm": 0.012873631902039051,
1927
+ "learning_rate": 5.5064929088747316e-05,
1928
+ "loss": 0.0048,
1929
+ "step": 224
1930
+ },
1931
+ {
1932
+ "epoch": 2.601156069364162,
1933
+ "grad_norm": 0.01452395599335432,
1934
+ "learning_rate": 5.46609639874473e-05,
1935
+ "loss": 0.005,
1936
+ "step": 225
1937
+ },
1938
+ {
1939
+ "epoch": 2.601156069364162,
1940
+ "eval_loss": 0.008248119615018368,
1941
+ "eval_runtime": 10.0518,
1942
+ "eval_samples_per_second": 4.974,
1943
+ "eval_steps_per_second": 1.293,
1944
+ "step": 225
1945
+ },
1946
+ {
1947
+ "epoch": 2.61271676300578,
1948
+ "grad_norm": 0.015882886946201324,
1949
+ "learning_rate": 5.4256691735681786e-05,
1950
+ "loss": 0.006,
1951
+ "step": 226
1952
+ },
1953
+ {
1954
+ "epoch": 2.6242774566473988,
1955
+ "grad_norm": 0.01853213645517826,
1956
+ "learning_rate": 5.385213897437975e-05,
1957
+ "loss": 0.0072,
1958
+ "step": 227
1959
+ },
1960
+ {
1961
+ "epoch": 2.6358381502890174,
1962
+ "grad_norm": 0.01727055385708809,
1963
+ "learning_rate": 5.344733236295525e-05,
1964
+ "loss": 0.0056,
1965
+ "step": 228
1966
+ },
1967
+ {
1968
+ "epoch": 2.647398843930636,
1969
+ "grad_norm": 0.01715169847011566,
1970
+ "learning_rate": 5.3042298577550696e-05,
1971
+ "loss": 0.007,
1972
+ "step": 229
1973
+ },
1974
+ {
1975
+ "epoch": 2.6589595375722546,
1976
+ "grad_norm": 0.01657768152654171,
1977
+ "learning_rate": 5.263706430927895e-05,
1978
+ "loss": 0.0065,
1979
+ "step": 230
1980
+ },
1981
+ {
1982
+ "epoch": 2.6589595375722546,
1983
+ "eval_loss": 0.00817356538027525,
1984
+ "eval_runtime": 10.0412,
1985
+ "eval_samples_per_second": 4.979,
1986
+ "eval_steps_per_second": 1.295,
1987
+ "step": 230
1988
+ },
1989
+ {
1990
+ "epoch": 2.6705202312138727,
1991
+ "grad_norm": 0.016935985535383224,
1992
+ "learning_rate": 5.223165626246432e-05,
1993
+ "loss": 0.0056,
1994
+ "step": 231
1995
+ },
1996
+ {
1997
+ "epoch": 2.6820809248554913,
1998
+ "grad_norm": 0.016983183100819588,
1999
+ "learning_rate": 5.182610115288295e-05,
2000
+ "loss": 0.0054,
2001
+ "step": 232
2002
+ },
2003
+ {
2004
+ "epoch": 2.69364161849711,
2005
+ "grad_norm": 0.014110002666711807,
2006
+ "learning_rate": 5.142042570600212e-05,
2007
+ "loss": 0.0048,
2008
+ "step": 233
2009
+ },
2010
+ {
2011
+ "epoch": 2.705202312138728,
2012
+ "grad_norm": 0.015584226697683334,
2013
+ "learning_rate": 5.1014656655219197e-05,
2014
+ "loss": 0.0074,
2015
+ "step": 234
2016
+ },
2017
+ {
2018
+ "epoch": 2.7167630057803467,
2019
+ "grad_norm": 0.015623894520103931,
2020
+ "learning_rate": 5.060882074009988e-05,
2021
+ "loss": 0.0061,
2022
+ "step": 235
2023
+ },
2024
+ {
2025
+ "epoch": 2.7167630057803467,
2026
+ "eval_loss": 0.00805756263434887,
2027
+ "eval_runtime": 10.0337,
2028
+ "eval_samples_per_second": 4.983,
2029
+ "eval_steps_per_second": 1.296,
2030
+ "step": 235
2031
+ },
2032
+ {
2033
+ "epoch": 2.7283236994219653,
2034
+ "grad_norm": 0.014514243230223656,
2035
+ "learning_rate": 5.020294470461615e-05,
2036
+ "loss": 0.005,
2037
+ "step": 236
2038
+ },
2039
+ {
2040
+ "epoch": 2.739884393063584,
2041
+ "grad_norm": 0.016889233142137527,
2042
+ "learning_rate": 4.979705529538385e-05,
2043
+ "loss": 0.0065,
2044
+ "step": 237
2045
+ },
2046
+ {
2047
+ "epoch": 2.7514450867052025,
2048
+ "grad_norm": 0.014339439570903778,
2049
+ "learning_rate": 4.9391179259900125e-05,
2050
+ "loss": 0.0047,
2051
+ "step": 238
2052
+ },
2053
+ {
2054
+ "epoch": 2.7630057803468207,
2055
+ "grad_norm": 0.019386202096939087,
2056
+ "learning_rate": 4.8985343344780815e-05,
2057
+ "loss": 0.0055,
2058
+ "step": 239
2059
+ },
2060
+ {
2061
+ "epoch": 2.7745664739884393,
2062
+ "grad_norm": 0.016825564205646515,
2063
+ "learning_rate": 4.857957429399788e-05,
2064
+ "loss": 0.0052,
2065
+ "step": 240
2066
+ },
2067
+ {
2068
+ "epoch": 2.7745664739884393,
2069
+ "eval_loss": 0.008152703754603863,
2070
+ "eval_runtime": 10.0237,
2071
+ "eval_samples_per_second": 4.988,
2072
+ "eval_steps_per_second": 1.297,
2073
+ "step": 240
2074
+ },
2075
+ {
2076
+ "epoch": 2.786127167630058,
2077
+ "grad_norm": 0.018642200157046318,
2078
+ "learning_rate": 4.817389884711705e-05,
2079
+ "loss": 0.0054,
2080
+ "step": 241
2081
+ },
2082
+ {
2083
+ "epoch": 2.7976878612716765,
2084
+ "grad_norm": 0.017443155869841576,
2085
+ "learning_rate": 4.776834373753569e-05,
2086
+ "loss": 0.0066,
2087
+ "step": 242
2088
+ },
2089
+ {
2090
+ "epoch": 2.809248554913295,
2091
+ "grad_norm": 0.017855728045105934,
2092
+ "learning_rate": 4.7362935690721076e-05,
2093
+ "loss": 0.0064,
2094
+ "step": 243
2095
+ },
2096
+ {
2097
+ "epoch": 2.820809248554913,
2098
+ "grad_norm": 0.013038886711001396,
2099
+ "learning_rate": 4.695770142244931e-05,
2100
+ "loss": 0.0054,
2101
+ "step": 244
2102
+ },
2103
+ {
2104
+ "epoch": 2.832369942196532,
2105
+ "grad_norm": 0.0145301828160882,
2106
+ "learning_rate": 4.655266763704476e-05,
2107
+ "loss": 0.0053,
2108
+ "step": 245
2109
+ },
2110
+ {
2111
+ "epoch": 2.832369942196532,
2112
+ "eval_loss": 0.008140629157423973,
2113
+ "eval_runtime": 10.0264,
2114
+ "eval_samples_per_second": 4.987,
2115
+ "eval_steps_per_second": 1.297,
2116
+ "step": 245
2117
+ },
2118
+ {
2119
+ "epoch": 2.8439306358381504,
2120
+ "grad_norm": 0.015260045416653156,
2121
+ "learning_rate": 4.614786102562026e-05,
2122
+ "loss": 0.0048,
2123
+ "step": 246
2124
+ },
2125
+ {
2126
+ "epoch": 2.8554913294797686,
2127
+ "grad_norm": 0.014731310307979584,
2128
+ "learning_rate": 4.574330826431821e-05,
2129
+ "loss": 0.005,
2130
+ "step": 247
2131
+ },
2132
+ {
2133
+ "epoch": 2.867052023121387,
2134
+ "grad_norm": 0.017430312931537628,
2135
+ "learning_rate": 4.5339036012552716e-05,
2136
+ "loss": 0.0062,
2137
+ "step": 248
2138
+ },
2139
+ {
2140
+ "epoch": 2.878612716763006,
2141
+ "grad_norm": 0.01655244641005993,
2142
+ "learning_rate": 4.493507091125269e-05,
2143
+ "loss": 0.0056,
2144
+ "step": 249
2145
+ },
2146
+ {
2147
+ "epoch": 2.8901734104046244,
2148
+ "grad_norm": 0.016315851360559464,
2149
+ "learning_rate": 4.4531439581106295e-05,
2150
+ "loss": 0.0058,
2151
+ "step": 250
2152
+ },
2153
+ {
2154
+ "epoch": 2.8901734104046244,
2155
+ "eval_loss": 0.007892865687608719,
2156
+ "eval_runtime": 10.0251,
2157
+ "eval_samples_per_second": 4.988,
2158
+ "eval_steps_per_second": 1.297,
2159
+ "step": 250
2160
+ },
2161
+ {
2162
+ "epoch": 2.901734104046243,
2163
+ "grad_norm": 0.014720520935952663,
2164
+ "learning_rate": 4.412816862080668e-05,
2165
+ "loss": 0.0064,
2166
+ "step": 251
2167
+ },
2168
+ {
2169
+ "epoch": 2.913294797687861,
2170
+ "grad_norm": 0.015001147985458374,
2171
+ "learning_rate": 4.37252846052992e-05,
2172
+ "loss": 0.0057,
2173
+ "step": 252
2174
+ },
2175
+ {
2176
+ "epoch": 2.9248554913294798,
2177
+ "grad_norm": 0.015956144779920578,
2178
+ "learning_rate": 4.332281408403011e-05,
2179
+ "loss": 0.0056,
2180
+ "step": 253
2181
+ },
2182
+ {
2183
+ "epoch": 2.9364161849710984,
2184
+ "grad_norm": 0.016037022694945335,
2185
+ "learning_rate": 4.292078357919701e-05,
2186
+ "loss": 0.0059,
2187
+ "step": 254
2188
+ },
2189
+ {
2190
+ "epoch": 2.9479768786127165,
2191
+ "grad_norm": 0.014494068920612335,
2192
+ "learning_rate": 4.25192195840011e-05,
2193
+ "loss": 0.0052,
2194
+ "step": 255
2195
+ },
2196
+ {
2197
+ "epoch": 2.9479768786127165,
2198
+ "eval_loss": 0.007827498018741608,
2199
+ "eval_runtime": 10.0269,
2200
+ "eval_samples_per_second": 4.987,
2201
+ "eval_steps_per_second": 1.297,
2202
+ "step": 255
2203
+ },
2204
+ {
2205
+ "epoch": 2.959537572254335,
2206
+ "grad_norm": 0.015506073832511902,
2207
+ "learning_rate": 4.2118148560901325e-05,
2208
+ "loss": 0.0066,
2209
+ "step": 256
2210
+ },
2211
+ {
2212
+ "epoch": 2.9710982658959537,
2213
+ "grad_norm": 0.01482071541249752,
2214
+ "learning_rate": 4.171759693987046e-05,
2215
+ "loss": 0.0062,
2216
+ "step": 257
2217
+ },
2218
+ {
2219
+ "epoch": 2.9826589595375723,
2220
+ "grad_norm": 0.0164498183876276,
2221
+ "learning_rate": 4.131759111665349e-05,
2222
+ "loss": 0.0056,
2223
+ "step": 258
2224
+ },
2225
+ {
2226
+ "epoch": 2.994219653179191,
2227
+ "grad_norm": 0.014011871069669724,
2228
+ "learning_rate": 4.0918157451028185e-05,
2229
+ "loss": 0.0053,
2230
+ "step": 259
2231
+ },
2232
+ {
2233
+ "epoch": 3.005780346820809,
2234
+ "grad_norm": 0.024348195642232895,
2235
+ "learning_rate": 4.051932226506797e-05,
2236
+ "loss": 0.0071,
2237
+ "step": 260
2238
+ },
2239
+ {
2240
+ "epoch": 3.005780346820809,
2241
+ "eval_loss": 0.007992882281541824,
2242
+ "eval_runtime": 10.0301,
2243
+ "eval_samples_per_second": 4.985,
2244
+ "eval_steps_per_second": 1.296,
2245
+ "step": 260
2246
+ },
2247
+ {
2248
+ "epoch": 3.0173410404624277,
2249
+ "grad_norm": 0.018887817859649658,
2250
+ "learning_rate": 4.012111184140734e-05,
2251
+ "loss": 0.0051,
2252
+ "step": 261
2253
+ },
2254
+ {
2255
+ "epoch": 3.0289017341040463,
2256
+ "grad_norm": 0.017569325864315033,
2257
+ "learning_rate": 3.972355242150998e-05,
2258
+ "loss": 0.0051,
2259
+ "step": 262
2260
+ },
2261
+ {
2262
+ "epoch": 3.040462427745665,
2263
+ "grad_norm": 0.013190064579248428,
2264
+ "learning_rate": 3.932667020393933e-05,
2265
+ "loss": 0.0039,
2266
+ "step": 263
2267
+ },
2268
+ {
2269
+ "epoch": 3.052023121387283,
2270
+ "grad_norm": 0.015570548363029957,
2271
+ "learning_rate": 3.893049134263224e-05,
2272
+ "loss": 0.0035,
2273
+ "step": 264
2274
+ },
2275
+ {
2276
+ "epoch": 3.0635838150289016,
2277
+ "grad_norm": 0.018783550709486008,
2278
+ "learning_rate": 3.8535041945175506e-05,
2279
+ "loss": 0.0051,
2280
+ "step": 265
2281
+ },
2282
+ {
2283
+ "epoch": 3.0635838150289016,
2284
+ "eval_loss": 0.008158711716532707,
2285
+ "eval_runtime": 10.0165,
2286
+ "eval_samples_per_second": 4.992,
2287
+ "eval_steps_per_second": 1.298,
2288
+ "step": 265
2289
+ },
2290
+ {
2291
+ "epoch": 3.0751445086705202,
2292
+ "grad_norm": 0.01301144901663065,
2293
+ "learning_rate": 3.814034807108529e-05,
2294
+ "loss": 0.0034,
2295
+ "step": 266
2296
+ },
2297
+ {
2298
+ "epoch": 3.086705202312139,
2299
+ "grad_norm": 0.019954444840550423,
2300
+ "learning_rate": 3.774643573008995e-05,
2301
+ "loss": 0.0067,
2302
+ "step": 267
2303
+ },
2304
+ {
2305
+ "epoch": 3.098265895953757,
2306
+ "grad_norm": 0.01796858012676239,
2307
+ "learning_rate": 3.735333088041596e-05,
2308
+ "loss": 0.0037,
2309
+ "step": 268
2310
+ },
2311
+ {
2312
+ "epoch": 3.1098265895953756,
2313
+ "grad_norm": 0.016962885856628418,
2314
+ "learning_rate": 3.69610594270774e-05,
2315
+ "loss": 0.0039,
2316
+ "step": 269
2317
+ },
2318
+ {
2319
+ "epoch": 3.121387283236994,
2320
+ "grad_norm": 0.017634421586990356,
2321
+ "learning_rate": 3.656964722016875e-05,
2322
+ "loss": 0.0033,
2323
+ "step": 270
2324
+ },
2325
+ {
2326
+ "epoch": 3.121387283236994,
2327
+ "eval_loss": 0.00860854797065258,
2328
+ "eval_runtime": 10.0238,
2329
+ "eval_samples_per_second": 4.988,
2330
+ "eval_steps_per_second": 1.297,
2331
+ "step": 270
2332
+ },
2333
+ {
2334
+ "epoch": 3.132947976878613,
2335
+ "grad_norm": 0.019069235771894455,
2336
+ "learning_rate": 3.6179120053161416e-05,
2337
+ "loss": 0.0044,
2338
+ "step": 271
2339
+ },
2340
+ {
2341
+ "epoch": 3.1445086705202314,
2342
+ "grad_norm": 0.01804421842098236,
2343
+ "learning_rate": 3.578950366120414e-05,
2344
+ "loss": 0.004,
2345
+ "step": 272
2346
+ },
2347
+ {
2348
+ "epoch": 3.1560693641618496,
2349
+ "grad_norm": 0.016116416081786156,
2350
+ "learning_rate": 3.5400823719426815e-05,
2351
+ "loss": 0.0038,
2352
+ "step": 273
2353
+ },
2354
+ {
2355
+ "epoch": 3.167630057803468,
2356
+ "grad_norm": 0.019759787246584892,
2357
+ "learning_rate": 3.5013105841248795e-05,
2358
+ "loss": 0.0036,
2359
+ "step": 274
2360
+ },
2361
+ {
2362
+ "epoch": 3.179190751445087,
2363
+ "grad_norm": 0.014977723360061646,
2364
+ "learning_rate": 3.462637557669084e-05,
2365
+ "loss": 0.004,
2366
+ "step": 275
2367
+ },
2368
+ {
2369
+ "epoch": 3.179190751445087,
2370
+ "eval_loss": 0.008404241874814034,
2371
+ "eval_runtime": 10.0295,
2372
+ "eval_samples_per_second": 4.985,
2373
+ "eval_steps_per_second": 1.296,
2374
+ "step": 275
2375
+ },
2376
+ {
2377
+ "epoch": 3.1907514450867054,
2378
+ "grad_norm": 0.016791895031929016,
2379
+ "learning_rate": 3.424065841069152e-05,
2380
+ "loss": 0.0049,
2381
+ "step": 276
2382
+ },
2383
+ {
2384
+ "epoch": 3.2023121387283235,
2385
+ "grad_norm": 0.013895588926970959,
2386
+ "learning_rate": 3.38559797614277e-05,
2387
+ "loss": 0.0039,
2388
+ "step": 277
2389
+ },
2390
+ {
2391
+ "epoch": 3.213872832369942,
2392
+ "grad_norm": 0.017442645505070686,
2393
+ "learning_rate": 3.347236497863957e-05,
2394
+ "loss": 0.0042,
2395
+ "step": 278
2396
+ },
2397
+ {
2398
+ "epoch": 3.2254335260115607,
2399
+ "grad_norm": 0.018163053318858147,
2400
+ "learning_rate": 3.308983934196018e-05,
2401
+ "loss": 0.0044,
2402
+ "step": 279
2403
+ },
2404
+ {
2405
+ "epoch": 3.2369942196531793,
2406
+ "grad_norm": 0.017282122746109962,
2407
+ "learning_rate": 3.2708428059249436e-05,
2408
+ "loss": 0.0032,
2409
+ "step": 280
2410
+ },
2411
+ {
2412
+ "epoch": 3.2369942196531793,
2413
+ "eval_loss": 0.008181248791515827,
2414
+ "eval_runtime": 10.0205,
2415
+ "eval_samples_per_second": 4.99,
2416
+ "eval_steps_per_second": 1.297,
2417
+ "step": 280
2418
+ },
2419
+ {
2420
+ "epoch": 3.2485549132947975,
2421
+ "grad_norm": 0.017854265868663788,
2422
+ "learning_rate": 3.232815626493304e-05,
2423
+ "loss": 0.0054,
2424
+ "step": 281
2425
+ },
2426
+ {
2427
+ "epoch": 3.260115606936416,
2428
+ "grad_norm": 0.0203102994710207,
2429
+ "learning_rate": 3.1949049018346126e-05,
2430
+ "loss": 0.0052,
2431
+ "step": 282
2432
+ },
2433
+ {
2434
+ "epoch": 3.2716763005780347,
2435
+ "grad_norm": 0.015286475419998169,
2436
+ "learning_rate": 3.157113130208191e-05,
2437
+ "loss": 0.0049,
2438
+ "step": 283
2439
+ },
2440
+ {
2441
+ "epoch": 3.2832369942196533,
2442
+ "grad_norm": 0.014563402161002159,
2443
+ "learning_rate": 3.1194428020345376e-05,
2444
+ "loss": 0.0039,
2445
+ "step": 284
2446
+ },
2447
+ {
2448
+ "epoch": 3.294797687861272,
2449
+ "grad_norm": 0.016170360147953033,
2450
+ "learning_rate": 3.081896399731202e-05,
2451
+ "loss": 0.0042,
2452
+ "step": 285
2453
+ },
2454
+ {
2455
+ "epoch": 3.294797687861272,
2456
+ "eval_loss": 0.008185806684195995,
2457
+ "eval_runtime": 10.0071,
2458
+ "eval_samples_per_second": 4.996,
2459
+ "eval_steps_per_second": 1.299,
2460
+ "step": 285
2461
+ },
2462
+ {
2463
+ "epoch": 3.30635838150289,
2464
+ "grad_norm": 0.017802009359002113,
2465
+ "learning_rate": 3.0444763975492208e-05,
2466
+ "loss": 0.0045,
2467
+ "step": 286
2468
+ },
2469
+ {
2470
+ "epoch": 3.3179190751445087,
2471
+ "grad_norm": 0.013784883543848991,
2472
+ "learning_rate": 3.0071852614100426e-05,
2473
+ "loss": 0.0036,
2474
+ "step": 287
2475
+ },
2476
+ {
2477
+ "epoch": 3.3294797687861273,
2478
+ "grad_norm": 0.01664113625884056,
2479
+ "learning_rate": 2.9700254487430444e-05,
2480
+ "loss": 0.0044,
2481
+ "step": 288
2482
+ },
2483
+ {
2484
+ "epoch": 3.3410404624277454,
2485
+ "grad_norm": 0.01927308365702629,
2486
+ "learning_rate": 2.9329994083235857e-05,
2487
+ "loss": 0.0055,
2488
+ "step": 289
2489
+ },
2490
+ {
2491
+ "epoch": 3.352601156069364,
2492
+ "grad_norm": 0.01657339371740818,
2493
+ "learning_rate": 2.896109580111634e-05,
2494
+ "loss": 0.0035,
2495
+ "step": 290
2496
+ },
2497
+ {
2498
+ "epoch": 3.352601156069364,
2499
+ "eval_loss": 0.008166169747710228,
2500
+ "eval_runtime": 10.0143,
2501
+ "eval_samples_per_second": 4.993,
2502
+ "eval_steps_per_second": 1.298,
2503
+ "step": 290
2504
+ },
2505
+ {
2506
+ "epoch": 3.3641618497109826,
2507
+ "grad_norm": 0.017788324505090714,
2508
+ "learning_rate": 2.859358395090983e-05,
2509
+ "loss": 0.0042,
2510
+ "step": 291
2511
+ },
2512
+ {
2513
+ "epoch": 3.3757225433526012,
2514
+ "grad_norm": 0.016261830925941467,
2515
+ "learning_rate": 2.8227482751090445e-05,
2516
+ "loss": 0.0043,
2517
+ "step": 292
2518
+ },
2519
+ {
2520
+ "epoch": 3.38728323699422,
2521
+ "grad_norm": 0.01472635380923748,
2522
+ "learning_rate": 2.7862816327172636e-05,
2523
+ "loss": 0.0037,
2524
+ "step": 293
2525
+ },
2526
+ {
2527
+ "epoch": 3.398843930635838,
2528
+ "grad_norm": 0.016420332714915276,
2529
+ "learning_rate": 2.7499608710121288e-05,
2530
+ "loss": 0.0042,
2531
+ "step": 294
2532
+ },
2533
+ {
2534
+ "epoch": 3.4104046242774566,
2535
+ "grad_norm": 0.016155356541275978,
2536
+ "learning_rate": 2.7137883834768073e-05,
2537
+ "loss": 0.0041,
2538
+ "step": 295
2539
+ },
2540
+ {
2541
+ "epoch": 3.4104046242774566,
2542
+ "eval_loss": 0.008127645589411259,
2543
+ "eval_runtime": 10.0238,
2544
+ "eval_samples_per_second": 4.988,
2545
+ "eval_steps_per_second": 1.297,
2546
+ "step": 295
2547
+ },
2548
+ {
2549
+ "epoch": 3.421965317919075,
2550
+ "grad_norm": 0.016076598316431046,
2551
+ "learning_rate": 2.6777665538234293e-05,
2552
+ "loss": 0.004,
2553
+ "step": 296
2554
+ },
2555
+ {
2556
+ "epoch": 3.433526011560694,
2557
+ "grad_norm": 0.017685944214463234,
2558
+ "learning_rate": 2.641897755835997e-05,
2559
+ "loss": 0.0046,
2560
+ "step": 297
2561
+ },
2562
+ {
2563
+ "epoch": 3.445086705202312,
2564
+ "grad_norm": 0.03867075592279434,
2565
+ "learning_rate": 2.606184353213956e-05,
2566
+ "loss": 0.0039,
2567
+ "step": 298
2568
+ },
2569
+ {
2570
+ "epoch": 3.4566473988439306,
2571
+ "grad_norm": 0.014819984324276447,
2572
+ "learning_rate": 2.5706286994164315e-05,
2573
+ "loss": 0.0037,
2574
+ "step": 299
2575
+ },
2576
+ {
2577
+ "epoch": 3.468208092485549,
2578
+ "grad_norm": 0.016593076288700104,
2579
+ "learning_rate": 2.5352331375071437e-05,
2580
+ "loss": 0.0048,
2581
+ "step": 300
2582
+ },
2583
+ {
2584
+ "epoch": 3.468208092485549,
2585
+ "eval_loss": 0.007986278273165226,
2586
+ "eval_runtime": 10.0089,
2587
+ "eval_samples_per_second": 4.996,
2588
+ "eval_steps_per_second": 1.299,
2589
+ "step": 300
2590
+ },
2591
+ {
2592
+ "epoch": 3.479768786127168,
2593
+ "grad_norm": 0.015115424059331417,
2594
+ "learning_rate": 2.500000000000001e-05,
2595
+ "loss": 0.0034,
2596
+ "step": 301
2597
+ },
2598
+ {
2599
+ "epoch": 3.491329479768786,
2600
+ "grad_norm": 0.016738681122660637,
2601
+ "learning_rate": 2.4649316087053837e-05,
2602
+ "loss": 0.0041,
2603
+ "step": 302
2604
+ },
2605
+ {
2606
+ "epoch": 3.5028901734104045,
2607
+ "grad_norm": 0.014471864327788353,
2608
+ "learning_rate": 2.4300302745771507e-05,
2609
+ "loss": 0.0034,
2610
+ "step": 303
2611
+ },
2612
+ {
2613
+ "epoch": 3.514450867052023,
2614
+ "grad_norm": 0.015291919000446796,
2615
+ "learning_rate": 2.3952982975603496e-05,
2616
+ "loss": 0.0043,
2617
+ "step": 304
2618
+ },
2619
+ {
2620
+ "epoch": 3.5260115606936417,
2621
+ "grad_norm": 0.017901018261909485,
2622
+ "learning_rate": 2.360737966439641e-05,
2623
+ "loss": 0.0046,
2624
+ "step": 305
2625
+ },
2626
+ {
2627
+ "epoch": 3.5260115606936417,
2628
+ "eval_loss": 0.00799076072871685,
2629
+ "eval_runtime": 10.1032,
2630
+ "eval_samples_per_second": 4.949,
2631
+ "eval_steps_per_second": 1.287,
2632
+ "step": 305
2633
+ },
2634
+ {
2635
+ "epoch": 3.5375722543352603,
2636
+ "grad_norm": 0.017450664192438126,
2637
+ "learning_rate": 2.326351558688493e-05,
2638
+ "loss": 0.0047,
2639
+ "step": 306
2640
+ },
2641
+ {
2642
+ "epoch": 3.5491329479768785,
2643
+ "grad_norm": 0.017974600195884705,
2644
+ "learning_rate": 2.2921413403190772e-05,
2645
+ "loss": 0.0046,
2646
+ "step": 307
2647
+ },
2648
+ {
2649
+ "epoch": 3.560693641618497,
2650
+ "grad_norm": 0.014545281417667866,
2651
+ "learning_rate": 2.2581095657329598e-05,
2652
+ "loss": 0.0033,
2653
+ "step": 308
2654
+ },
2655
+ {
2656
+ "epoch": 3.5722543352601157,
2657
+ "grad_norm": 0.015802579000592232,
2658
+ "learning_rate": 2.224258477572524e-05,
2659
+ "loss": 0.0037,
2660
+ "step": 309
2661
+ },
2662
+ {
2663
+ "epoch": 3.583815028901734,
2664
+ "grad_norm": 0.017255526036024094,
2665
+ "learning_rate": 2.1905903065731974e-05,
2666
+ "loss": 0.004,
2667
+ "step": 310
2668
+ },
2669
+ {
2670
+ "epoch": 3.583815028901734,
2671
+ "eval_loss": 0.007966941222548485,
2672
+ "eval_runtime": 10.0846,
2673
+ "eval_samples_per_second": 4.958,
2674
+ "eval_steps_per_second": 1.289,
2675
+ "step": 310
2676
+ },
2677
+ {
2678
+ "epoch": 3.5953757225433525,
2679
+ "grad_norm": 0.014843069948256016,
2680
+ "learning_rate": 2.1571072714164443e-05,
2681
+ "loss": 0.0035,
2682
+ "step": 311
2683
+ },
2684
+ {
2685
+ "epoch": 3.606936416184971,
2686
+ "grad_norm": 0.01944170519709587,
2687
+ "learning_rate": 2.123811578583551e-05,
2688
+ "loss": 0.0056,
2689
+ "step": 312
2690
+ },
2691
+ {
2692
+ "epoch": 3.6184971098265897,
2693
+ "grad_norm": 0.017738202586770058,
2694
+ "learning_rate": 2.090705422210237e-05,
2695
+ "loss": 0.0043,
2696
+ "step": 313
2697
+ },
2698
+ {
2699
+ "epoch": 3.6300578034682083,
2700
+ "grad_norm": 0.018833834677934647,
2701
+ "learning_rate": 2.057790983942047e-05,
2702
+ "loss": 0.0049,
2703
+ "step": 314
2704
+ },
2705
+ {
2706
+ "epoch": 3.6416184971098264,
2707
+ "grad_norm": 0.013943798840045929,
2708
+ "learning_rate": 2.0250704327906024e-05,
2709
+ "loss": 0.0032,
2710
+ "step": 315
2711
+ },
2712
+ {
2713
+ "epoch": 3.6416184971098264,
2714
+ "eval_loss": 0.008140211924910545,
2715
+ "eval_runtime": 10.0297,
2716
+ "eval_samples_per_second": 4.985,
2717
+ "eval_steps_per_second": 1.296,
2718
+ "step": 315
2719
+ },
2720
+ {
2721
+ "epoch": 3.653179190751445,
2722
+ "grad_norm": 0.015995629131793976,
2723
+ "learning_rate": 1.9925459249906485e-05,
2724
+ "loss": 0.0037,
2725
+ "step": 316
2726
+ },
2727
+ {
2728
+ "epoch": 3.6647398843930636,
2729
+ "grad_norm": 0.017212923616170883,
2730
+ "learning_rate": 1.960219603857977e-05,
2731
+ "loss": 0.0048,
2732
+ "step": 317
2733
+ },
2734
+ {
2735
+ "epoch": 3.6763005780346822,
2736
+ "grad_norm": 0.019134720787405968,
2737
+ "learning_rate": 1.928093599648179e-05,
2738
+ "loss": 0.0047,
2739
+ "step": 318
2740
+ },
2741
+ {
2742
+ "epoch": 3.687861271676301,
2743
+ "grad_norm": 0.016614330932497978,
2744
+ "learning_rate": 1.8961700294162577e-05,
2745
+ "loss": 0.0034,
2746
+ "step": 319
2747
+ },
2748
+ {
2749
+ "epoch": 3.699421965317919,
2750
+ "grad_norm": 0.017316371202468872,
2751
+ "learning_rate": 1.86445099687713e-05,
2752
+ "loss": 0.0039,
2753
+ "step": 320
2754
+ },
2755
+ {
2756
+ "epoch": 3.699421965317919,
2757
+ "eval_loss": 0.008361711166799068,
2758
+ "eval_runtime": 10.0095,
2759
+ "eval_samples_per_second": 4.995,
2760
+ "eval_steps_per_second": 1.299,
2761
+ "step": 320
2762
+ },
2763
+ {
2764
+ "epoch": 3.7109826589595376,
2765
+ "grad_norm": 0.015041043981909752,
2766
+ "learning_rate": 1.832938592266984e-05,
2767
+ "loss": 0.0037,
2768
+ "step": 321
2769
+ },
2770
+ {
2771
+ "epoch": 3.722543352601156,
2772
+ "grad_norm": 0.0185141172260046,
2773
+ "learning_rate": 1.801634892205545e-05,
2774
+ "loss": 0.0041,
2775
+ "step": 322
2776
+ },
2777
+ {
2778
+ "epoch": 3.7341040462427744,
2779
+ "grad_norm": 0.017875155434012413,
2780
+ "learning_rate": 1.7705419595592193e-05,
2781
+ "loss": 0.0037,
2782
+ "step": 323
2783
+ },
2784
+ {
2785
+ "epoch": 3.745664739884393,
2786
+ "grad_norm": 0.015563211403787136,
2787
+ "learning_rate": 1.7396618433051647e-05,
2788
+ "loss": 0.0043,
2789
+ "step": 324
2790
+ },
2791
+ {
2792
+ "epoch": 3.7572254335260116,
2793
+ "grad_norm": 0.019554760307073593,
2794
+ "learning_rate": 1.7089965783962608e-05,
2795
+ "loss": 0.0042,
2796
+ "step": 325
2797
+ },
2798
+ {
2799
+ "epoch": 3.7572254335260116,
2800
+ "eval_loss": 0.008260131813585758,
2801
+ "eval_runtime": 10.0115,
2802
+ "eval_samples_per_second": 4.994,
2803
+ "eval_steps_per_second": 1.299,
2804
+ "step": 325
2805
+ },
2806
+ {
2807
+ "epoch": 3.76878612716763,
2808
+ "grad_norm": 0.016527488827705383,
2809
+ "learning_rate": 1.678548185627004e-05,
2810
+ "loss": 0.0043,
2811
+ "step": 326
2812
+ },
2813
+ {
2814
+ "epoch": 3.7803468208092488,
2815
+ "grad_norm": 0.015184947289526463,
2816
+ "learning_rate": 1.6483186715003523e-05,
2817
+ "loss": 0.0035,
2818
+ "step": 327
2819
+ },
2820
+ {
2821
+ "epoch": 3.791907514450867,
2822
+ "grad_norm": 0.020948296412825584,
2823
+ "learning_rate": 1.618310028095486e-05,
2824
+ "loss": 0.0039,
2825
+ "step": 328
2826
+ },
2827
+ {
2828
+ "epoch": 3.8034682080924855,
2829
+ "grad_norm": 0.014377256855368614,
2830
+ "learning_rate": 1.5885242329365448e-05,
2831
+ "loss": 0.0033,
2832
+ "step": 329
2833
+ },
2834
+ {
2835
+ "epoch": 3.815028901734104,
2836
+ "grad_norm": 0.017349926754832268,
2837
+ "learning_rate": 1.5589632488623053e-05,
2838
+ "loss": 0.0046,
2839
+ "step": 330
2840
+ },
2841
+ {
2842
+ "epoch": 3.815028901734104,
2843
+ "eval_loss": 0.008042494766414165,
2844
+ "eval_runtime": 10.1315,
2845
+ "eval_samples_per_second": 4.935,
2846
+ "eval_steps_per_second": 1.283,
2847
+ "step": 330
2848
+ },
2849
+ {
2850
+ "epoch": 3.8265895953757223,
2851
+ "grad_norm": 0.014084051363170147,
2852
+ "learning_rate": 1.5296290238968303e-05,
2853
+ "loss": 0.0032,
2854
+ "step": 331
2855
+ },
2856
+ {
2857
+ "epoch": 3.838150289017341,
2858
+ "grad_norm": 0.016601048409938812,
2859
+ "learning_rate": 1.500523491121108e-05,
2860
+ "loss": 0.0035,
2861
+ "step": 332
2862
+ },
2863
+ {
2864
+ "epoch": 3.8497109826589595,
2865
+ "grad_norm": 0.015788624063134193,
2866
+ "learning_rate": 1.47164856854565e-05,
2867
+ "loss": 0.0038,
2868
+ "step": 333
2869
+ },
2870
+ {
2871
+ "epoch": 3.861271676300578,
2872
+ "grad_norm": 0.014880317263305187,
2873
+ "learning_rate": 1.4430061589841121e-05,
2874
+ "loss": 0.0034,
2875
+ "step": 334
2876
+ },
2877
+ {
2878
+ "epoch": 3.8728323699421967,
2879
+ "grad_norm": 0.01920904405415058,
2880
+ "learning_rate": 1.4145981499278876e-05,
2881
+ "loss": 0.0035,
2882
+ "step": 335
2883
+ },
2884
+ {
2885
+ "epoch": 3.8728323699421967,
2886
+ "eval_loss": 0.008081013336777687,
2887
+ "eval_runtime": 10.0106,
2888
+ "eval_samples_per_second": 4.995,
2889
+ "eval_steps_per_second": 1.299,
2890
+ "step": 335
2891
+ },
2892
+ {
2893
+ "epoch": 3.884393063583815,
2894
+ "grad_norm": 0.016501102596521378,
2895
+ "learning_rate": 1.386426413421738e-05,
2896
+ "loss": 0.004,
2897
+ "step": 336
2898
+ },
2899
+ {
2900
+ "epoch": 3.8959537572254335,
2901
+ "grad_norm": 0.016265930607914925,
2902
+ "learning_rate": 1.3584928059404205e-05,
2903
+ "loss": 0.0034,
2904
+ "step": 337
2905
+ },
2906
+ {
2907
+ "epoch": 3.907514450867052,
2908
+ "grad_norm": 0.019726134836673737,
2909
+ "learning_rate": 1.3307991682663462e-05,
2910
+ "loss": 0.0031,
2911
+ "step": 338
2912
+ },
2913
+ {
2914
+ "epoch": 3.9190751445086707,
2915
+ "grad_norm": 0.016232285648584366,
2916
+ "learning_rate": 1.3033473253682848e-05,
2917
+ "loss": 0.0034,
2918
+ "step": 339
2919
+ },
2920
+ {
2921
+ "epoch": 3.9306358381502893,
2922
+ "grad_norm": 0.02013998292386532,
2923
+ "learning_rate": 1.2761390862810907e-05,
2924
+ "loss": 0.0048,
2925
+ "step": 340
2926
+ },
2927
+ {
2928
+ "epoch": 3.9306358381502893,
2929
+ "eval_loss": 0.008075674995779991,
2930
+ "eval_runtime": 10.0299,
2931
+ "eval_samples_per_second": 4.985,
2932
+ "eval_steps_per_second": 1.296,
2933
+ "step": 340
2934
+ },
2935
+ {
2936
+ "epoch": 3.9421965317919074,
2937
+ "grad_norm": 0.013452830724418163,
2938
+ "learning_rate": 1.2491762439865035e-05,
2939
+ "loss": 0.003,
2940
+ "step": 341
2941
+ },
2942
+ {
2943
+ "epoch": 3.953757225433526,
2944
+ "grad_norm": 0.012992053292691708,
2945
+ "learning_rate": 1.2224605752949786e-05,
2946
+ "loss": 0.0028,
2947
+ "step": 342
2948
+ },
2949
+ {
2950
+ "epoch": 3.9653179190751446,
2951
+ "grad_norm": 0.015416258946061134,
2952
+ "learning_rate": 1.1959938407286097e-05,
2953
+ "loss": 0.0037,
2954
+ "step": 343
2955
+ },
2956
+ {
2957
+ "epoch": 3.976878612716763,
2958
+ "grad_norm": 0.015255059115588665,
2959
+ "learning_rate": 1.1697777844051105e-05,
2960
+ "loss": 0.0036,
2961
+ "step": 344
2962
+ },
2963
+ {
2964
+ "epoch": 3.9884393063583814,
2965
+ "grad_norm": 0.018186306580901146,
2966
+ "learning_rate": 1.143814133922872e-05,
2967
+ "loss": 0.0056,
2968
+ "step": 345
2969
+ },
2970
+ {
2971
+ "epoch": 3.9884393063583814,
2972
+ "eval_loss": 0.008018155582249165,
2973
+ "eval_runtime": 10.115,
2974
+ "eval_samples_per_second": 4.943,
2975
+ "eval_steps_per_second": 1.285,
2976
+ "step": 345
2977
+ },
2978
+ {
2979
+ "epoch": 4.0,
2980
+ "grad_norm": 0.026972023770213127,
2981
+ "learning_rate": 1.118104600247129e-05,
2982
+ "loss": 0.0065,
2983
+ "step": 346
2984
+ },
2985
+ {
2986
+ "epoch": 4.011560693641618,
2987
+ "grad_norm": 0.01358290296047926,
2988
+ "learning_rate": 1.0926508775971994e-05,
2989
+ "loss": 0.0029,
2990
+ "step": 347
2991
+ },
2992
+ {
2993
+ "epoch": 4.023121387283237,
2994
+ "grad_norm": 0.011624607257544994,
2995
+ "learning_rate": 1.0674546433348454e-05,
2996
+ "loss": 0.0028,
2997
+ "step": 348
2998
+ },
2999
+ {
3000
+ "epoch": 4.034682080924855,
3001
+ "grad_norm": 0.012059401720762253,
3002
+ "learning_rate": 1.0425175578537299e-05,
3003
+ "loss": 0.0033,
3004
+ "step": 349
3005
+ },
3006
+ {
3007
+ "epoch": 4.046242774566474,
3008
+ "grad_norm": 0.011458152905106544,
3009
+ "learning_rate": 1.0178412644700092e-05,
3010
+ "loss": 0.0025,
3011
+ "step": 350
3012
+ },
3013
+ {
3014
+ "epoch": 4.046242774566474,
3015
+ "eval_loss": 0.008002113550901413,
3016
+ "eval_runtime": 10.1777,
3017
+ "eval_samples_per_second": 4.913,
3018
+ "eval_steps_per_second": 1.277,
3019
+ "step": 350
3020
+ },
3021
+ {
3022
+ "epoch": 4.057803468208093,
3023
+ "grad_norm": 0.012259789742529392,
3024
+ "learning_rate": 9.934273893140334e-06,
3025
+ "loss": 0.0027,
3026
+ "step": 351
3027
+ },
3028
+ {
3029
+ "epoch": 4.069364161849711,
3030
+ "grad_norm": 0.013933391310274601,
3031
+ "learning_rate": 9.692775412231863e-06,
3032
+ "loss": 0.0027,
3033
+ "step": 352
3034
+ },
3035
+ {
3036
+ "epoch": 4.08092485549133,
3037
+ "grad_norm": 0.012962523847818375,
3038
+ "learning_rate": 9.453933116358715e-06,
3039
+ "loss": 0.0024,
3040
+ "step": 353
3041
+ },
3042
+ {
3043
+ "epoch": 4.092485549132948,
3044
+ "grad_norm": 0.01309504546225071,
3045
+ "learning_rate": 9.21776274486636e-06,
3046
+ "loss": 0.0028,
3047
+ "step": 354
3048
+ },
3049
+ {
3050
+ "epoch": 4.104046242774566,
3051
+ "grad_norm": 0.015043212100863457,
3052
+ "learning_rate": 8.984279861024453e-06,
3053
+ "loss": 0.0035,
3054
+ "step": 355
3055
+ },
3056
+ {
3057
+ "epoch": 4.104046242774566,
3058
+ "eval_loss": 0.008168390020728111,
3059
+ "eval_runtime": 10.0257,
3060
+ "eval_samples_per_second": 4.987,
3061
+ "eval_steps_per_second": 1.297,
3062
+ "step": 355
3063
+ },
3064
+ {
3065
+ "epoch": 4.115606936416185,
3066
+ "grad_norm": 0.014944328926503658,
3067
+ "learning_rate": 8.75349985100134e-06,
3068
+ "loss": 0.0034,
3069
+ "step": 356
3070
+ },
3071
+ {
3072
+ "epoch": 4.127167630057803,
3073
+ "grad_norm": 0.016272595152258873,
3074
+ "learning_rate": 8.525437922850032e-06,
3075
+ "loss": 0.0025,
3076
+ "step": 357
3077
+ },
3078
+ {
3079
+ "epoch": 4.138728323699422,
3080
+ "grad_norm": 0.013790381141006947,
3081
+ "learning_rate": 8.30010910550611e-06,
3082
+ "loss": 0.0025,
3083
+ "step": 358
3084
+ },
3085
+ {
3086
+ "epoch": 4.1502890173410405,
3087
+ "grad_norm": 0.013851807452738285,
3088
+ "learning_rate": 8.077528247797234e-06,
3089
+ "loss": 0.0029,
3090
+ "step": 359
3091
+ },
3092
+ {
3093
+ "epoch": 4.161849710982659,
3094
+ "grad_norm": 0.013270116411149502,
3095
+ "learning_rate": 7.857710017464737e-06,
3096
+ "loss": 0.0028,
3097
+ "step": 360
3098
+ },
3099
+ {
3100
+ "epoch": 4.161849710982659,
3101
+ "eval_loss": 0.00829649344086647,
3102
+ "eval_runtime": 10.0,
3103
+ "eval_samples_per_second": 5.0,
3104
+ "eval_steps_per_second": 1.3,
3105
+ "step": 360
3106
+ },
3107
+ {
3108
+ "epoch": 4.173410404624278,
3109
+ "grad_norm": 0.017382489517331123,
3110
+ "learning_rate": 7.640668900196984e-06,
3111
+ "loss": 0.0041,
3112
+ "step": 361
3113
+ },
3114
+ {
3115
+ "epoch": 4.184971098265896,
3116
+ "grad_norm": 0.014215102419257164,
3117
+ "learning_rate": 7.426419198674772e-06,
3118
+ "loss": 0.0025,
3119
+ "step": 362
3120
+ },
3121
+ {
3122
+ "epoch": 4.196531791907514,
3123
+ "grad_norm": 0.01837097853422165,
3124
+ "learning_rate": 7.214975031628857e-06,
3125
+ "loss": 0.0036,
3126
+ "step": 363
3127
+ },
3128
+ {
3129
+ "epoch": 4.208092485549133,
3130
+ "grad_norm": 0.01614932157099247,
3131
+ "learning_rate": 7.006350332909495e-06,
3132
+ "loss": 0.0027,
3133
+ "step": 364
3134
+ },
3135
+ {
3136
+ "epoch": 4.219653179190751,
3137
+ "grad_norm": 0.016307765617966652,
3138
+ "learning_rate": 6.800558850568295e-06,
3139
+ "loss": 0.0028,
3140
+ "step": 365
3141
+ },
3142
+ {
3143
+ "epoch": 4.219653179190751,
3144
+ "eval_loss": 0.008427992463111877,
3145
+ "eval_runtime": 10.0341,
3146
+ "eval_samples_per_second": 4.983,
3147
+ "eval_steps_per_second": 1.296,
3148
+ "step": 365
3149
+ },
3150
+ {
3151
+ "epoch": 4.23121387283237,
3152
+ "grad_norm": 0.024037158116698265,
3153
+ "learning_rate": 6.5976141459521355e-06,
3154
+ "loss": 0.0026,
3155
+ "step": 366
3156
+ },
3157
+ {
3158
+ "epoch": 4.242774566473988,
3159
+ "grad_norm": 0.018489433452486992,
3160
+ "learning_rate": 6.397529592809614e-06,
3161
+ "loss": 0.0034,
3162
+ "step": 367
3163
+ },
3164
+ {
3165
+ "epoch": 4.254335260115607,
3166
+ "grad_norm": 0.013452818617224693,
3167
+ "learning_rate": 6.2003183764096695e-06,
3168
+ "loss": 0.0025,
3169
+ "step": 368
3170
+ },
3171
+ {
3172
+ "epoch": 4.265895953757226,
3173
+ "grad_norm": 0.017129331827163696,
3174
+ "learning_rate": 6.005993492672657e-06,
3175
+ "loss": 0.0037,
3176
+ "step": 369
3177
+ },
3178
+ {
3179
+ "epoch": 4.277456647398844,
3180
+ "grad_norm": 0.01633543334901333,
3181
+ "learning_rate": 5.814567747314048e-06,
3182
+ "loss": 0.003,
3183
+ "step": 370
3184
+ },
3185
+ {
3186
+ "epoch": 4.277456647398844,
3187
+ "eval_loss": 0.008522397838532925,
3188
+ "eval_runtime": 10.0223,
3189
+ "eval_samples_per_second": 4.989,
3190
+ "eval_steps_per_second": 1.297,
3191
+ "step": 370
3192
+ },
3193
+ {
3194
+ "epoch": 4.289017341040463,
3195
+ "grad_norm": 0.013097944669425488,
3196
+ "learning_rate": 5.626053755000421e-06,
3197
+ "loss": 0.0021,
3198
+ "step": 371
3199
+ },
3200
+ {
3201
+ "epoch": 4.300578034682081,
3202
+ "grad_norm": 0.016527358442544937,
3203
+ "learning_rate": 5.440463938518303e-06,
3204
+ "loss": 0.003,
3205
+ "step": 372
3206
+ },
3207
+ {
3208
+ "epoch": 4.312138728323699,
3209
+ "grad_norm": 0.015918167307972908,
3210
+ "learning_rate": 5.257810527955409e-06,
3211
+ "loss": 0.0027,
3212
+ "step": 373
3213
+ },
3214
+ {
3215
+ "epoch": 4.323699421965318,
3216
+ "grad_norm": 0.01487621571868658,
3217
+ "learning_rate": 5.078105559894791e-06,
3218
+ "loss": 0.0025,
3219
+ "step": 374
3220
+ },
3221
+ {
3222
+ "epoch": 4.335260115606936,
3223
+ "grad_norm": 0.01791987195611,
3224
+ "learning_rate": 4.901360876621597e-06,
3225
+ "loss": 0.0033,
3226
+ "step": 375
3227
+ },
3228
+ {
3229
+ "epoch": 4.335260115606936,
3230
+ "eval_loss": 0.008536826819181442,
3231
+ "eval_runtime": 10.0084,
3232
+ "eval_samples_per_second": 4.996,
3233
+ "eval_steps_per_second": 1.299,
3234
+ "step": 375
3235
+ },
3236
+ {
3237
+ "epoch": 4.3468208092485545,
3238
+ "grad_norm": 0.013367927633225918,
3239
+ "learning_rate": 4.727588125342669e-06,
3240
+ "loss": 0.0022,
3241
+ "step": 376
3242
+ },
3243
+ {
3244
+ "epoch": 4.358381502890174,
3245
+ "grad_norm": 0.013060873374342918,
3246
+ "learning_rate": 4.556798757419068e-06,
3247
+ "loss": 0.0025,
3248
+ "step": 377
3249
+ },
3250
+ {
3251
+ "epoch": 4.369942196531792,
3252
+ "grad_norm": 0.014499946497380733,
3253
+ "learning_rate": 4.389004027611404e-06,
3254
+ "loss": 0.0027,
3255
+ "step": 378
3256
+ },
3257
+ {
3258
+ "epoch": 4.381502890173411,
3259
+ "grad_norm": 0.01943526417016983,
3260
+ "learning_rate": 4.224214993338149e-06,
3261
+ "loss": 0.004,
3262
+ "step": 379
3263
+ },
3264
+ {
3265
+ "epoch": 4.393063583815029,
3266
+ "grad_norm": 0.019275827333331108,
3267
+ "learning_rate": 4.062442513947007e-06,
3268
+ "loss": 0.003,
3269
+ "step": 380
3270
+ },
3271
+ {
3272
+ "epoch": 4.393063583815029,
3273
+ "eval_loss": 0.008570068515837193,
3274
+ "eval_runtime": 10.0111,
3275
+ "eval_samples_per_second": 4.994,
3276
+ "eval_steps_per_second": 1.299,
3277
+ "step": 380
3278
+ },
3279
+ {
3280
+ "epoch": 4.404624277456647,
3281
+ "grad_norm": 0.01620578207075596,
3282
+ "learning_rate": 3.903697249999289e-06,
3283
+ "loss": 0.0031,
3284
+ "step": 381
3285
+ },
3286
+ {
3287
+ "epoch": 4.416184971098266,
3288
+ "grad_norm": 0.01429419033229351,
3289
+ "learning_rate": 3.7479896625674027e-06,
3290
+ "loss": 0.0026,
3291
+ "step": 382
3292
+ },
3293
+ {
3294
+ "epoch": 4.427745664739884,
3295
+ "grad_norm": 0.015918832272291183,
3296
+ "learning_rate": 3.595330012545445e-06,
3297
+ "loss": 0.0026,
3298
+ "step": 383
3299
+ },
3300
+ {
3301
+ "epoch": 4.4393063583815024,
3302
+ "grad_norm": 0.019388854503631592,
3303
+ "learning_rate": 3.445728359973094e-06,
3304
+ "loss": 0.0029,
3305
+ "step": 384
3306
+ },
3307
+ {
3308
+ "epoch": 4.4508670520231215,
3309
+ "grad_norm": 0.012549116276204586,
3310
+ "learning_rate": 3.299194563372604e-06,
3311
+ "loss": 0.0022,
3312
+ "step": 385
3313
+ },
3314
+ {
3315
+ "epoch": 4.4508670520231215,
3316
+ "eval_loss": 0.008573681116104126,
3317
+ "eval_runtime": 10.0229,
3318
+ "eval_samples_per_second": 4.989,
3319
+ "eval_steps_per_second": 1.297,
3320
+ "step": 385
3321
+ },
3322
+ {
3323
+ "epoch": 4.46242774566474,
3324
+ "grad_norm": 0.01509170513600111,
3325
+ "learning_rate": 3.1557382790991687e-06,
3326
+ "loss": 0.0026,
3327
+ "step": 386
3328
+ },
3329
+ {
3330
+ "epoch": 4.473988439306359,
3331
+ "grad_norm": 0.014067728072404861,
3332
+ "learning_rate": 3.0153689607045845e-06,
3333
+ "loss": 0.0025,
3334
+ "step": 387
3335
+ },
3336
+ {
3337
+ "epoch": 4.485549132947977,
3338
+ "grad_norm": 0.028946029022336006,
3339
+ "learning_rate": 2.878095858314278e-06,
3340
+ "loss": 0.0027,
3341
+ "step": 388
3342
+ },
3343
+ {
3344
+ "epoch": 4.497109826589595,
3345
+ "grad_norm": 0.01480345893651247,
3346
+ "learning_rate": 2.743928018017744e-06,
3347
+ "loss": 0.0025,
3348
+ "step": 389
3349
+ },
3350
+ {
3351
+ "epoch": 4.508670520231214,
3352
+ "grad_norm": 0.02504677325487137,
3353
+ "learning_rate": 2.6128742812723704e-06,
3354
+ "loss": 0.0028,
3355
+ "step": 390
3356
+ },
3357
+ {
3358
+ "epoch": 4.508670520231214,
3359
+ "eval_loss": 0.008553516119718552,
3360
+ "eval_runtime": 10.0039,
3361
+ "eval_samples_per_second": 4.998,
3362
+ "eval_steps_per_second": 1.299,
3363
+ "step": 390
3364
+ },
3365
+ {
3366
+ "epoch": 4.520231213872832,
3367
+ "grad_norm": 0.016089266166090965,
3368
+ "learning_rate": 2.4849432843208785e-06,
3369
+ "loss": 0.0033,
3370
+ "step": 391
3371
+ },
3372
+ {
3373
+ "epoch": 4.531791907514451,
3374
+ "grad_norm": 0.015426091849803925,
3375
+ "learning_rate": 2.3601434576221546e-06,
3376
+ "loss": 0.0029,
3377
+ "step": 392
3378
+ },
3379
+ {
3380
+ "epoch": 4.543352601156069,
3381
+ "grad_norm": 0.017408043146133423,
3382
+ "learning_rate": 2.238483025295707e-06,
3383
+ "loss": 0.0031,
3384
+ "step": 393
3385
+ },
3386
+ {
3387
+ "epoch": 4.554913294797688,
3388
+ "grad_norm": 0.017079446464776993,
3389
+ "learning_rate": 2.1199700045797077e-06,
3390
+ "loss": 0.0027,
3391
+ "step": 394
3392
+ },
3393
+ {
3394
+ "epoch": 4.566473988439307,
3395
+ "grad_norm": 0.016879020258784294,
3396
+ "learning_rate": 2.0046122053026694e-06,
3397
+ "loss": 0.0028,
3398
+ "step": 395
3399
+ },
3400
+ {
3401
+ "epoch": 4.566473988439307,
3402
+ "eval_loss": 0.008501513861119747,
3403
+ "eval_runtime": 10.036,
3404
+ "eval_samples_per_second": 4.982,
3405
+ "eval_steps_per_second": 1.295,
3406
+ "step": 395
3407
+ },
3408
+ {
3409
+ "epoch": 4.578034682080925,
3410
+ "grad_norm": 0.030611367896199226,
3411
+ "learning_rate": 1.8924172293688147e-06,
3412
+ "loss": 0.0032,
3413
+ "step": 396
3414
+ },
3415
+ {
3416
+ "epoch": 4.589595375722544,
3417
+ "grad_norm": 0.017865322530269623,
3418
+ "learning_rate": 1.7833924702570725e-06,
3419
+ "loss": 0.0035,
3420
+ "step": 397
3421
+ },
3422
+ {
3423
+ "epoch": 4.601156069364162,
3424
+ "grad_norm": 0.014931568875908852,
3425
+ "learning_rate": 1.6775451125338959e-06,
3426
+ "loss": 0.0025,
3427
+ "step": 398
3428
+ },
3429
+ {
3430
+ "epoch": 4.61271676300578,
3431
+ "grad_norm": 0.015031742863357067,
3432
+ "learning_rate": 1.5748821313798124e-06,
3433
+ "loss": 0.0024,
3434
+ "step": 399
3435
+ },
3436
+ {
3437
+ "epoch": 4.624277456647399,
3438
+ "grad_norm": 0.017130030319094658,
3439
+ "learning_rate": 1.4754102921297364e-06,
3440
+ "loss": 0.0031,
3441
+ "step": 400
3442
+ },
3443
+ {
3444
+ "epoch": 4.624277456647399,
3445
+ "eval_loss": 0.008478561416268349,
3446
+ "eval_runtime": 10.0323,
3447
+ "eval_samples_per_second": 4.984,
3448
+ "eval_steps_per_second": 1.296,
3449
+ "step": 400
3450
+ },
3451
+ {
3452
+ "epoch": 4.635838150289017,
3453
+ "grad_norm": 0.014694861136376858,
3454
+ "learning_rate": 1.3791361498271705e-06,
3455
+ "loss": 0.0024,
3456
+ "step": 401
3457
+ },
3458
+ {
3459
+ "epoch": 4.6473988439306355,
3460
+ "grad_norm": 0.013526085764169693,
3461
+ "learning_rate": 1.2860660487922616e-06,
3462
+ "loss": 0.0023,
3463
+ "step": 402
3464
+ },
3465
+ {
3466
+ "epoch": 4.658959537572255,
3467
+ "grad_norm": 0.04836466535925865,
3468
+ "learning_rate": 1.196206122203647e-06,
3469
+ "loss": 0.0024,
3470
+ "step": 403
3471
+ },
3472
+ {
3473
+ "epoch": 4.670520231213873,
3474
+ "grad_norm": 0.016095180064439774,
3475
+ "learning_rate": 1.1095622916943494e-06,
3476
+ "loss": 0.0033,
3477
+ "step": 404
3478
+ },
3479
+ {
3480
+ "epoch": 4.682080924855491,
3481
+ "grad_norm": 0.019678572192788124,
3482
+ "learning_rate": 1.0261402669615505e-06,
3483
+ "loss": 0.0038,
3484
+ "step": 405
3485
+ },
3486
+ {
3487
+ "epoch": 4.682080924855491,
3488
+ "eval_loss": 0.00843281950801611,
3489
+ "eval_runtime": 10.0323,
3490
+ "eval_samples_per_second": 4.984,
3491
+ "eval_steps_per_second": 1.296,
3492
+ "step": 405
3493
+ },
3494
+ {
3495
+ "epoch": 4.69364161849711,
3496
+ "grad_norm": 0.013817240484058857,
3497
+ "learning_rate": 9.459455453902866e-07,
3498
+ "loss": 0.0024,
3499
+ "step": 406
3500
+ },
3501
+ {
3502
+ "epoch": 4.705202312138728,
3503
+ "grad_norm": 0.0165092833340168,
3504
+ "learning_rate": 8.68983411691221e-07,
3505
+ "loss": 0.0029,
3506
+ "step": 407
3507
+ },
3508
+ {
3509
+ "epoch": 4.716763005780347,
3510
+ "grad_norm": 0.016268854960799217,
3511
+ "learning_rate": 7.952589375523567e-07,
3512
+ "loss": 0.0028,
3513
+ "step": 408
3514
+ },
3515
+ {
3516
+ "epoch": 4.728323699421965,
3517
+ "grad_norm": 0.013906327076256275,
3518
+ "learning_rate": 7.247769813048644e-07,
3519
+ "loss": 0.0025,
3520
+ "step": 409
3521
+ },
3522
+ {
3523
+ "epoch": 4.7398843930635834,
3524
+ "grad_norm": 0.0136026069521904,
3525
+ "learning_rate": 6.57542187602872e-07,
3526
+ "loss": 0.0024,
3527
+ "step": 410
3528
+ },
3529
+ {
3530
+ "epoch": 4.7398843930635834,
3531
+ "eval_loss": 0.00842086412012577,
3532
+ "eval_runtime": 10.0656,
3533
+ "eval_samples_per_second": 4.967,
3534
+ "eval_steps_per_second": 1.292,
3535
+ "step": 410
3536
+ },
3537
+ {
3538
+ "epoch": 4.7514450867052025,
3539
+ "grad_norm": 0.022275064140558243,
3540
+ "learning_rate": 5.935589871174208e-07,
3541
+ "loss": 0.0028,
3542
+ "step": 411
3543
+ },
3544
+ {
3545
+ "epoch": 4.763005780346821,
3546
+ "grad_norm": 0.016609348356723785,
3547
+ "learning_rate": 5.328315962444874e-07,
3548
+ "loss": 0.0029,
3549
+ "step": 412
3550
+ },
3551
+ {
3552
+ "epoch": 4.77456647398844,
3553
+ "grad_norm": 0.015365025959908962,
3554
+ "learning_rate": 4.753640168271456e-07,
3555
+ "loss": 0.0029,
3556
+ "step": 413
3557
+ },
3558
+ {
3559
+ "epoch": 4.786127167630058,
3560
+ "grad_norm": 0.014568125829100609,
3561
+ "learning_rate": 4.2116003589179887e-07,
3562
+ "loss": 0.0024,
3563
+ "step": 414
3564
+ },
3565
+ {
3566
+ "epoch": 4.797687861271676,
3567
+ "grad_norm": 0.014286377467215061,
3568
+ "learning_rate": 3.702232253986804e-07,
3569
+ "loss": 0.0024,
3570
+ "step": 415
3571
+ },
3572
+ {
3573
+ "epoch": 4.797687861271676,
3574
+ "eval_loss": 0.008439392782747746,
3575
+ "eval_runtime": 10.0373,
3576
+ "eval_samples_per_second": 4.981,
3577
+ "eval_steps_per_second": 1.295,
3578
+ "step": 415
3579
+ },
3580
+ {
3581
+ "epoch": 4.809248554913295,
3582
+ "grad_norm": 0.015557860024273396,
3583
+ "learning_rate": 3.2255694200643006e-07,
3584
+ "loss": 0.0027,
3585
+ "step": 416
3586
+ },
3587
+ {
3588
+ "epoch": 4.820809248554913,
3589
+ "grad_norm": 0.01427092682570219,
3590
+ "learning_rate": 2.78164326850916e-07,
3591
+ "loss": 0.0023,
3592
+ "step": 417
3593
+ },
3594
+ {
3595
+ "epoch": 4.832369942196532,
3596
+ "grad_norm": 0.01711309514939785,
3597
+ "learning_rate": 2.3704830533821108e-07,
3598
+ "loss": 0.0031,
3599
+ "step": 418
3600
+ },
3601
+ {
3602
+ "epoch": 4.84393063583815,
3603
+ "grad_norm": 0.015366033650934696,
3604
+ "learning_rate": 1.9921158695184738e-07,
3605
+ "loss": 0.0026,
3606
+ "step": 419
3607
+ },
3608
+ {
3609
+ "epoch": 4.855491329479769,
3610
+ "grad_norm": 0.013661878183484077,
3611
+ "learning_rate": 1.6465666507425315e-07,
3612
+ "loss": 0.0024,
3613
+ "step": 420
3614
+ },
3615
+ {
3616
+ "epoch": 4.855491329479769,
3617
+ "eval_loss": 0.008424060419201851,
3618
+ "eval_runtime": 10.0452,
3619
+ "eval_samples_per_second": 4.978,
3620
+ "eval_steps_per_second": 1.294,
3621
+ "step": 420
3622
+ },
3623
+ {
3624
+ "epoch": 4.867052023121388,
3625
+ "grad_norm": 0.01569373905658722,
3626
+ "learning_rate": 1.333858168224178e-07,
3627
+ "loss": 0.0027,
3628
+ "step": 421
3629
+ },
3630
+ {
3631
+ "epoch": 4.878612716763006,
3632
+ "grad_norm": 0.02022898755967617,
3633
+ "learning_rate": 1.0540110289786742e-07,
3634
+ "loss": 0.0032,
3635
+ "step": 422
3636
+ },
3637
+ {
3638
+ "epoch": 4.890173410404624,
3639
+ "grad_norm": 0.013800419867038727,
3640
+ "learning_rate": 8.07043674508623e-08,
3641
+ "loss": 0.0024,
3642
+ "step": 423
3643
+ },
3644
+ {
3645
+ "epoch": 4.901734104046243,
3646
+ "grad_norm": 0.017323607578873634,
3647
+ "learning_rate": 5.929723795884967e-08,
3648
+ "loss": 0.0029,
3649
+ "step": 424
3650
+ },
3651
+ {
3652
+ "epoch": 4.913294797687861,
3653
+ "grad_norm": 0.014345725998282433,
3654
+ "learning_rate": 4.1181125119221787e-08,
3655
+ "loss": 0.0026,
3656
+ "step": 425
3657
+ },
3658
+ {
3659
+ "epoch": 4.913294797687861,
3660
+ "eval_loss": 0.008420780301094055,
3661
+ "eval_runtime": 10.0258,
3662
+ "eval_samples_per_second": 4.987,
3663
+ "eval_steps_per_second": 1.297,
3664
+ "step": 425
3665
+ },
3666
+ {
3667
+ "epoch": 4.924855491329479,
3668
+ "grad_norm": 0.014356693252921104,
3669
+ "learning_rate": 2.6357222756384636e-08,
3670
+ "loss": 0.0025,
3671
+ "step": 426
3672
+ },
3673
+ {
3674
+ "epoch": 4.936416184971098,
3675
+ "grad_norm": 0.014968520030379295,
3676
+ "learning_rate": 1.482650774303207e-08,
3677
+ "loss": 0.0028,
3678
+ "step": 427
3679
+ },
3680
+ {
3681
+ "epoch": 4.9479768786127165,
3682
+ "grad_norm": 0.02624007686972618,
3683
+ "learning_rate": 6.589739935819461e-09,
3684
+ "loss": 0.0033,
3685
+ "step": 428
3686
+ },
3687
+ {
3688
+ "epoch": 4.959537572254336,
3689
+ "grad_norm": 0.016497237607836723,
3690
+ "learning_rate": 1.6474621252704493e-09,
3691
+ "loss": 0.0031,
3692
+ "step": 429
3693
+ },
3694
+ {
3695
+ "epoch": 4.971098265895954,
3696
+ "grad_norm": 0.01508865226060152,
3697
+ "learning_rate": 0.0,
3698
+ "loss": 0.0029,
3699
+ "step": 430
3700
+ },
3701
+ {
3702
+ "epoch": 4.971098265895954,
3703
+ "eval_loss": 0.008429310284554958,
3704
+ "eval_runtime": 10.0331,
3705
+ "eval_samples_per_second": 4.983,
3706
+ "eval_steps_per_second": 1.296,
3707
+ "step": 430
3708
+ },
3709
+ {
3710
+ "epoch": 4.971098265895954,
3711
+ "step": 430,
3712
+ "total_flos": 1.0207257247425331e+18,
3713
+ "train_loss": 0.0087554031284526,
3714
+ "train_runtime": 8412.5192,
3715
+ "train_samples_per_second": 1.645,
3716
+ "train_steps_per_second": 0.051
3717
+ }
3718
+ ],
3719
+ "logging_steps": 1,
3720
+ "max_steps": 430,
3721
+ "num_input_tokens_seen": 0,
3722
+ "num_train_epochs": 5,
3723
+ "save_steps": 50,
3724
+ "stateful_callbacks": {
3725
+ "TrainerControl": {
3726
+ "args": {
3727
+ "should_epoch_stop": false,
3728
+ "should_evaluate": false,
3729
+ "should_log": false,
3730
+ "should_save": true,
3731
+ "should_training_stop": true
3732
+ },
3733
+ "attributes": {}
3734
+ }
3735
+ },
3736
+ "total_flos": 1.0207257247425331e+18,
3737
+ "train_batch_size": 4,
3738
+ "trial_name": null,
3739
+ "trial_params": null
3740
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72886bedd016d1f99814720df6614c5543c0ad45208bb8f78e98bee78c53147d
3
+ size 5432
training_eval_loss.png ADDED
training_loss.png ADDED