Hugging Face's logo

taopanda
/
62762fca-efdc-4892-951a-bd14116e3f88

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
FatCat87 commited on
Commit
41aeac0
·
verified ·
1 Parent(s): 6f35817

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. checkpoint-501/README.md +202 -0
  2. checkpoint-501/adapter_config.json +34 -0
  3. checkpoint-501/adapter_model.safetensors +3 -0
  4. checkpoint-501/added_tokens.json +25 -0
  5. checkpoint-501/merges.txt +0 -0
  6. checkpoint-501/optimizer.pt +3 -0
  7. checkpoint-501/rng_state_0.pth +3 -0
  8. checkpoint-501/rng_state_1.pth +3 -0
  9. checkpoint-501/rng_state_2.pth +3 -0
  10. checkpoint-501/rng_state_3.pth +3 -0
  11. checkpoint-501/scheduler.pt +3 -0
  12. checkpoint-501/special_tokens_map.json +31 -0
  13. checkpoint-501/tokenizer.json +0 -0
  14. checkpoint-501/tokenizer_config.json +215 -0
  15. checkpoint-501/trainer_state.json +3572 -0
  16. checkpoint-501/training_args.bin +3 -0
  17. checkpoint-501/vocab.json +0 -0
  18. merged/added_tokens.json +25 -0
  19. merged/config.json +29 -0
  20. merged/generation_config.json +9 -0
  21. merged/merges.txt +0 -0
  22. merged/pytorch_model-00001-of-00004.bin +3 -0
  23. merged/pytorch_model-00002-of-00004.bin +3 -0
  24. merged/pytorch_model-00003-of-00004.bin +3 -0
  25. merged/pytorch_model-00004-of-00004.bin +3 -0
  26. merged/pytorch_model.bin.index.json +346 -0
  27. merged/special_tokens_map.json +31 -0
  28. merged/tokenizer.json +0 -0
  29. merged/tokenizer_config.json +215 -0
  30. merged/vocab.json +0 -0
checkpoint-501/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: unsloth/Qwen2.5-Coder-7B
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-501/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-501/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f6b3f409551c56a609b2df62476212ab2ed5a5beb3b16df0a722af770c6189
3
+ size 323014168
checkpoint-501/added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|PAD_TOKEN|>": 151665,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
checkpoint-501/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-501/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3023a35593b13f15169b37bab0a21784ee5355449dffef8fe70a04dda2d554a4
3
+ size 162231028
checkpoint-501/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b159170d67e489984d54807a0ae024eb597fe7e213b9e7e9f888c6a9ce075ff
3
+ size 14960
checkpoint-501/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c0548936aac7ebc0cb4824f272b56aa0334d75455d0d02d70b3076d210be11
3
+ size 14960
checkpoint-501/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af6f05cc838864fc931e2ffa9f7e650f0d25b7c65876bb2bc6f29793f23f8f06
3
+ size 14960
checkpoint-501/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b060a804dd7c0054832c2aa6bfac4982c1a632298436b3de5d3d9f0f4525ab0
3
+ size 14960
checkpoint-501/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae2296ce539479e44f95a086379a88782e7ae1f041903ce8dfc0ab8b6933c29
3
+ size 1064
checkpoint-501/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|PAD_TOKEN|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-501/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-501/tokenizer_config.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|PAD_TOKEN|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
+ ],
205
+ "bos_token": null,
206
+ "clean_up_tokenization_spaces": false,
207
+ "eos_token": "<|endoftext|>",
208
+ "errors": "replace",
209
+ "model_max_length": 131072,
210
+ "pad_token": "<|PAD_TOKEN|>",
211
+ "padding_side": "left",
212
+ "split_special_tokens": false,
213
+ "tokenizer_class": "Qwen2Tokenizer",
214
+ "unk_token": null
215
+ }
checkpoint-501/trainer_state.json ADDED
@@ -0,0 +1,3572 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9985052316890882,
5
+ "eval_steps": 167,
6
+ "global_step": 501,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.001993024414549078,
13
+ "grad_norm": 0.05287065729498863,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.3875,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.001993024414549078,
20
+ "eval_loss": 2.5549981594085693,
21
+ "eval_runtime": 41.2289,
22
+ "eval_samples_per_second": 20.495,
23
+ "eval_steps_per_second": 2.571,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.003986048829098156,
28
+ "grad_norm": 0.06495615094900131,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.6361,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.005979073243647235,
35
+ "grad_norm": 0.060323264449834824,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.6314,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.007972097658196313,
42
+ "grad_norm": 0.06755875051021576,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.6248,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.009965122072745391,
49
+ "grad_norm": 0.07026221603155136,
50
+ "learning_rate": 0.0001,
51
+ "loss": 2.6,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.01195814648729447,
56
+ "grad_norm": 0.058893654495477676,
57
+ "learning_rate": 0.00012,
58
+ "loss": 2.4617,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.013951170901843548,
63
+ "grad_norm": 0.07267533242702484,
64
+ "learning_rate": 0.00014,
65
+ "loss": 2.6848,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.015944195316392625,
70
+ "grad_norm": 0.07501880824565887,
71
+ "learning_rate": 0.00016,
72
+ "loss": 2.4478,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.017937219730941704,
77
+ "grad_norm": 0.07286067306995392,
78
+ "learning_rate": 0.00018,
79
+ "loss": 2.5294,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.019930244145490782,
84
+ "grad_norm": 0.07428107410669327,
85
+ "learning_rate": 0.0002,
86
+ "loss": 2.4104,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.02192326856003986,
91
+ "grad_norm": 0.0881316289305687,
92
+ "learning_rate": 0.00019999795305919378,
93
+ "loss": 2.5427,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.02391629297458894,
98
+ "grad_norm": 0.09794878959655762,
99
+ "learning_rate": 0.0001999918123205744,
100
+ "loss": 2.449,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.025909317389138018,
105
+ "grad_norm": 0.12311644852161407,
106
+ "learning_rate": 0.00019998157803553638,
107
+ "loss": 2.4273,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.027902341803687097,
112
+ "grad_norm": 0.11273285746574402,
113
+ "learning_rate": 0.00019996725062305934,
114
+ "loss": 2.4291,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.029895366218236172,
119
+ "grad_norm": 0.10147881507873535,
120
+ "learning_rate": 0.00019994883066969053,
121
+ "loss": 2.3181,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.03188839063278525,
126
+ "grad_norm": 0.1054357960820198,
127
+ "learning_rate": 0.00019992631892952107,
128
+ "loss": 2.5176,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.03388141504733433,
133
+ "grad_norm": 0.12467704713344574,
134
+ "learning_rate": 0.0001998997163241549,
135
+ "loss": 2.4257,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.03587443946188341,
140
+ "grad_norm": 0.15358665585517883,
141
+ "learning_rate": 0.00019986902394267118,
142
+ "loss": 2.4519,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.037867463876432486,
147
+ "grad_norm": 0.09839481860399246,
148
+ "learning_rate": 0.00019983424304157973,
149
+ "loss": 2.4609,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.039860488290981565,
154
+ "grad_norm": 0.11362826824188232,
155
+ "learning_rate": 0.00019979537504476944,
156
+ "loss": 2.4418,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.04185351270553064,
161
+ "grad_norm": 0.08789506554603577,
162
+ "learning_rate": 0.00019975242154345008,
163
+ "loss": 2.3725,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.04384653712007972,
168
+ "grad_norm": 0.08682800084352493,
169
+ "learning_rate": 0.00019970538429608714,
170
+ "loss": 2.3597,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.0458395615346288,
175
+ "grad_norm": 0.0822245180606842,
176
+ "learning_rate": 0.00019965426522832984,
177
+ "loss": 2.4181,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.04783258594917788,
182
+ "grad_norm": 0.08259279280900955,
183
+ "learning_rate": 0.0001995990664329323,
184
+ "loss": 2.3302,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.04982561036372696,
189
+ "grad_norm": 0.0976216048002243,
190
+ "learning_rate": 0.00019953979016966788,
191
+ "loss": 2.3518,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.051818634778276036,
196
+ "grad_norm": 0.07256148010492325,
197
+ "learning_rate": 0.0001994764388652366,
198
+ "loss": 2.2947,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.053811659192825115,
203
+ "grad_norm": 0.08327591419219971,
204
+ "learning_rate": 0.00019940901511316582,
205
+ "loss": 2.3938,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.05580468360737419,
210
+ "grad_norm": 0.07075290381908417,
211
+ "learning_rate": 0.0001993375216737042,
212
+ "loss": 2.3935,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.05779770802192327,
217
+ "grad_norm": 0.08164233714342117,
218
+ "learning_rate": 0.00019926196147370849,
219
+ "loss": 2.3321,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.059790732436472344,
224
+ "grad_norm": 0.07011182606220245,
225
+ "learning_rate": 0.0001991823376065238,
226
+ "loss": 2.5099,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.06178375685102142,
231
+ "grad_norm": 0.07080947607755661,
232
+ "learning_rate": 0.00019909865333185702,
233
+ "loss": 2.3739,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.0637767812655705,
238
+ "grad_norm": 0.07467987388372421,
239
+ "learning_rate": 0.00019901091207564324,
240
+ "loss": 2.468,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.06576980568011959,
245
+ "grad_norm": 0.07430382817983627,
246
+ "learning_rate": 0.00019891911742990565,
247
+ "loss": 2.514,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.06776283009466866,
252
+ "grad_norm": 0.09713613986968994,
253
+ "learning_rate": 0.00019882327315260838,
254
+ "loss": 2.5276,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.06975585450921774,
259
+ "grad_norm": 0.06677185744047165,
260
+ "learning_rate": 0.00019872338316750265,
261
+ "loss": 2.5217,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.07174887892376682,
266
+ "grad_norm": 0.07167352735996246,
267
+ "learning_rate": 0.0001986194515639662,
268
+ "loss": 2.3537,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.0737419033383159,
273
+ "grad_norm": 0.0652233213186264,
274
+ "learning_rate": 0.00019851148259683585,
275
+ "loss": 2.2171,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.07573492775286497,
280
+ "grad_norm": 0.09544400870800018,
281
+ "learning_rate": 0.0001983994806862333,
282
+ "loss": 2.4351,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.07772795216741404,
287
+ "grad_norm": 0.0639595314860344,
288
+ "learning_rate": 0.00019828345041738413,
289
+ "loss": 2.4514,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.07972097658196313,
294
+ "grad_norm": 0.08084385842084885,
295
+ "learning_rate": 0.00019816339654043022,
296
+ "loss": 2.3315,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.0817140009965122,
301
+ "grad_norm": 0.0713881179690361,
302
+ "learning_rate": 0.0001980393239702351,
303
+ "loss": 2.3641,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.08370702541106129,
308
+ "grad_norm": 0.07158852368593216,
309
+ "learning_rate": 0.00019791123778618305,
310
+ "loss": 2.3927,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.08570004982561036,
315
+ "grad_norm": 0.07691681385040283,
316
+ "learning_rate": 0.00019777914323197064,
317
+ "loss": 2.3735,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.08769307424015944,
322
+ "grad_norm": 0.09183619916439056,
323
+ "learning_rate": 0.00019764304571539266,
324
+ "loss": 2.52,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.08968609865470852,
329
+ "grad_norm": 0.07233479619026184,
330
+ "learning_rate": 0.00019750295080812023,
331
+ "loss": 2.3307,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.0916791230692576,
336
+ "grad_norm": 0.08435732126235962,
337
+ "learning_rate": 0.00019735886424547306,
338
+ "loss": 2.3688,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.09367214748380667,
343
+ "grad_norm": 0.07783546298742294,
344
+ "learning_rate": 0.0001972107919261844,
345
+ "loss": 2.4481,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.09566517189835576,
350
+ "grad_norm": 0.07377699762582779,
351
+ "learning_rate": 0.00019705873991215974,
352
+ "loss": 2.4,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.09765819631290483,
357
+ "grad_norm": 0.07814358919858932,
358
+ "learning_rate": 0.00019690271442822848,
359
+ "loss": 2.5179,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.09965122072745392,
364
+ "grad_norm": 0.0662505030632019,
365
+ "learning_rate": 0.0001967427218618893,
366
+ "loss": 2.3914,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.10164424514200299,
371
+ "grad_norm": 0.07971400022506714,
372
+ "learning_rate": 0.00019657876876304835,
373
+ "loss": 2.3238,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.10363726955655207,
378
+ "grad_norm": 0.06901857256889343,
379
+ "learning_rate": 0.00019641086184375145,
380
+ "loss": 2.3452,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.10563029397110114,
385
+ "grad_norm": 0.07353848963975906,
386
+ "learning_rate": 0.00019623900797790912,
387
+ "loss": 2.3548,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.10762331838565023,
392
+ "grad_norm": 0.08996592462062836,
393
+ "learning_rate": 0.00019606321420101512,
394
+ "loss": 2.4352,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.1096163428001993,
399
+ "grad_norm": 0.08336281776428223,
400
+ "learning_rate": 0.0001958834877098586,
401
+ "loss": 2.3223,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.11160936721474839,
406
+ "grad_norm": 0.08819875121116638,
407
+ "learning_rate": 0.0001956998358622293,
408
+ "loss": 2.5107,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.11360239162929746,
413
+ "grad_norm": 0.07561585307121277,
414
+ "learning_rate": 0.00019551226617661648,
415
+ "loss": 2.413,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.11559541604384654,
420
+ "grad_norm": 0.07585092633962631,
421
+ "learning_rate": 0.00019532078633190095,
422
+ "loss": 2.3788,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.11758844045839562,
427
+ "grad_norm": 0.06750821322202682,
428
+ "learning_rate": 0.00019512540416704094,
429
+ "loss": 2.4499,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.11958146487294469,
434
+ "grad_norm": 0.0755094513297081,
435
+ "learning_rate": 0.00019492612768075092,
436
+ "loss": 2.421,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.12157448928749377,
441
+ "grad_norm": 0.06977269798517227,
442
+ "learning_rate": 0.00019472296503117437,
443
+ "loss": 2.2985,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.12356751370204284,
448
+ "grad_norm": 0.07430297136306763,
449
+ "learning_rate": 0.00019451592453554955,
450
+ "loss": 2.4395,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.12556053811659193,
455
+ "grad_norm": 0.07390575110912323,
456
+ "learning_rate": 0.00019430501466986933,
457
+ "loss": 2.3886,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.127553562531141,
462
+ "grad_norm": 0.0816730186343193,
463
+ "learning_rate": 0.0001940902440685339,
464
+ "loss": 2.4348,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.12954658694569007,
469
+ "grad_norm": 0.08618990331888199,
470
+ "learning_rate": 0.0001938716215239974,
471
+ "loss": 2.5626,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.13153961136023917,
476
+ "grad_norm": 0.07344585657119751,
477
+ "learning_rate": 0.00019364915598640793,
478
+ "loss": 2.3255,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.13353263577478824,
483
+ "grad_norm": 0.07738056033849716,
484
+ "learning_rate": 0.00019342285656324135,
485
+ "loss": 2.4293,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.13552566018933732,
490
+ "grad_norm": 0.07774533331394196,
491
+ "learning_rate": 0.00019319273251892805,
492
+ "loss": 2.4104,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.1375186846038864,
497
+ "grad_norm": 0.07248608767986298,
498
+ "learning_rate": 0.000192958793274474,
499
+ "loss": 2.377,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.1395117090184355,
504
+ "grad_norm": 0.08310771733522415,
505
+ "learning_rate": 0.00019272104840707487,
506
+ "loss": 2.4057,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.14150473343298456,
511
+ "grad_norm": 0.07131807506084442,
512
+ "learning_rate": 0.0001924795076497241,
513
+ "loss": 2.3632,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.14349775784753363,
518
+ "grad_norm": 0.07065235078334808,
519
+ "learning_rate": 0.0001922341808908144,
520
+ "loss": 2.3864,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.1454907822620827,
525
+ "grad_norm": 0.08351413160562515,
526
+ "learning_rate": 0.00019198507817373272,
527
+ "loss": 2.3546,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.1474838066766318,
532
+ "grad_norm": 0.07136453688144684,
533
+ "learning_rate": 0.00019173220969644948,
534
+ "loss": 2.4945,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.14947683109118087,
539
+ "grad_norm": 0.07159949839115143,
540
+ "learning_rate": 0.00019147558581110078,
541
+ "loss": 2.292,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.15146985550572994,
546
+ "grad_norm": 0.09557915478944778,
547
+ "learning_rate": 0.0001912152170235646,
548
+ "loss": 2.3603,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.15346287992027902,
553
+ "grad_norm": 0.07749924063682556,
554
+ "learning_rate": 0.0001909511139930309,
555
+ "loss": 2.411,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.1554559043348281,
560
+ "grad_norm": 0.08089883625507355,
561
+ "learning_rate": 0.00019068328753156513,
562
+ "loss": 2.4272,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.1574489287493772,
567
+ "grad_norm": 0.08237191289663315,
568
+ "learning_rate": 0.0001904117486036655,
569
+ "loss": 2.4792,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.15944195316392626,
574
+ "grad_norm": 0.07698153704404831,
575
+ "learning_rate": 0.00019013650832581423,
576
+ "loss": 2.3268,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.16143497757847533,
581
+ "grad_norm": 0.08599510043859482,
582
+ "learning_rate": 0.00018985757796602252,
583
+ "loss": 2.3539,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.1634280019930244,
588
+ "grad_norm": 0.06759509444236755,
589
+ "learning_rate": 0.00018957496894336898,
590
+ "loss": 2.4933,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.1654210264075735,
595
+ "grad_norm": 0.07102535665035248,
596
+ "learning_rate": 0.0001892886928275325,
597
+ "loss": 2.2701,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.16741405082212257,
602
+ "grad_norm": 0.08493571728467941,
603
+ "learning_rate": 0.00018899876133831835,
604
+ "loss": 2.4632,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.16940707523667164,
609
+ "grad_norm": 0.08319897204637527,
610
+ "learning_rate": 0.0001887051863451784,
611
+ "loss": 2.4856,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.17140009965122072,
616
+ "grad_norm": 0.06596291065216064,
617
+ "learning_rate": 0.00018840797986672538,
618
+ "loss": 2.3721,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.17339312406576982,
623
+ "grad_norm": 0.07499933987855911,
624
+ "learning_rate": 0.0001881071540702406,
625
+ "loss": 2.4339,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.1753861484803189,
630
+ "grad_norm": 0.07612438499927521,
631
+ "learning_rate": 0.00018780272127117607,
632
+ "loss": 2.3893,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.17737917289486796,
637
+ "grad_norm": 0.07736552506685257,
638
+ "learning_rate": 0.00018749469393265016,
639
+ "loss": 2.3834,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.17937219730941703,
644
+ "grad_norm": 0.08996405452489853,
645
+ "learning_rate": 0.00018718308466493744,
646
+ "loss": 2.4032,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.18136522172396613,
651
+ "grad_norm": 0.0919409915804863,
652
+ "learning_rate": 0.0001868679062249524,
653
+ "loss": 2.3861,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.1833582461385152,
658
+ "grad_norm": 0.07732091844081879,
659
+ "learning_rate": 0.00018654917151572729,
660
+ "loss": 2.3722,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.18535127055306427,
665
+ "grad_norm": 0.0725676640868187,
666
+ "learning_rate": 0.00018622689358588373,
667
+ "loss": 2.3614,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.18734429496761335,
672
+ "grad_norm": 0.06600993126630783,
673
+ "learning_rate": 0.00018590108562909863,
674
+ "loss": 2.4025,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.18933731938216244,
679
+ "grad_norm": 0.07493855804204941,
680
+ "learning_rate": 0.00018557176098356405,
681
+ "loss": 2.1991,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.19133034379671152,
686
+ "grad_norm": 0.07322800159454346,
687
+ "learning_rate": 0.0001852389331314411,
688
+ "loss": 2.4095,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.1933233682112606,
693
+ "grad_norm": 0.07966592907905579,
694
+ "learning_rate": 0.00018490261569830798,
695
+ "loss": 2.3731,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.19531639262580966,
700
+ "grad_norm": 0.07612770795822144,
701
+ "learning_rate": 0.0001845628224526023,
702
+ "loss": 2.3436,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.19730941704035873,
707
+ "grad_norm": 0.09146429598331451,
708
+ "learning_rate": 0.0001842195673050572,
709
+ "loss": 2.3442,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.19930244145490783,
714
+ "grad_norm": 0.08144223690032959,
715
+ "learning_rate": 0.00018387286430813208,
716
+ "loss": 2.3233,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.2012954658694569,
721
+ "grad_norm": 0.0802980437874794,
722
+ "learning_rate": 0.00018352272765543722,
723
+ "loss": 2.3668,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.20328849028400597,
728
+ "grad_norm": 0.07687564939260483,
729
+ "learning_rate": 0.0001831691716811526,
730
+ "loss": 2.558,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.20528151469855505,
735
+ "grad_norm": 0.0707612857222557,
736
+ "learning_rate": 0.00018281221085944126,
737
+ "loss": 2.4082,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.20727453911310414,
742
+ "grad_norm": 0.07944275438785553,
743
+ "learning_rate": 0.0001824518598038567,
744
+ "loss": 2.4548,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.20926756352765322,
749
+ "grad_norm": 0.07518940418958664,
750
+ "learning_rate": 0.00018208813326674444,
751
+ "loss": 2.347,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.2112605879422023,
756
+ "grad_norm": 0.0737578421831131,
757
+ "learning_rate": 0.00018172104613863835,
758
+ "loss": 2.2228,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.21325361235675136,
763
+ "grad_norm": 0.08424503356218338,
764
+ "learning_rate": 0.00018135061344765088,
765
+ "loss": 2.4694,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.21524663677130046,
770
+ "grad_norm": 0.09100914746522903,
771
+ "learning_rate": 0.0001809768503588578,
772
+ "loss": 2.5781,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.21723966118584953,
777
+ "grad_norm": 0.07634501904249191,
778
+ "learning_rate": 0.00018059977217367755,
779
+ "loss": 2.4596,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.2192326856003986,
784
+ "grad_norm": 0.0686226487159729,
785
+ "learning_rate": 0.00018021939432924454,
786
+ "loss": 2.4031,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.22122571001494767,
791
+ "grad_norm": 0.06668750196695328,
792
+ "learning_rate": 0.00017983573239777748,
793
+ "loss": 2.4276,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.22321873442949677,
798
+ "grad_norm": 0.06847918778657913,
799
+ "learning_rate": 0.00017944880208594155,
800
+ "loss": 2.2508,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.22521175884404585,
805
+ "grad_norm": 0.0749887079000473,
806
+ "learning_rate": 0.0001790586192342057,
807
+ "loss": 2.3678,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.22720478325859492,
812
+ "grad_norm": 0.07855971902608871,
813
+ "learning_rate": 0.00017866519981619394,
814
+ "loss": 2.3082,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.229197807673144,
819
+ "grad_norm": 0.060192834585905075,
820
+ "learning_rate": 0.00017826855993803147,
821
+ "loss": 2.4431,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.2311908320876931,
826
+ "grad_norm": 0.06574233621358871,
827
+ "learning_rate": 0.00017786871583768535,
828
+ "loss": 2.419,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.23318385650224216,
833
+ "grad_norm": 0.07050640881061554,
834
+ "learning_rate": 0.00017746568388429966,
835
+ "loss": 2.2912,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.23517688091679123,
840
+ "grad_norm": 0.08388429135084152,
841
+ "learning_rate": 0.00017705948057752545,
842
+ "loss": 2.486,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.2371699053313403,
847
+ "grad_norm": 0.08265074342489243,
848
+ "learning_rate": 0.00017665012254684524,
849
+ "loss": 2.4887,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.23916292974588937,
854
+ "grad_norm": 0.06995350867509842,
855
+ "learning_rate": 0.00017623762655089207,
856
+ "loss": 2.4096,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.24115595416043847,
861
+ "grad_norm": 0.09300334751605988,
862
+ "learning_rate": 0.0001758220094767638,
863
+ "loss": 2.4469,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.24314897857498755,
868
+ "grad_norm": 0.14214161038398743,
869
+ "learning_rate": 0.0001754032883393313,
870
+ "loss": 2.4855,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.24514200298953662,
875
+ "grad_norm": 0.08307930827140808,
876
+ "learning_rate": 0.0001749814802805423,
877
+ "loss": 2.3968,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.2471350274040857,
882
+ "grad_norm": 0.07516124099493027,
883
+ "learning_rate": 0.00017455660256871931,
884
+ "loss": 2.4828,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.2491280518186348,
889
+ "grad_norm": 0.08234971761703491,
890
+ "learning_rate": 0.00017412867259785286,
891
+ "loss": 2.4102,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.25112107623318386,
896
+ "grad_norm": 0.06870054453611374,
897
+ "learning_rate": 0.00017369770788688938,
898
+ "loss": 2.4244,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.25311410064773293,
903
+ "grad_norm": 0.06862769275903702,
904
+ "learning_rate": 0.00017326372607901386,
905
+ "loss": 2.406,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.255107125062282,
910
+ "grad_norm": 0.07357139885425568,
911
+ "learning_rate": 0.0001728267449409278,
912
+ "loss": 2.3246,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.2571001494768311,
917
+ "grad_norm": 0.06696347147226334,
918
+ "learning_rate": 0.0001723867823621216,
919
+ "loss": 2.2834,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.25909317389138015,
924
+ "grad_norm": 0.08405718207359314,
925
+ "learning_rate": 0.00017194385635414244,
926
+ "loss": 2.3598,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.2610861983059293,
931
+ "grad_norm": 0.07290710508823395,
932
+ "learning_rate": 0.00017149798504985665,
933
+ "loss": 2.3657,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.26307922272047835,
938
+ "grad_norm": 0.07178878784179688,
939
+ "learning_rate": 0.00017104918670270762,
940
+ "loss": 2.4459,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.2650722471350274,
945
+ "grad_norm": 0.08426004648208618,
946
+ "learning_rate": 0.00017059747968596836,
947
+ "loss": 2.4059,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.2670652715495765,
952
+ "grad_norm": 0.0784025564789772,
953
+ "learning_rate": 0.00017014288249198934,
954
+ "loss": 2.167,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.26905829596412556,
959
+ "grad_norm": 0.06741447001695633,
960
+ "learning_rate": 0.00016968541373144156,
961
+ "loss": 2.251,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.27105132037867463,
966
+ "grad_norm": 0.07658060640096664,
967
+ "learning_rate": 0.0001692250921325544,
968
+ "loss": 2.4971,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.2730443447932237,
973
+ "grad_norm": 0.07873057574033737,
974
+ "learning_rate": 0.0001687619365403492,
975
+ "loss": 2.2501,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.2750373692077728,
980
+ "grad_norm": 0.06821373850107193,
981
+ "learning_rate": 0.0001682959659158676,
982
+ "loss": 2.3857,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.27703039362232185,
987
+ "grad_norm": 0.0815286785364151,
988
+ "learning_rate": 0.0001678271993353953,
989
+ "loss": 2.4767,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.279023418036871,
994
+ "grad_norm": 0.07839839905500412,
995
+ "learning_rate": 0.00016735565598968114,
996
+ "loss": 2.3555,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.28101644245142005,
1001
+ "grad_norm": 0.08067015558481216,
1002
+ "learning_rate": 0.00016688135518315144,
1003
+ "loss": 2.3882,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.2830094668659691,
1008
+ "grad_norm": 0.09060754626989365,
1009
+ "learning_rate": 0.00016640431633311973,
1010
+ "loss": 2.4853,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.2850024912805182,
1015
+ "grad_norm": 0.06602101027965546,
1016
+ "learning_rate": 0.00016592455896899177,
1017
+ "loss": 2.2281,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.28699551569506726,
1022
+ "grad_norm": 0.1278272569179535,
1023
+ "learning_rate": 0.00016544210273146607,
1024
+ "loss": 2.4952,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.28898854010961633,
1029
+ "grad_norm": 0.0747796967625618,
1030
+ "learning_rate": 0.0001649569673717298,
1031
+ "loss": 2.4031,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.2909815645241654,
1036
+ "grad_norm": 0.07359785586595535,
1037
+ "learning_rate": 0.0001644691727506503,
1038
+ "loss": 2.3986,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.2929745889387145,
1043
+ "grad_norm": 0.07316705584526062,
1044
+ "learning_rate": 0.00016397873883796182,
1045
+ "loss": 2.3427,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.2949676133532636,
1050
+ "grad_norm": 0.08125218749046326,
1051
+ "learning_rate": 0.00016348568571144815,
1052
+ "loss": 2.4141,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.2969606377678127,
1057
+ "grad_norm": 0.08206519484519958,
1058
+ "learning_rate": 0.0001629900335561206,
1059
+ "loss": 2.3646,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.29895366218236175,
1064
+ "grad_norm": 0.08812980353832245,
1065
+ "learning_rate": 0.0001624918026633916,
1066
+ "loss": 2.4601,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.3009466865969108,
1071
+ "grad_norm": 0.08105914294719696,
1072
+ "learning_rate": 0.00016199101343024403,
1073
+ "loss": 2.3585,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.3029397110114599,
1078
+ "grad_norm": 0.06967832148075104,
1079
+ "learning_rate": 0.00016148768635839623,
1080
+ "loss": 2.2433,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.30493273542600896,
1085
+ "grad_norm": 0.09295759350061417,
1086
+ "learning_rate": 0.0001609818420534627,
1087
+ "loss": 2.4471,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.30692575984055803,
1092
+ "grad_norm": 0.07374819368124008,
1093
+ "learning_rate": 0.00016047350122411037,
1094
+ "loss": 2.4467,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.3089187842551071,
1099
+ "grad_norm": 0.09636169672012329,
1100
+ "learning_rate": 0.00015996268468121102,
1101
+ "loss": 2.3976,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.3109118086696562,
1106
+ "grad_norm": 0.09988832473754883,
1107
+ "learning_rate": 0.00015944941333698913,
1108
+ "loss": 2.4552,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.3129048330842053,
1113
+ "grad_norm": 0.07126818597316742,
1114
+ "learning_rate": 0.00015893370820416593,
1115
+ "loss": 2.3902,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.3148978574987544,
1120
+ "grad_norm": 0.07881104201078415,
1121
+ "learning_rate": 0.00015841559039509896,
1122
+ "loss": 2.3797,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.31689088191330345,
1127
+ "grad_norm": 0.0768013745546341,
1128
+ "learning_rate": 0.00015789508112091803,
1129
+ "loss": 2.3964,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.3188839063278525,
1134
+ "grad_norm": 0.08057546615600586,
1135
+ "learning_rate": 0.00015737220169065655,
1136
+ "loss": 2.4749,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.3208769307424016,
1141
+ "grad_norm": 0.07979754358530045,
1142
+ "learning_rate": 0.00015684697351037936,
1143
+ "loss": 2.4418,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.32286995515695066,
1148
+ "grad_norm": 0.06544126570224762,
1149
+ "learning_rate": 0.00015631941808230638,
1150
+ "loss": 2.2927,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.32486297957149973,
1155
+ "grad_norm": 0.08288611471652985,
1156
+ "learning_rate": 0.00015578955700393227,
1157
+ "loss": 2.3505,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.3268560039860488,
1162
+ "grad_norm": 0.0897054448723793,
1163
+ "learning_rate": 0.0001552574119671423,
1164
+ "loss": 2.5074,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.32884902840059793,
1169
+ "grad_norm": 0.08678635954856873,
1170
+ "learning_rate": 0.00015472300475732426,
1171
+ "loss": 2.4926,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.330842052815147,
1176
+ "grad_norm": 0.09113283455371857,
1177
+ "learning_rate": 0.00015418635725247666,
1178
+ "loss": 2.395,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.3328350772296961,
1183
+ "grad_norm": 0.06857576966285706,
1184
+ "learning_rate": 0.00015364749142231303,
1185
+ "loss": 2.476,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.3328350772296961,
1190
+ "eval_loss": 2.387300491333008,
1191
+ "eval_runtime": 44.0668,
1192
+ "eval_samples_per_second": 19.175,
1193
+ "eval_steps_per_second": 2.405,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.33482810164424515,
1198
+ "grad_norm": 0.08880946785211563,
1199
+ "learning_rate": 0.00015310642932736253,
1200
+ "loss": 2.4641,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.3368211260587942,
1205
+ "grad_norm": 0.08142423629760742,
1206
+ "learning_rate": 0.00015256319311806671,
1207
+ "loss": 2.4356,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.3388141504733433,
1212
+ "grad_norm": 0.08891778439283371,
1213
+ "learning_rate": 0.0001520178050338729,
1214
+ "loss": 2.4217,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.34080717488789236,
1219
+ "grad_norm": 0.0702689066529274,
1220
+ "learning_rate": 0.0001514702874023236,
1221
+ "loss": 2.2909,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.34280019930244143,
1226
+ "grad_norm": 0.06824884563684464,
1227
+ "learning_rate": 0.00015092066263814243,
1228
+ "loss": 2.4295,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.34479322371699056,
1233
+ "grad_norm": 0.08762337267398834,
1234
+ "learning_rate": 0.0001503689532423166,
1235
+ "loss": 2.4908,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.34678624813153963,
1240
+ "grad_norm": 0.06757575273513794,
1241
+ "learning_rate": 0.00014981518180117557,
1242
+ "loss": 2.3773,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.3487792725460887,
1247
+ "grad_norm": 0.08849743753671646,
1248
+ "learning_rate": 0.00014925937098546652,
1249
+ "loss": 2.3519,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.3507722969606378,
1254
+ "grad_norm": 0.08153015375137329,
1255
+ "learning_rate": 0.0001487015435494263,
1256
+ "loss": 2.3288,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.35276532137518685,
1261
+ "grad_norm": 0.07309590280056,
1262
+ "learning_rate": 0.00014814172232984968,
1263
+ "loss": 2.5162,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.3547583457897359,
1268
+ "grad_norm": 0.07999510318040848,
1269
+ "learning_rate": 0.0001475799302451547,
1270
+ "loss": 2.3182,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.356751370204285,
1275
+ "grad_norm": 0.07473445683717728,
1276
+ "learning_rate": 0.0001470161902944442,
1277
+ "loss": 2.5029,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.35874439461883406,
1282
+ "grad_norm": 0.08201662451028824,
1283
+ "learning_rate": 0.00014645052555656431,
1284
+ "loss": 2.2793,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.36073741903338313,
1289
+ "grad_norm": 0.07323934882879257,
1290
+ "learning_rate": 0.00014588295918915978,
1291
+ "loss": 2.3341,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.36273044344793226,
1296
+ "grad_norm": 0.07921049743890762,
1297
+ "learning_rate": 0.0001453135144277257,
1298
+ "loss": 2.3682,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.36472346786248133,
1303
+ "grad_norm": 0.08165313303470612,
1304
+ "learning_rate": 0.0001447422145846565,
1305
+ "loss": 2.5328,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.3667164922770304,
1310
+ "grad_norm": 0.07465358823537827,
1311
+ "learning_rate": 0.00014416908304829142,
1312
+ "loss": 2.325,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.3687095166915795,
1317
+ "grad_norm": 0.08058230578899384,
1318
+ "learning_rate": 0.00014359414328195703,
1319
+ "loss": 2.3559,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.37070254110612855,
1324
+ "grad_norm": 0.08216605335474014,
1325
+ "learning_rate": 0.00014301741882300672,
1326
+ "loss": 2.4959,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.3726955655206776,
1331
+ "grad_norm": 0.0775436982512474,
1332
+ "learning_rate": 0.000142438933281857,
1333
+ "loss": 2.3949,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.3746885899352267,
1338
+ "grad_norm": 0.07073415815830231,
1339
+ "learning_rate": 0.00014185871034102116,
1340
+ "loss": 2.5376,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.37668161434977576,
1345
+ "grad_norm": 0.07668204605579376,
1346
+ "learning_rate": 0.00014127677375413942,
1347
+ "loss": 2.2313,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.3786746387643249,
1352
+ "grad_norm": 0.07412687689065933,
1353
+ "learning_rate": 0.00014069314734500675,
1354
+ "loss": 2.2357,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.38066766317887396,
1359
+ "grad_norm": 0.08573145419359207,
1360
+ "learning_rate": 0.00014010785500659736,
1361
+ "loss": 2.3195,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.38266068759342303,
1366
+ "grad_norm": 0.08401142805814743,
1367
+ "learning_rate": 0.0001395209207000867,
1368
+ "loss": 2.3743,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.3846537120079721,
1373
+ "grad_norm": 0.08807343244552612,
1374
+ "learning_rate": 0.00013893236845387042,
1375
+ "loss": 2.3483,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.3866467364225212,
1380
+ "grad_norm": 0.06947995722293854,
1381
+ "learning_rate": 0.0001383422223625807,
1382
+ "loss": 2.4067,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.38863976083707025,
1387
+ "grad_norm": 0.07555301487445831,
1388
+ "learning_rate": 0.00013775050658609988,
1389
+ "loss": 2.3116,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.3906327852516193,
1394
+ "grad_norm": 0.09824465960264206,
1395
+ "learning_rate": 0.00013715724534857127,
1396
+ "loss": 2.4625,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.3926258096661684,
1401
+ "grad_norm": 0.07294239103794098,
1402
+ "learning_rate": 0.00013656246293740766,
1403
+ "loss": 2.2869,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.39461883408071746,
1408
+ "grad_norm": 0.07457131147384644,
1409
+ "learning_rate": 0.0001359661837022968,
1410
+ "loss": 2.4017,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.3966118584952666,
1415
+ "grad_norm": 0.0777326449751854,
1416
+ "learning_rate": 0.0001353684320542046,
1417
+ "loss": 2.318,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.39860488290981566,
1422
+ "grad_norm": 0.07553141564130783,
1423
+ "learning_rate": 0.0001347692324643759,
1424
+ "loss": 2.3538,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.40059790732436473,
1429
+ "grad_norm": 0.06624465435743332,
1430
+ "learning_rate": 0.00013416860946333255,
1431
+ "loss": 2.2975,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.4025909317389138,
1436
+ "grad_norm": 0.07756485044956207,
1437
+ "learning_rate": 0.00013356658763986917,
1438
+ "loss": 2.4048,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.4045839561534629,
1443
+ "grad_norm": 0.07636179029941559,
1444
+ "learning_rate": 0.00013296319164004644,
1445
+ "loss": 2.4506,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.40657698056801195,
1450
+ "grad_norm": 0.0766957700252533,
1451
+ "learning_rate": 0.0001323584461661823,
1452
+ "loss": 2.3196,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.408570004982561,
1457
+ "grad_norm": 0.08431121706962585,
1458
+ "learning_rate": 0.00013175237597584045,
1459
+ "loss": 2.4682,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.4105630293971101,
1464
+ "grad_norm": 0.08995452523231506,
1465
+ "learning_rate": 0.00013114500588081698,
1466
+ "loss": 2.3855,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.4125560538116592,
1471
+ "grad_norm": 0.09474631398916245,
1472
+ "learning_rate": 0.00013053636074612457,
1473
+ "loss": 2.6147,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.4145490782262083,
1478
+ "grad_norm": 0.07415032386779785,
1479
+ "learning_rate": 0.00012992646548897442,
1480
+ "loss": 2.4186,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.41654210264075736,
1485
+ "grad_norm": 0.08406328409910202,
1486
+ "learning_rate": 0.0001293153450777564,
1487
+ "loss": 2.5179,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.41853512705530643,
1492
+ "grad_norm": 0.08891643583774567,
1493
+ "learning_rate": 0.00012870302453101657,
1494
+ "loss": 2.3027,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.4205281514698555,
1499
+ "grad_norm": 0.1395743042230606,
1500
+ "learning_rate": 0.00012808952891643326,
1501
+ "loss": 2.3359,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.4225211758844046,
1506
+ "grad_norm": 0.07339651882648468,
1507
+ "learning_rate": 0.00012747488334979062,
1508
+ "loss": 2.3851,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.42451420029895365,
1513
+ "grad_norm": 0.08407889306545258,
1514
+ "learning_rate": 0.00012685911299395046,
1515
+ "loss": 2.2163,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.4265072247135027,
1520
+ "grad_norm": 0.08630604296922684,
1521
+ "learning_rate": 0.00012624224305782215,
1522
+ "loss": 2.4366,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.4285002491280518,
1527
+ "grad_norm": 0.0809294730424881,
1528
+ "learning_rate": 0.0001256242987953306,
1529
+ "loss": 2.444,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.4304932735426009,
1534
+ "grad_norm": 0.0742102637887001,
1535
+ "learning_rate": 0.00012500530550438232,
1536
+ "loss": 2.2523,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.43248629795715,
1541
+ "grad_norm": 0.06552259624004364,
1542
+ "learning_rate": 0.00012438528852582988,
1543
+ "loss": 2.2975,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.43447932237169906,
1548
+ "grad_norm": 0.09436741471290588,
1549
+ "learning_rate": 0.00012376427324243432,
1550
+ "loss": 2.4428,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.43647234678624813,
1555
+ "grad_norm": 0.07835572957992554,
1556
+ "learning_rate": 0.00012314228507782614,
1557
+ "loss": 2.4217,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.4384653712007972,
1562
+ "grad_norm": 0.07683923840522766,
1563
+ "learning_rate": 0.00012251934949546447,
1564
+ "loss": 2.2785,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.4404583956153463,
1569
+ "grad_norm": 0.07561761885881424,
1570
+ "learning_rate": 0.00012189549199759453,
1571
+ "loss": 2.4763,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.44245142002989535,
1576
+ "grad_norm": 0.08108748495578766,
1577
+ "learning_rate": 0.00012127073812420375,
1578
+ "loss": 2.2859,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.4444444444444444,
1583
+ "grad_norm": 0.08844010531902313,
1584
+ "learning_rate": 0.00012064511345197607,
1585
+ "loss": 2.4214,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.44643746885899355,
1590
+ "grad_norm": 0.07926416397094727,
1591
+ "learning_rate": 0.00012001864359324489,
1592
+ "loss": 2.4016,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.4484304932735426,
1597
+ "grad_norm": 0.07725399732589722,
1598
+ "learning_rate": 0.00011939135419494456,
1599
+ "loss": 2.2892,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.4504235176880917,
1604
+ "grad_norm": 0.0865224227309227,
1605
+ "learning_rate": 0.00011876327093756047,
1606
+ "loss": 2.3323,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.45241654210264076,
1611
+ "grad_norm": 0.08520185202360153,
1612
+ "learning_rate": 0.00011813441953407754,
1613
+ "loss": 2.4763,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.45440956651718983,
1618
+ "grad_norm": 0.08354134112596512,
1619
+ "learning_rate": 0.0001175048257289278,
1620
+ "loss": 2.26,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.4564025909317389,
1625
+ "grad_norm": 0.068196602165699,
1626
+ "learning_rate": 0.00011687451529693624,
1627
+ "loss": 2.3824,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.458395615346288,
1632
+ "grad_norm": 0.0725112035870552,
1633
+ "learning_rate": 0.00011624351404226572,
1634
+ "loss": 2.3182,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.46038863976083705,
1639
+ "grad_norm": 0.07587240636348724,
1640
+ "learning_rate": 0.00011561184779736061,
1641
+ "loss": 2.3753,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.4623816641753862,
1646
+ "grad_norm": 0.08274877816438675,
1647
+ "learning_rate": 0.00011497954242188913,
1648
+ "loss": 2.3417,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.46437468858993525,
1653
+ "grad_norm": 0.07583466172218323,
1654
+ "learning_rate": 0.00011434662380168486,
1655
+ "loss": 2.4552,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.4663677130044843,
1660
+ "grad_norm": 0.07493368536233902,
1661
+ "learning_rate": 0.00011371311784768673,
1662
+ "loss": 2.3099,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.4683607374190334,
1667
+ "grad_norm": 0.10445628315210342,
1668
+ "learning_rate": 0.00011307905049487855,
1669
+ "loss": 2.4744,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.47035376183358246,
1674
+ "grad_norm": 0.08778560161590576,
1675
+ "learning_rate": 0.00011244444770122707,
1676
+ "loss": 2.3622,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.47234678624813153,
1681
+ "grad_norm": 0.10534396022558212,
1682
+ "learning_rate": 0.00011180933544661936,
1683
+ "loss": 2.3793,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.4743398106626806,
1688
+ "grad_norm": 0.08375269174575806,
1689
+ "learning_rate": 0.00011117373973179925,
1690
+ "loss": 2.5479,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.4763328350772297,
1695
+ "grad_norm": 0.07987891137599945,
1696
+ "learning_rate": 0.00011053768657730284,
1697
+ "loss": 2.3698,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.47832585949177875,
1702
+ "grad_norm": 0.07837790250778198,
1703
+ "learning_rate": 0.00010990120202239324,
1704
+ "loss": 2.2549,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.4803188839063279,
1709
+ "grad_norm": 0.07100849598646164,
1710
+ "learning_rate": 0.00010926431212399466,
1711
+ "loss": 2.1705,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.48231190832087695,
1716
+ "grad_norm": 0.08972784876823425,
1717
+ "learning_rate": 0.0001086270429556255,
1718
+ "loss": 2.4271,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.484304932735426,
1723
+ "grad_norm": 0.07568995654582977,
1724
+ "learning_rate": 0.00010798942060633108,
1725
+ "loss": 2.4392,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.4862979571499751,
1730
+ "grad_norm": 0.07962235808372498,
1731
+ "learning_rate": 0.0001073514711796155,
1732
+ "loss": 2.3391,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 0.48829098156452416,
1737
+ "grad_norm": 0.08790632337331772,
1738
+ "learning_rate": 0.00010671322079237307,
1739
+ "loss": 2.3399,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 0.49028400597907323,
1744
+ "grad_norm": 0.08196309208869934,
1745
+ "learning_rate": 0.00010607469557381899,
1746
+ "loss": 2.3413,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 0.4922770303936223,
1751
+ "grad_norm": 0.07845258712768555,
1752
+ "learning_rate": 0.00010543592166441983,
1753
+ "loss": 2.4144,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 0.4942700548081714,
1758
+ "grad_norm": 0.09686846286058426,
1759
+ "learning_rate": 0.00010479692521482316,
1760
+ "loss": 2.3982,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 0.4962630792227205,
1765
+ "grad_norm": 0.0939926877617836,
1766
+ "learning_rate": 0.00010415773238478715,
1767
+ "loss": 2.4944,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 0.4982561036372696,
1772
+ "grad_norm": 0.08639413863420486,
1773
+ "learning_rate": 0.00010351836934210957,
1774
+ "loss": 2.425,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 0.5002491280518186,
1779
+ "grad_norm": 0.0854463130235672,
1780
+ "learning_rate": 0.00010287886226155641,
1781
+ "loss": 2.4194,
1782
+ "step": 251
1783
+ },
1784
+ {
1785
+ "epoch": 0.5022421524663677,
1786
+ "grad_norm": 0.068091981112957,
1787
+ "learning_rate": 0.00010223923732379048,
1788
+ "loss": 2.3863,
1789
+ "step": 252
1790
+ },
1791
+ {
1792
+ "epoch": 0.5042351768809168,
1793
+ "grad_norm": 0.08234778046607971,
1794
+ "learning_rate": 0.00010159952071429952,
1795
+ "loss": 2.3304,
1796
+ "step": 253
1797
+ },
1798
+ {
1799
+ "epoch": 0.5062282012954659,
1800
+ "grad_norm": 0.07626478374004364,
1801
+ "learning_rate": 0.0001009597386223241,
1802
+ "loss": 2.4942,
1803
+ "step": 254
1804
+ },
1805
+ {
1806
+ "epoch": 0.5082212257100149,
1807
+ "grad_norm": 0.07903891056776047,
1808
+ "learning_rate": 0.00010031991723978574,
1809
+ "loss": 2.4462,
1810
+ "step": 255
1811
+ },
1812
+ {
1813
+ "epoch": 0.510214250124564,
1814
+ "grad_norm": 0.0762149766087532,
1815
+ "learning_rate": 9.96800827602143e-05,
1816
+ "loss": 2.294,
1817
+ "step": 256
1818
+ },
1819
+ {
1820
+ "epoch": 0.5122072745391131,
1821
+ "grad_norm": 0.0710691586136818,
1822
+ "learning_rate": 9.90402613776759e-05,
1823
+ "loss": 2.4069,
1824
+ "step": 257
1825
+ },
1826
+ {
1827
+ "epoch": 0.5142002989536621,
1828
+ "grad_norm": 0.0813589096069336,
1829
+ "learning_rate": 9.84004792857005e-05,
1830
+ "loss": 2.4097,
1831
+ "step": 258
1832
+ },
1833
+ {
1834
+ "epoch": 0.5161933233682112,
1835
+ "grad_norm": 0.07613521069288254,
1836
+ "learning_rate": 9.776076267620955e-05,
1837
+ "loss": 2.4159,
1838
+ "step": 259
1839
+ },
1840
+ {
1841
+ "epoch": 0.5181863477827603,
1842
+ "grad_norm": 0.07381565123796463,
1843
+ "learning_rate": 9.712113773844361e-05,
1844
+ "loss": 2.3325,
1845
+ "step": 260
1846
+ },
1847
+ {
1848
+ "epoch": 0.5201793721973094,
1849
+ "grad_norm": 0.08574292808771133,
1850
+ "learning_rate": 9.648163065789045e-05,
1851
+ "loss": 2.4013,
1852
+ "step": 261
1853
+ },
1854
+ {
1855
+ "epoch": 0.5221723966118585,
1856
+ "grad_norm": 0.07233965396881104,
1857
+ "learning_rate": 9.584226761521285e-05,
1858
+ "loss": 2.3174,
1859
+ "step": 262
1860
+ },
1861
+ {
1862
+ "epoch": 0.5241654210264076,
1863
+ "grad_norm": 0.08652372658252716,
1864
+ "learning_rate": 9.520307478517686e-05,
1865
+ "loss": 2.3664,
1866
+ "step": 263
1867
+ },
1868
+ {
1869
+ "epoch": 0.5261584454409567,
1870
+ "grad_norm": 0.07672926038503647,
1871
+ "learning_rate": 9.456407833558018e-05,
1872
+ "loss": 2.3683,
1873
+ "step": 264
1874
+ },
1875
+ {
1876
+ "epoch": 0.5281514698555058,
1877
+ "grad_norm": 0.0732818990945816,
1878
+ "learning_rate": 9.3925304426181e-05,
1879
+ "loss": 2.3606,
1880
+ "step": 265
1881
+ },
1882
+ {
1883
+ "epoch": 0.5301444942700548,
1884
+ "grad_norm": 0.07968168705701828,
1885
+ "learning_rate": 9.328677920762697e-05,
1886
+ "loss": 2.4648,
1887
+ "step": 266
1888
+ },
1889
+ {
1890
+ "epoch": 0.5321375186846039,
1891
+ "grad_norm": 0.09718236327171326,
1892
+ "learning_rate": 9.264852882038453e-05,
1893
+ "loss": 2.4041,
1894
+ "step": 267
1895
+ },
1896
+ {
1897
+ "epoch": 0.534130543099153,
1898
+ "grad_norm": 0.07884249091148376,
1899
+ "learning_rate": 9.201057939366896e-05,
1900
+ "loss": 2.3663,
1901
+ "step": 268
1902
+ },
1903
+ {
1904
+ "epoch": 0.536123567513702,
1905
+ "grad_norm": 0.06967094540596008,
1906
+ "learning_rate": 9.13729570443745e-05,
1907
+ "loss": 2.4421,
1908
+ "step": 269
1909
+ },
1910
+ {
1911
+ "epoch": 0.5381165919282511,
1912
+ "grad_norm": 0.083594411611557,
1913
+ "learning_rate": 9.073568787600539e-05,
1914
+ "loss": 2.3412,
1915
+ "step": 270
1916
+ },
1917
+ {
1918
+ "epoch": 0.5401096163428002,
1919
+ "grad_norm": 0.08003851026296616,
1920
+ "learning_rate": 9.009879797760678e-05,
1921
+ "loss": 2.3437,
1922
+ "step": 271
1923
+ },
1924
+ {
1925
+ "epoch": 0.5421026407573493,
1926
+ "grad_norm": 0.0989484116435051,
1927
+ "learning_rate": 8.946231342269718e-05,
1928
+ "loss": 2.4203,
1929
+ "step": 272
1930
+ },
1931
+ {
1932
+ "epoch": 0.5440956651718983,
1933
+ "grad_norm": 0.06733080744743347,
1934
+ "learning_rate": 8.882626026820078e-05,
1935
+ "loss": 2.4546,
1936
+ "step": 273
1937
+ },
1938
+ {
1939
+ "epoch": 0.5460886895864474,
1940
+ "grad_norm": 0.0802733302116394,
1941
+ "learning_rate": 8.819066455338066e-05,
1942
+ "loss": 2.357,
1943
+ "step": 274
1944
+ },
1945
+ {
1946
+ "epoch": 0.5480817140009965,
1947
+ "grad_norm": 0.07700028270483017,
1948
+ "learning_rate": 8.755555229877294e-05,
1949
+ "loss": 2.3546,
1950
+ "step": 275
1951
+ },
1952
+ {
1953
+ "epoch": 0.5500747384155455,
1954
+ "grad_norm": 0.0829630196094513,
1955
+ "learning_rate": 8.692094950512145e-05,
1956
+ "loss": 2.4158,
1957
+ "step": 276
1958
+ },
1959
+ {
1960
+ "epoch": 0.5520677628300946,
1961
+ "grad_norm": 0.09082596004009247,
1962
+ "learning_rate": 8.62868821523133e-05,
1963
+ "loss": 2.3937,
1964
+ "step": 277
1965
+ },
1966
+ {
1967
+ "epoch": 0.5540607872446437,
1968
+ "grad_norm": 0.07257676124572754,
1969
+ "learning_rate": 8.565337619831516e-05,
1970
+ "loss": 2.3785,
1971
+ "step": 278
1972
+ },
1973
+ {
1974
+ "epoch": 0.5560538116591929,
1975
+ "grad_norm": 0.0851656049489975,
1976
+ "learning_rate": 8.502045757811085e-05,
1977
+ "loss": 2.3528,
1978
+ "step": 279
1979
+ },
1980
+ {
1981
+ "epoch": 0.558046836073742,
1982
+ "grad_norm": 0.08436737954616547,
1983
+ "learning_rate": 8.438815220263941e-05,
1984
+ "loss": 2.4697,
1985
+ "step": 280
1986
+ },
1987
+ {
1988
+ "epoch": 0.560039860488291,
1989
+ "grad_norm": 0.07827769964933395,
1990
+ "learning_rate": 8.37564859577343e-05,
1991
+ "loss": 2.3362,
1992
+ "step": 281
1993
+ },
1994
+ {
1995
+ "epoch": 0.5620328849028401,
1996
+ "grad_norm": 0.06859832257032394,
1997
+ "learning_rate": 8.312548470306378e-05,
1998
+ "loss": 2.239,
1999
+ "step": 282
2000
+ },
2001
+ {
2002
+ "epoch": 0.5640259093173892,
2003
+ "grad_norm": 0.09093625843524933,
2004
+ "learning_rate": 8.249517427107225e-05,
2005
+ "loss": 2.4027,
2006
+ "step": 283
2007
+ },
2008
+ {
2009
+ "epoch": 0.5660189337319382,
2010
+ "grad_norm": 0.07230457663536072,
2011
+ "learning_rate": 8.186558046592247e-05,
2012
+ "loss": 2.3005,
2013
+ "step": 284
2014
+ },
2015
+ {
2016
+ "epoch": 0.5680119581464873,
2017
+ "grad_norm": 0.08575095981359482,
2018
+ "learning_rate": 8.123672906243955e-05,
2019
+ "loss": 2.3379,
2020
+ "step": 285
2021
+ },
2022
+ {
2023
+ "epoch": 0.5700049825610364,
2024
+ "grad_norm": 0.0768265426158905,
2025
+ "learning_rate": 8.060864580505543e-05,
2026
+ "loss": 2.3717,
2027
+ "step": 286
2028
+ },
2029
+ {
2030
+ "epoch": 0.5719980069755854,
2031
+ "grad_norm": 0.08535900712013245,
2032
+ "learning_rate": 7.998135640675513e-05,
2033
+ "loss": 2.2963,
2034
+ "step": 287
2035
+ },
2036
+ {
2037
+ "epoch": 0.5739910313901345,
2038
+ "grad_norm": 0.07312452048063278,
2039
+ "learning_rate": 7.935488654802394e-05,
2040
+ "loss": 2.3839,
2041
+ "step": 288
2042
+ },
2043
+ {
2044
+ "epoch": 0.5759840558046836,
2045
+ "grad_norm": 0.08283963054418564,
2046
+ "learning_rate": 7.872926187579626e-05,
2047
+ "loss": 2.361,
2048
+ "step": 289
2049
+ },
2050
+ {
2051
+ "epoch": 0.5779770802192327,
2052
+ "grad_norm": 0.08063699305057526,
2053
+ "learning_rate": 7.810450800240549e-05,
2054
+ "loss": 2.396,
2055
+ "step": 290
2056
+ },
2057
+ {
2058
+ "epoch": 0.5799701046337817,
2059
+ "grad_norm": 0.08969046920537949,
2060
+ "learning_rate": 7.748065050453557e-05,
2061
+ "loss": 2.4518,
2062
+ "step": 291
2063
+ },
2064
+ {
2065
+ "epoch": 0.5819631290483308,
2066
+ "grad_norm": 0.07726722955703735,
2067
+ "learning_rate": 7.685771492217386e-05,
2068
+ "loss": 2.3444,
2069
+ "step": 292
2070
+ },
2071
+ {
2072
+ "epoch": 0.5839561534628799,
2073
+ "grad_norm": 0.07222528010606766,
2074
+ "learning_rate": 7.623572675756569e-05,
2075
+ "loss": 2.322,
2076
+ "step": 293
2077
+ },
2078
+ {
2079
+ "epoch": 0.585949177877429,
2080
+ "grad_norm": 0.08061039447784424,
2081
+ "learning_rate": 7.561471147417016e-05,
2082
+ "loss": 2.4666,
2083
+ "step": 294
2084
+ },
2085
+ {
2086
+ "epoch": 0.587942202291978,
2087
+ "grad_norm": 0.08834525942802429,
2088
+ "learning_rate": 7.499469449561769e-05,
2089
+ "loss": 2.5125,
2090
+ "step": 295
2091
+ },
2092
+ {
2093
+ "epoch": 0.5899352267065272,
2094
+ "grad_norm": 0.07406936585903168,
2095
+ "learning_rate": 7.437570120466942e-05,
2096
+ "loss": 2.2816,
2097
+ "step": 296
2098
+ },
2099
+ {
2100
+ "epoch": 0.5919282511210763,
2101
+ "grad_norm": 0.07327903807163239,
2102
+ "learning_rate": 7.375775694217787e-05,
2103
+ "loss": 2.3489,
2104
+ "step": 297
2105
+ },
2106
+ {
2107
+ "epoch": 0.5939212755356253,
2108
+ "grad_norm": 0.07576936483383179,
2109
+ "learning_rate": 7.314088700604958e-05,
2110
+ "loss": 2.3808,
2111
+ "step": 298
2112
+ },
2113
+ {
2114
+ "epoch": 0.5959142999501744,
2115
+ "grad_norm": 0.0771130621433258,
2116
+ "learning_rate": 7.252511665020939e-05,
2117
+ "loss": 2.4651,
2118
+ "step": 299
2119
+ },
2120
+ {
2121
+ "epoch": 0.5979073243647235,
2122
+ "grad_norm": 0.0683421716094017,
2123
+ "learning_rate": 7.191047108356672e-05,
2124
+ "loss": 2.3074,
2125
+ "step": 300
2126
+ },
2127
+ {
2128
+ "epoch": 0.5999003487792726,
2129
+ "grad_norm": 0.06771375238895416,
2130
+ "learning_rate": 7.129697546898344e-05,
2131
+ "loss": 2.3923,
2132
+ "step": 301
2133
+ },
2134
+ {
2135
+ "epoch": 0.6018933731938216,
2136
+ "grad_norm": 0.07541806250810623,
2137
+ "learning_rate": 7.068465492224361e-05,
2138
+ "loss": 2.4531,
2139
+ "step": 302
2140
+ },
2141
+ {
2142
+ "epoch": 0.6038863976083707,
2143
+ "grad_norm": 0.10348574072122574,
2144
+ "learning_rate": 7.007353451102556e-05,
2145
+ "loss": 2.4558,
2146
+ "step": 303
2147
+ },
2148
+ {
2149
+ "epoch": 0.6058794220229198,
2150
+ "grad_norm": 0.0760045051574707,
2151
+ "learning_rate": 6.946363925387546e-05,
2152
+ "loss": 2.3943,
2153
+ "step": 304
2154
+ },
2155
+ {
2156
+ "epoch": 0.6078724464374688,
2157
+ "grad_norm": 0.06345969438552856,
2158
+ "learning_rate": 6.885499411918304e-05,
2159
+ "loss": 2.3374,
2160
+ "step": 305
2161
+ },
2162
+ {
2163
+ "epoch": 0.6098654708520179,
2164
+ "grad_norm": 0.06523160636425018,
2165
+ "learning_rate": 6.824762402415957e-05,
2166
+ "loss": 2.3551,
2167
+ "step": 306
2168
+ },
2169
+ {
2170
+ "epoch": 0.611858495266567,
2171
+ "grad_norm": 0.0740005224943161,
2172
+ "learning_rate": 6.764155383381771e-05,
2173
+ "loss": 2.2716,
2174
+ "step": 307
2175
+ },
2176
+ {
2177
+ "epoch": 0.6138515196811161,
2178
+ "grad_norm": 0.07560506463050842,
2179
+ "learning_rate": 6.703680835995359e-05,
2180
+ "loss": 2.4588,
2181
+ "step": 308
2182
+ },
2183
+ {
2184
+ "epoch": 0.6158445440956651,
2185
+ "grad_norm": 0.08071526139974594,
2186
+ "learning_rate": 6.643341236013086e-05,
2187
+ "loss": 2.3548,
2188
+ "step": 309
2189
+ },
2190
+ {
2191
+ "epoch": 0.6178375685102142,
2192
+ "grad_norm": 0.07100915908813477,
2193
+ "learning_rate": 6.583139053666745e-05,
2194
+ "loss": 2.4133,
2195
+ "step": 310
2196
+ },
2197
+ {
2198
+ "epoch": 0.6198305929247633,
2199
+ "grad_norm": 0.07325609028339386,
2200
+ "learning_rate": 6.523076753562411e-05,
2201
+ "loss": 2.2923,
2202
+ "step": 311
2203
+ },
2204
+ {
2205
+ "epoch": 0.6218236173393124,
2206
+ "grad_norm": 0.07450801879167557,
2207
+ "learning_rate": 6.463156794579544e-05,
2208
+ "loss": 2.3831,
2209
+ "step": 312
2210
+ },
2211
+ {
2212
+ "epoch": 0.6238166417538615,
2213
+ "grad_norm": 0.07177051156759262,
2214
+ "learning_rate": 6.403381629770325e-05,
2215
+ "loss": 2.344,
2216
+ "step": 313
2217
+ },
2218
+ {
2219
+ "epoch": 0.6258096661684106,
2220
+ "grad_norm": 0.07902934402227402,
2221
+ "learning_rate": 6.343753706259239e-05,
2222
+ "loss": 2.3579,
2223
+ "step": 314
2224
+ },
2225
+ {
2226
+ "epoch": 0.6278026905829597,
2227
+ "grad_norm": 0.06792254745960236,
2228
+ "learning_rate": 6.284275465142874e-05,
2229
+ "loss": 2.2613,
2230
+ "step": 315
2231
+ },
2232
+ {
2233
+ "epoch": 0.6297957149975087,
2234
+ "grad_norm": 0.10840310901403427,
2235
+ "learning_rate": 6.224949341390016e-05,
2236
+ "loss": 2.3326,
2237
+ "step": 316
2238
+ },
2239
+ {
2240
+ "epoch": 0.6317887394120578,
2241
+ "grad_norm": 0.0750327855348587,
2242
+ "learning_rate": 6.165777763741931e-05,
2243
+ "loss": 2.3518,
2244
+ "step": 317
2245
+ },
2246
+ {
2247
+ "epoch": 0.6337817638266069,
2248
+ "grad_norm": 0.0807526633143425,
2249
+ "learning_rate": 6.106763154612962e-05,
2250
+ "loss": 2.3051,
2251
+ "step": 318
2252
+ },
2253
+ {
2254
+ "epoch": 0.635774788241156,
2255
+ "grad_norm": 0.08849233388900757,
2256
+ "learning_rate": 6.047907929991333e-05,
2257
+ "loss": 2.3744,
2258
+ "step": 319
2259
+ },
2260
+ {
2261
+ "epoch": 0.637767812655705,
2262
+ "grad_norm": 0.08082512766122818,
2263
+ "learning_rate": 5.989214499340267e-05,
2264
+ "loss": 2.3462,
2265
+ "step": 320
2266
+ },
2267
+ {
2268
+ "epoch": 0.6397608370702541,
2269
+ "grad_norm": 0.07355140149593353,
2270
+ "learning_rate": 5.9306852654993294e-05,
2271
+ "loss": 2.3976,
2272
+ "step": 321
2273
+ },
2274
+ {
2275
+ "epoch": 0.6417538614848032,
2276
+ "grad_norm": 0.07888400554656982,
2277
+ "learning_rate": 5.872322624586061e-05,
2278
+ "loss": 2.3825,
2279
+ "step": 322
2280
+ },
2281
+ {
2282
+ "epoch": 0.6437468858993523,
2283
+ "grad_norm": 0.0955699235200882,
2284
+ "learning_rate": 5.814128965897887e-05,
2285
+ "loss": 2.5342,
2286
+ "step": 323
2287
+ },
2288
+ {
2289
+ "epoch": 0.6457399103139013,
2290
+ "grad_norm": 0.08044037222862244,
2291
+ "learning_rate": 5.756106671814301e-05,
2292
+ "loss": 2.3302,
2293
+ "step": 324
2294
+ },
2295
+ {
2296
+ "epoch": 0.6477329347284504,
2297
+ "grad_norm": 0.07451853901147842,
2298
+ "learning_rate": 5.6982581176993335e-05,
2299
+ "loss": 2.3267,
2300
+ "step": 325
2301
+ },
2302
+ {
2303
+ "epoch": 0.6497259591429995,
2304
+ "grad_norm": 0.07391540706157684,
2305
+ "learning_rate": 5.640585671804296e-05,
2306
+ "loss": 2.443,
2307
+ "step": 326
2308
+ },
2309
+ {
2310
+ "epoch": 0.6517189835575485,
2311
+ "grad_norm": 0.07789580523967743,
2312
+ "learning_rate": 5.5830916951708565e-05,
2313
+ "loss": 2.4257,
2314
+ "step": 327
2315
+ },
2316
+ {
2317
+ "epoch": 0.6537120079720976,
2318
+ "grad_norm": 0.07448147982358932,
2319
+ "learning_rate": 5.52577854153435e-05,
2320
+ "loss": 2.2732,
2321
+ "step": 328
2322
+ },
2323
+ {
2324
+ "epoch": 0.6557050323866468,
2325
+ "grad_norm": 0.07067444920539856,
2326
+ "learning_rate": 5.4686485572274336e-05,
2327
+ "loss": 2.4449,
2328
+ "step": 329
2329
+ },
2330
+ {
2331
+ "epoch": 0.6576980568011959,
2332
+ "grad_norm": 0.08958334475755692,
2333
+ "learning_rate": 5.4117040810840246e-05,
2334
+ "loss": 2.473,
2335
+ "step": 330
2336
+ },
2337
+ {
2338
+ "epoch": 0.6596910812157449,
2339
+ "grad_norm": 0.07817470282316208,
2340
+ "learning_rate": 5.354947444343572e-05,
2341
+ "loss": 2.3639,
2342
+ "step": 331
2343
+ },
2344
+ {
2345
+ "epoch": 0.661684105630294,
2346
+ "grad_norm": 0.07394227385520935,
2347
+ "learning_rate": 5.298380970555584e-05,
2348
+ "loss": 2.3803,
2349
+ "step": 332
2350
+ },
2351
+ {
2352
+ "epoch": 0.6636771300448431,
2353
+ "grad_norm": 0.06865612417459488,
2354
+ "learning_rate": 5.242006975484528e-05,
2355
+ "loss": 2.3511,
2356
+ "step": 333
2357
+ },
2358
+ {
2359
+ "epoch": 0.6656701544593921,
2360
+ "grad_norm": 0.0840463936328888,
2361
+ "learning_rate": 5.1858277670150304e-05,
2362
+ "loss": 2.3939,
2363
+ "step": 334
2364
+ },
2365
+ {
2366
+ "epoch": 0.6656701544593921,
2367
+ "eval_loss": 2.3827075958251953,
2368
+ "eval_runtime": 44.5796,
2369
+ "eval_samples_per_second": 18.955,
2370
+ "eval_steps_per_second": 2.378,
2371
+ "step": 334
2372
+ },
2373
+ {
2374
+ "epoch": 0.6676631788739412,
2375
+ "grad_norm": 0.07661012560129166,
2376
+ "learning_rate": 5.129845645057372e-05,
2377
+ "loss": 2.3933,
2378
+ "step": 335
2379
+ },
2380
+ {
2381
+ "epoch": 0.6696562032884903,
2382
+ "grad_norm": 0.0602739118039608,
2383
+ "learning_rate": 5.074062901453351e-05,
2384
+ "loss": 2.3163,
2385
+ "step": 336
2386
+ },
2387
+ {
2388
+ "epoch": 0.6716492277030394,
2389
+ "grad_norm": 0.08398034423589706,
2390
+ "learning_rate": 5.0184818198824454e-05,
2391
+ "loss": 2.4036,
2392
+ "step": 337
2393
+ },
2394
+ {
2395
+ "epoch": 0.6736422521175884,
2396
+ "grad_norm": 0.09583730250597,
2397
+ "learning_rate": 4.963104675768345e-05,
2398
+ "loss": 2.2898,
2399
+ "step": 338
2400
+ },
2401
+ {
2402
+ "epoch": 0.6756352765321375,
2403
+ "grad_norm": 0.08750230818986893,
2404
+ "learning_rate": 4.907933736185757e-05,
2405
+ "loss": 2.4703,
2406
+ "step": 339
2407
+ },
2408
+ {
2409
+ "epoch": 0.6776283009466866,
2410
+ "grad_norm": 0.07826811820268631,
2411
+ "learning_rate": 4.8529712597676426e-05,
2412
+ "loss": 2.5204,
2413
+ "step": 340
2414
+ },
2415
+ {
2416
+ "epoch": 0.6796213253612357,
2417
+ "grad_norm": 0.08350390195846558,
2418
+ "learning_rate": 4.79821949661271e-05,
2419
+ "loss": 2.3043,
2420
+ "step": 341
2421
+ },
2422
+ {
2423
+ "epoch": 0.6816143497757847,
2424
+ "grad_norm": 0.07721138000488281,
2425
+ "learning_rate": 4.74368068819333e-05,
2426
+ "loss": 2.3367,
2427
+ "step": 342
2428
+ },
2429
+ {
2430
+ "epoch": 0.6836073741903338,
2431
+ "grad_norm": 0.0709657222032547,
2432
+ "learning_rate": 4.689357067263751e-05,
2433
+ "loss": 2.3262,
2434
+ "step": 343
2435
+ },
2436
+ {
2437
+ "epoch": 0.6856003986048829,
2438
+ "grad_norm": 0.07002606242895126,
2439
+ "learning_rate": 4.635250857768696e-05,
2440
+ "loss": 2.2506,
2441
+ "step": 344
2442
+ },
2443
+ {
2444
+ "epoch": 0.6875934230194319,
2445
+ "grad_norm": 0.07383072376251221,
2446
+ "learning_rate": 4.581364274752338e-05,
2447
+ "loss": 2.322,
2448
+ "step": 345
2449
+ },
2450
+ {
2451
+ "epoch": 0.6895864474339811,
2452
+ "grad_norm": 0.07141583412885666,
2453
+ "learning_rate": 4.527699524267576e-05,
2454
+ "loss": 2.3248,
2455
+ "step": 346
2456
+ },
2457
+ {
2458
+ "epoch": 0.6915794718485302,
2459
+ "grad_norm": 0.0772763192653656,
2460
+ "learning_rate": 4.474258803285774e-05,
2461
+ "loss": 2.3644,
2462
+ "step": 347
2463
+ },
2464
+ {
2465
+ "epoch": 0.6935724962630793,
2466
+ "grad_norm": 0.0871165320277214,
2467
+ "learning_rate": 4.4210442996067724e-05,
2468
+ "loss": 2.3487,
2469
+ "step": 348
2470
+ },
2471
+ {
2472
+ "epoch": 0.6955655206776283,
2473
+ "grad_norm": 0.10185298323631287,
2474
+ "learning_rate": 4.368058191769363e-05,
2475
+ "loss": 2.3311,
2476
+ "step": 349
2477
+ },
2478
+ {
2479
+ "epoch": 0.6975585450921774,
2480
+ "grad_norm": 0.10113190859556198,
2481
+ "learning_rate": 4.315302648962066e-05,
2482
+ "loss": 2.4132,
2483
+ "step": 350
2484
+ },
2485
+ {
2486
+ "epoch": 0.6995515695067265,
2487
+ "grad_norm": 0.07139188796281815,
2488
+ "learning_rate": 4.262779830934346e-05,
2489
+ "loss": 2.3678,
2490
+ "step": 351
2491
+ },
2492
+ {
2493
+ "epoch": 0.7015445939212755,
2494
+ "grad_norm": 0.07751680910587311,
2495
+ "learning_rate": 4.210491887908201e-05,
2496
+ "loss": 2.3148,
2497
+ "step": 352
2498
+ },
2499
+ {
2500
+ "epoch": 0.7035376183358246,
2501
+ "grad_norm": 0.07935532927513123,
2502
+ "learning_rate": 4.158440960490103e-05,
2503
+ "loss": 2.3578,
2504
+ "step": 353
2505
+ },
2506
+ {
2507
+ "epoch": 0.7055306427503737,
2508
+ "grad_norm": 0.09375318139791489,
2509
+ "learning_rate": 4.1066291795834114e-05,
2510
+ "loss": 2.4649,
2511
+ "step": 354
2512
+ },
2513
+ {
2514
+ "epoch": 0.7075236671649228,
2515
+ "grad_norm": 0.08690986782312393,
2516
+ "learning_rate": 4.055058666301087e-05,
2517
+ "loss": 2.4892,
2518
+ "step": 355
2519
+ },
2520
+ {
2521
+ "epoch": 0.7095166915794718,
2522
+ "grad_norm": 0.07989779114723206,
2523
+ "learning_rate": 4.003731531878899e-05,
2524
+ "loss": 2.355,
2525
+ "step": 356
2526
+ },
2527
+ {
2528
+ "epoch": 0.7115097159940209,
2529
+ "grad_norm": 0.07995428144931793,
2530
+ "learning_rate": 3.952649877588964e-05,
2531
+ "loss": 2.4607,
2532
+ "step": 357
2533
+ },
2534
+ {
2535
+ "epoch": 0.71350274040857,
2536
+ "grad_norm": 0.07497061043977737,
2537
+ "learning_rate": 3.901815794653729e-05,
2538
+ "loss": 2.4173,
2539
+ "step": 358
2540
+ },
2541
+ {
2542
+ "epoch": 0.715495764823119,
2543
+ "grad_norm": 0.0910346582531929,
2544
+ "learning_rate": 3.851231364160379e-05,
2545
+ "loss": 2.3495,
2546
+ "step": 359
2547
+ },
2548
+ {
2549
+ "epoch": 0.7174887892376681,
2550
+ "grad_norm": 0.07578431069850922,
2551
+ "learning_rate": 3.800898656975599e-05,
2552
+ "loss": 2.4328,
2553
+ "step": 360
2554
+ },
2555
+ {
2556
+ "epoch": 0.7194818136522172,
2557
+ "grad_norm": 0.08033338189125061,
2558
+ "learning_rate": 3.750819733660844e-05,
2559
+ "loss": 2.3933,
2560
+ "step": 361
2561
+ },
2562
+ {
2563
+ "epoch": 0.7214748380667663,
2564
+ "grad_norm": 0.08443833142518997,
2565
+ "learning_rate": 3.700996644387944e-05,
2566
+ "loss": 2.3738,
2567
+ "step": 362
2568
+ },
2569
+ {
2570
+ "epoch": 0.7234678624813154,
2571
+ "grad_norm": 0.07808777689933777,
2572
+ "learning_rate": 3.651431428855188e-05,
2573
+ "loss": 2.3657,
2574
+ "step": 363
2575
+ },
2576
+ {
2577
+ "epoch": 0.7254608868958645,
2578
+ "grad_norm": 0.0763661339879036,
2579
+ "learning_rate": 3.602126116203819e-05,
2580
+ "loss": 2.5027,
2581
+ "step": 364
2582
+ },
2583
+ {
2584
+ "epoch": 0.7274539113104136,
2585
+ "grad_norm": 0.0828479751944542,
2586
+ "learning_rate": 3.553082724934973e-05,
2587
+ "loss": 2.4403,
2588
+ "step": 365
2589
+ },
2590
+ {
2591
+ "epoch": 0.7294469357249627,
2592
+ "grad_norm": 0.09415590018033981,
2593
+ "learning_rate": 3.504303262827022e-05,
2594
+ "loss": 2.3867,
2595
+ "step": 366
2596
+ },
2597
+ {
2598
+ "epoch": 0.7314399601395117,
2599
+ "grad_norm": 0.08218465000391006,
2600
+ "learning_rate": 3.4557897268533935e-05,
2601
+ "loss": 2.3015,
2602
+ "step": 367
2603
+ },
2604
+ {
2605
+ "epoch": 0.7334329845540608,
2606
+ "grad_norm": 0.0691927969455719,
2607
+ "learning_rate": 3.407544103100824e-05,
2608
+ "loss": 2.3201,
2609
+ "step": 368
2610
+ },
2611
+ {
2612
+ "epoch": 0.7354260089686099,
2613
+ "grad_norm": 0.10156194865703583,
2614
+ "learning_rate": 3.359568366688028e-05,
2615
+ "loss": 2.4098,
2616
+ "step": 369
2617
+ },
2618
+ {
2619
+ "epoch": 0.737419033383159,
2620
+ "grad_norm": 0.0831843763589859,
2621
+ "learning_rate": 3.3118644816848574e-05,
2622
+ "loss": 2.376,
2623
+ "step": 370
2624
+ },
2625
+ {
2626
+ "epoch": 0.739412057797708,
2627
+ "grad_norm": 0.07294479757547379,
2628
+ "learning_rate": 3.264434401031887e-05,
2629
+ "loss": 2.3875,
2630
+ "step": 371
2631
+ },
2632
+ {
2633
+ "epoch": 0.7414050822122571,
2634
+ "grad_norm": 0.08912045508623123,
2635
+ "learning_rate": 3.217280066460472e-05,
2636
+ "loss": 2.3977,
2637
+ "step": 372
2638
+ },
2639
+ {
2640
+ "epoch": 0.7433981066268062,
2641
+ "grad_norm": 0.08084306865930557,
2642
+ "learning_rate": 3.170403408413243e-05,
2643
+ "loss": 2.513,
2644
+ "step": 373
2645
+ },
2646
+ {
2647
+ "epoch": 0.7453911310413552,
2648
+ "grad_norm": 0.08256525546312332,
2649
+ "learning_rate": 3.1238063459650805e-05,
2650
+ "loss": 2.5314,
2651
+ "step": 374
2652
+ },
2653
+ {
2654
+ "epoch": 0.7473841554559043,
2655
+ "grad_norm": 0.08760195225477219,
2656
+ "learning_rate": 3.077490786744562e-05,
2657
+ "loss": 2.5324,
2658
+ "step": 375
2659
+ },
2660
+ {
2661
+ "epoch": 0.7493771798704534,
2662
+ "grad_norm": 0.08779318630695343,
2663
+ "learning_rate": 3.031458626855849e-05,
2664
+ "loss": 2.5542,
2665
+ "step": 376
2666
+ },
2667
+ {
2668
+ "epoch": 0.7513702042850025,
2669
+ "grad_norm": 0.0900694951415062,
2670
+ "learning_rate": 2.985711750801068e-05,
2671
+ "loss": 2.3322,
2672
+ "step": 377
2673
+ },
2674
+ {
2675
+ "epoch": 0.7533632286995515,
2676
+ "grad_norm": 0.08247546851634979,
2677
+ "learning_rate": 2.9402520314031644e-05,
2678
+ "loss": 2.3681,
2679
+ "step": 378
2680
+ },
2681
+ {
2682
+ "epoch": 0.7553562531141006,
2683
+ "grad_norm": 0.06914635747671127,
2684
+ "learning_rate": 2.895081329729239e-05,
2685
+ "loss": 2.3285,
2686
+ "step": 379
2687
+ },
2688
+ {
2689
+ "epoch": 0.7573492775286498,
2690
+ "grad_norm": 0.07177409529685974,
2691
+ "learning_rate": 2.8502014950143373e-05,
2692
+ "loss": 2.3168,
2693
+ "step": 380
2694
+ },
2695
+ {
2696
+ "epoch": 0.7593423019431988,
2697
+ "grad_norm": 0.07681553065776825,
2698
+ "learning_rate": 2.805614364585758e-05,
2699
+ "loss": 2.4145,
2700
+ "step": 381
2701
+ },
2702
+ {
2703
+ "epoch": 0.7613353263577479,
2704
+ "grad_norm": 0.08254451304674149,
2705
+ "learning_rate": 2.7613217637878407e-05,
2706
+ "loss": 2.3909,
2707
+ "step": 382
2708
+ },
2709
+ {
2710
+ "epoch": 0.763328350772297,
2711
+ "grad_norm": 0.0785088837146759,
2712
+ "learning_rate": 2.7173255059072233e-05,
2713
+ "loss": 2.4128,
2714
+ "step": 383
2715
+ },
2716
+ {
2717
+ "epoch": 0.7653213751868461,
2718
+ "grad_norm": 0.08350493013858795,
2719
+ "learning_rate": 2.6736273920986167e-05,
2720
+ "loss": 2.4004,
2721
+ "step": 384
2722
+ },
2723
+ {
2724
+ "epoch": 0.7673143996013951,
2725
+ "grad_norm": 0.08478900045156479,
2726
+ "learning_rate": 2.6302292113110637e-05,
2727
+ "loss": 2.497,
2728
+ "step": 385
2729
+ },
2730
+ {
2731
+ "epoch": 0.7693074240159442,
2732
+ "grad_norm": 0.09736384451389313,
2733
+ "learning_rate": 2.5871327402147172e-05,
2734
+ "loss": 2.4065,
2735
+ "step": 386
2736
+ },
2737
+ {
2738
+ "epoch": 0.7713004484304933,
2739
+ "grad_norm": 0.08156121522188187,
2740
+ "learning_rate": 2.5443397431280702e-05,
2741
+ "loss": 2.4204,
2742
+ "step": 387
2743
+ },
2744
+ {
2745
+ "epoch": 0.7732934728450424,
2746
+ "grad_norm": 0.08983148634433746,
2747
+ "learning_rate": 2.5018519719457723e-05,
2748
+ "loss": 2.354,
2749
+ "step": 388
2750
+ },
2751
+ {
2752
+ "epoch": 0.7752864972595914,
2753
+ "grad_norm": 0.08759213984012604,
2754
+ "learning_rate": 2.4596711660668692e-05,
2755
+ "loss": 2.3316,
2756
+ "step": 389
2757
+ },
2758
+ {
2759
+ "epoch": 0.7772795216741405,
2760
+ "grad_norm": 0.08413752168416977,
2761
+ "learning_rate": 2.4177990523236216e-05,
2762
+ "loss": 2.3757,
2763
+ "step": 390
2764
+ },
2765
+ {
2766
+ "epoch": 0.7792725460886896,
2767
+ "grad_norm": 0.1015741303563118,
2768
+ "learning_rate": 2.3762373449107932e-05,
2769
+ "loss": 2.3046,
2770
+ "step": 391
2771
+ },
2772
+ {
2773
+ "epoch": 0.7812655705032386,
2774
+ "grad_norm": 0.072001613676548,
2775
+ "learning_rate": 2.334987745315478e-05,
2776
+ "loss": 2.4124,
2777
+ "step": 392
2778
+ },
2779
+ {
2780
+ "epoch": 0.7832585949177877,
2781
+ "grad_norm": 0.09683099389076233,
2782
+ "learning_rate": 2.2940519422474573e-05,
2783
+ "loss": 2.268,
2784
+ "step": 393
2785
+ },
2786
+ {
2787
+ "epoch": 0.7852516193323368,
2788
+ "grad_norm": 0.07149074971675873,
2789
+ "learning_rate": 2.253431611570035e-05,
2790
+ "loss": 2.3804,
2791
+ "step": 394
2792
+ },
2793
+ {
2794
+ "epoch": 0.7872446437468859,
2795
+ "grad_norm": 0.07630407065153122,
2796
+ "learning_rate": 2.213128416231468e-05,
2797
+ "loss": 2.2419,
2798
+ "step": 395
2799
+ },
2800
+ {
2801
+ "epoch": 0.7892376681614349,
2802
+ "grad_norm": 0.0810355693101883,
2803
+ "learning_rate": 2.1731440061968533e-05,
2804
+ "loss": 2.3996,
2805
+ "step": 396
2806
+ },
2807
+ {
2808
+ "epoch": 0.7912306925759841,
2809
+ "grad_norm": 0.11724942922592163,
2810
+ "learning_rate": 2.133480018380608e-05,
2811
+ "loss": 2.467,
2812
+ "step": 397
2813
+ },
2814
+ {
2815
+ "epoch": 0.7932237169905332,
2816
+ "grad_norm": 0.0887303277850151,
2817
+ "learning_rate": 2.0941380765794327e-05,
2818
+ "loss": 2.3601,
2819
+ "step": 398
2820
+ },
2821
+ {
2822
+ "epoch": 0.7952167414050823,
2823
+ "grad_norm": 0.07561491429805756,
2824
+ "learning_rate": 2.0551197914058464e-05,
2825
+ "loss": 2.4107,
2826
+ "step": 399
2827
+ },
2828
+ {
2829
+ "epoch": 0.7972097658196313,
2830
+ "grad_norm": 0.10401255637407303,
2831
+ "learning_rate": 2.0164267602222586e-05,
2832
+ "loss": 2.442,
2833
+ "step": 400
2834
+ },
2835
+ {
2836
+ "epoch": 0.7992027902341804,
2837
+ "grad_norm": 0.10470756888389587,
2838
+ "learning_rate": 1.978060567075547e-05,
2839
+ "loss": 2.426,
2840
+ "step": 401
2841
+ },
2842
+ {
2843
+ "epoch": 0.8011958146487295,
2844
+ "grad_norm": 0.06922411173582077,
2845
+ "learning_rate": 1.940022782632248e-05,
2846
+ "loss": 2.3405,
2847
+ "step": 402
2848
+ },
2849
+ {
2850
+ "epoch": 0.8031888390632785,
2851
+ "grad_norm": 0.06700870394706726,
2852
+ "learning_rate": 1.902314964114219e-05,
2853
+ "loss": 2.2573,
2854
+ "step": 403
2855
+ },
2856
+ {
2857
+ "epoch": 0.8051818634778276,
2858
+ "grad_norm": 0.07740623503923416,
2859
+ "learning_rate": 1.8649386552349134e-05,
2860
+ "loss": 2.3546,
2861
+ "step": 404
2862
+ },
2863
+ {
2864
+ "epoch": 0.8071748878923767,
2865
+ "grad_norm": 0.08431963622570038,
2866
+ "learning_rate": 1.827895386136166e-05,
2867
+ "loss": 2.4211,
2868
+ "step": 405
2869
+ },
2870
+ {
2871
+ "epoch": 0.8091679123069258,
2872
+ "grad_norm": 0.0843239575624466,
2873
+ "learning_rate": 1.7911866733255556e-05,
2874
+ "loss": 2.4549,
2875
+ "step": 406
2876
+ },
2877
+ {
2878
+ "epoch": 0.8111609367214748,
2879
+ "grad_norm": 0.08042541891336441,
2880
+ "learning_rate": 1.7548140196143335e-05,
2881
+ "loss": 2.3238,
2882
+ "step": 407
2883
+ },
2884
+ {
2885
+ "epoch": 0.8131539611360239,
2886
+ "grad_norm": 0.07442708313465118,
2887
+ "learning_rate": 1.718778914055873e-05,
2888
+ "loss": 2.5171,
2889
+ "step": 408
2890
+ },
2891
+ {
2892
+ "epoch": 0.815146985550573,
2893
+ "grad_norm": 0.08357364684343338,
2894
+ "learning_rate": 1.6830828318847414e-05,
2895
+ "loss": 2.3985,
2896
+ "step": 409
2897
+ },
2898
+ {
2899
+ "epoch": 0.817140009965122,
2900
+ "grad_norm": 0.0690893903374672,
2901
+ "learning_rate": 1.647727234456279e-05,
2902
+ "loss": 2.3126,
2903
+ "step": 410
2904
+ },
2905
+ {
2906
+ "epoch": 0.8191330343796711,
2907
+ "grad_norm": 0.08741918206214905,
2908
+ "learning_rate": 1.6127135691867945e-05,
2909
+ "loss": 2.4094,
2910
+ "step": 411
2911
+ },
2912
+ {
2913
+ "epoch": 0.8211260587942202,
2914
+ "grad_norm": 0.08018897473812103,
2915
+ "learning_rate": 1.5780432694942815e-05,
2916
+ "loss": 2.3558,
2917
+ "step": 412
2918
+ },
2919
+ {
2920
+ "epoch": 0.8231190832087693,
2921
+ "grad_norm": 0.07996531575918198,
2922
+ "learning_rate": 1.543717754739774e-05,
2923
+ "loss": 2.3011,
2924
+ "step": 413
2925
+ },
2926
+ {
2927
+ "epoch": 0.8251121076233184,
2928
+ "grad_norm": 0.07992850989103317,
2929
+ "learning_rate": 1.5097384301692041e-05,
2930
+ "loss": 2.3581,
2931
+ "step": 414
2932
+ },
2933
+ {
2934
+ "epoch": 0.8271051320378675,
2935
+ "grad_norm": 0.08212057501077652,
2936
+ "learning_rate": 1.4761066868558914e-05,
2937
+ "loss": 2.5278,
2938
+ "step": 415
2939
+ },
2940
+ {
2941
+ "epoch": 0.8290981564524166,
2942
+ "grad_norm": 0.09027457237243652,
2943
+ "learning_rate": 1.4428239016435951e-05,
2944
+ "loss": 2.3586,
2945
+ "step": 416
2946
+ },
2947
+ {
2948
+ "epoch": 0.8310911808669657,
2949
+ "grad_norm": 0.0927945077419281,
2950
+ "learning_rate": 1.4098914370901384e-05,
2951
+ "loss": 2.3267,
2952
+ "step": 417
2953
+ },
2954
+ {
2955
+ "epoch": 0.8330842052815147,
2956
+ "grad_norm": 0.08409656584262848,
2957
+ "learning_rate": 1.3773106414116299e-05,
2958
+ "loss": 2.2682,
2959
+ "step": 418
2960
+ },
2961
+ {
2962
+ "epoch": 0.8350772296960638,
2963
+ "grad_norm": 0.068994902074337,
2964
+ "learning_rate": 1.3450828484272726e-05,
2965
+ "loss": 2.2709,
2966
+ "step": 419
2967
+ },
2968
+ {
2969
+ "epoch": 0.8370702541106129,
2970
+ "grad_norm": 0.07671903073787689,
2971
+ "learning_rate": 1.3132093775047615e-05,
2972
+ "loss": 2.4374,
2973
+ "step": 420
2974
+ },
2975
+ {
2976
+ "epoch": 0.8390632785251619,
2977
+ "grad_norm": 0.08394601941108704,
2978
+ "learning_rate": 1.2816915335062595e-05,
2979
+ "loss": 2.4758,
2980
+ "step": 421
2981
+ },
2982
+ {
2983
+ "epoch": 0.841056302939711,
2984
+ "grad_norm": 0.09269397705793381,
2985
+ "learning_rate": 1.2505306067349853e-05,
2986
+ "loss": 2.4142,
2987
+ "step": 422
2988
+ },
2989
+ {
2990
+ "epoch": 0.8430493273542601,
2991
+ "grad_norm": 0.08710778504610062,
2992
+ "learning_rate": 1.2197278728823947e-05,
2993
+ "loss": 2.3521,
2994
+ "step": 423
2995
+ },
2996
+ {
2997
+ "epoch": 0.8450423517688092,
2998
+ "grad_norm": 0.08058036118745804,
2999
+ "learning_rate": 1.1892845929759412e-05,
3000
+ "loss": 2.3784,
3001
+ "step": 424
3002
+ },
3003
+ {
3004
+ "epoch": 0.8470353761833582,
3005
+ "grad_norm": 0.07262316346168518,
3006
+ "learning_rate": 1.1592020133274639e-05,
3007
+ "loss": 2.3183,
3008
+ "step": 425
3009
+ },
3010
+ {
3011
+ "epoch": 0.8490284005979073,
3012
+ "grad_norm": 0.08008604496717453,
3013
+ "learning_rate": 1.129481365482159e-05,
3014
+ "loss": 2.4448,
3015
+ "step": 426
3016
+ },
3017
+ {
3018
+ "epoch": 0.8510214250124564,
3019
+ "grad_norm": 0.07576307654380798,
3020
+ "learning_rate": 1.1001238661681657e-05,
3021
+ "loss": 2.4082,
3022
+ "step": 427
3023
+ },
3024
+ {
3025
+ "epoch": 0.8530144494270054,
3026
+ "grad_norm": 0.08715996891260147,
3027
+ "learning_rate": 1.07113071724675e-05,
3028
+ "loss": 2.4999,
3029
+ "step": 428
3030
+ },
3031
+ {
3032
+ "epoch": 0.8550074738415545,
3033
+ "grad_norm": 0.09236744791269302,
3034
+ "learning_rate": 1.0425031056631007e-05,
3035
+ "loss": 2.4637,
3036
+ "step": 429
3037
+ },
3038
+ {
3039
+ "epoch": 0.8570004982561036,
3040
+ "grad_norm": 0.07726194709539413,
3041
+ "learning_rate": 1.0142422033977505e-05,
3042
+ "loss": 2.4252,
3043
+ "step": 430
3044
+ },
3045
+ {
3046
+ "epoch": 0.8589935226706528,
3047
+ "grad_norm": 0.08456709235906601,
3048
+ "learning_rate": 9.863491674185776e-06,
3049
+ "loss": 2.3925,
3050
+ "step": 431
3051
+ },
3052
+ {
3053
+ "epoch": 0.8609865470852018,
3054
+ "grad_norm": 0.08284948766231537,
3055
+ "learning_rate": 9.588251396334524e-06,
3056
+ "loss": 2.2566,
3057
+ "step": 432
3058
+ },
3059
+ {
3060
+ "epoch": 0.8629795714997509,
3061
+ "grad_norm": 0.09571260958909988,
3062
+ "learning_rate": 9.316712468434874e-06,
3063
+ "loss": 2.3975,
3064
+ "step": 433
3065
+ },
3066
+ {
3067
+ "epoch": 0.8649725959143,
3068
+ "grad_norm": 0.08725487440824509,
3069
+ "learning_rate": 9.048886006969093e-06,
3070
+ "loss": 2.4255,
3071
+ "step": 434
3072
+ },
3073
+ {
3074
+ "epoch": 0.866965620328849,
3075
+ "grad_norm": 0.07475867122411728,
3076
+ "learning_rate": 8.784782976435424e-06,
3077
+ "loss": 2.4703,
3078
+ "step": 435
3079
+ },
3080
+ {
3081
+ "epoch": 0.8689586447433981,
3082
+ "grad_norm": 0.07269957661628723,
3083
+ "learning_rate": 8.524414188899266e-06,
3084
+ "loss": 2.3915,
3085
+ "step": 436
3086
+ },
3087
+ {
3088
+ "epoch": 0.8709516691579472,
3089
+ "grad_norm": 0.07792806625366211,
3090
+ "learning_rate": 8.267790303550526e-06,
3091
+ "loss": 2.5082,
3092
+ "step": 437
3093
+ },
3094
+ {
3095
+ "epoch": 0.8729446935724963,
3096
+ "grad_norm": 0.07521213591098785,
3097
+ "learning_rate": 8.014921826267285e-06,
3098
+ "loss": 2.3379,
3099
+ "step": 438
3100
+ },
3101
+ {
3102
+ "epoch": 0.8749377179870453,
3103
+ "grad_norm": 0.07535220682621002,
3104
+ "learning_rate": 7.765819109185635e-06,
3105
+ "loss": 2.3369,
3106
+ "step": 439
3107
+ },
3108
+ {
3109
+ "epoch": 0.8769307424015944,
3110
+ "grad_norm": 0.09499151259660721,
3111
+ "learning_rate": 7.520492350275876e-06,
3112
+ "loss": 2.4126,
3113
+ "step": 440
3114
+ },
3115
+ {
3116
+ "epoch": 0.8789237668161435,
3117
+ "grad_norm": 0.08234364539384842,
3118
+ "learning_rate": 7.278951592925154e-06,
3119
+ "loss": 2.394,
3120
+ "step": 441
3121
+ },
3122
+ {
3123
+ "epoch": 0.8809167912306926,
3124
+ "grad_norm": 0.07767913490533829,
3125
+ "learning_rate": 7.041206725526028e-06,
3126
+ "loss": 2.4593,
3127
+ "step": 442
3128
+ },
3129
+ {
3130
+ "epoch": 0.8829098156452416,
3131
+ "grad_norm": 0.08887754380702972,
3132
+ "learning_rate": 6.807267481071966e-06,
3133
+ "loss": 2.308,
3134
+ "step": 443
3135
+ },
3136
+ {
3137
+ "epoch": 0.8849028400597907,
3138
+ "grad_norm": 0.07949234545230865,
3139
+ "learning_rate": 6.577143436758659e-06,
3140
+ "loss": 2.3729,
3141
+ "step": 444
3142
+ },
3143
+ {
3144
+ "epoch": 0.8868958644743398,
3145
+ "grad_norm": 0.09185628592967987,
3146
+ "learning_rate": 6.350844013592061e-06,
3147
+ "loss": 2.3265,
3148
+ "step": 445
3149
+ },
3150
+ {
3151
+ "epoch": 0.8888888888888888,
3152
+ "grad_norm": 0.09360305219888687,
3153
+ "learning_rate": 6.1283784760026494e-06,
3154
+ "loss": 2.3192,
3155
+ "step": 446
3156
+ },
3157
+ {
3158
+ "epoch": 0.890881913303438,
3159
+ "grad_norm": 0.09174556285142899,
3160
+ "learning_rate": 5.9097559314661214e-06,
3161
+ "loss": 2.3377,
3162
+ "step": 447
3163
+ },
3164
+ {
3165
+ "epoch": 0.8928749377179871,
3166
+ "grad_norm": 0.08584918826818466,
3167
+ "learning_rate": 5.694985330130698e-06,
3168
+ "loss": 2.339,
3169
+ "step": 448
3170
+ },
3171
+ {
3172
+ "epoch": 0.8948679621325362,
3173
+ "grad_norm": 0.0800124853849411,
3174
+ "learning_rate": 5.484075464450455e-06,
3175
+ "loss": 2.2795,
3176
+ "step": 449
3177
+ },
3178
+ {
3179
+ "epoch": 0.8968609865470852,
3180
+ "grad_norm": 0.07980230450630188,
3181
+ "learning_rate": 5.277034968825667e-06,
3182
+ "loss": 2.4143,
3183
+ "step": 450
3184
+ },
3185
+ {
3186
+ "epoch": 0.8988540109616343,
3187
+ "grad_norm": 0.08572199940681458,
3188
+ "learning_rate": 5.073872319249073e-06,
3189
+ "loss": 2.3389,
3190
+ "step": 451
3191
+ },
3192
+ {
3193
+ "epoch": 0.9008470353761834,
3194
+ "grad_norm": 0.079259492456913,
3195
+ "learning_rate": 4.8745958329590615e-06,
3196
+ "loss": 2.5576,
3197
+ "step": 452
3198
+ },
3199
+ {
3200
+ "epoch": 0.9028400597907325,
3201
+ "grad_norm": 0.08473755419254303,
3202
+ "learning_rate": 4.679213668099036e-06,
3203
+ "loss": 2.2563,
3204
+ "step": 453
3205
+ },
3206
+ {
3207
+ "epoch": 0.9048330842052815,
3208
+ "grad_norm": 0.07899723201990128,
3209
+ "learning_rate": 4.487733823383522e-06,
3210
+ "loss": 2.3936,
3211
+ "step": 454
3212
+ },
3213
+ {
3214
+ "epoch": 0.9068261086198306,
3215
+ "grad_norm": 0.09196992218494415,
3216
+ "learning_rate": 4.3001641377707125e-06,
3217
+ "loss": 2.4257,
3218
+ "step": 455
3219
+ },
3220
+ {
3221
+ "epoch": 0.9088191330343797,
3222
+ "grad_norm": 0.0749785453081131,
3223
+ "learning_rate": 4.116512290141405e-06,
3224
+ "loss": 2.2589,
3225
+ "step": 456
3226
+ },
3227
+ {
3228
+ "epoch": 0.9108121574489287,
3229
+ "grad_norm": 0.07740684598684311,
3230
+ "learning_rate": 3.936785798984877e-06,
3231
+ "loss": 2.3823,
3232
+ "step": 457
3233
+ },
3234
+ {
3235
+ "epoch": 0.9128051818634778,
3236
+ "grad_norm": 0.07983781397342682,
3237
+ "learning_rate": 3.7609920220908813e-06,
3238
+ "loss": 2.3314,
3239
+ "step": 458
3240
+ },
3241
+ {
3242
+ "epoch": 0.9147982062780269,
3243
+ "grad_norm": 0.07211541384458542,
3244
+ "learning_rate": 3.5891381562485504e-06,
3245
+ "loss": 2.3273,
3246
+ "step": 459
3247
+ },
3248
+ {
3249
+ "epoch": 0.916791230692576,
3250
+ "grad_norm": 0.07012934237718582,
3251
+ "learning_rate": 3.4212312369516497e-06,
3252
+ "loss": 2.4765,
3253
+ "step": 460
3254
+ },
3255
+ {
3256
+ "epoch": 0.918784255107125,
3257
+ "grad_norm": 0.07496382296085358,
3258
+ "learning_rate": 3.2572781381107197e-06,
3259
+ "loss": 2.4434,
3260
+ "step": 461
3261
+ },
3262
+ {
3263
+ "epoch": 0.9207772795216741,
3264
+ "grad_norm": 0.07562927901744843,
3265
+ "learning_rate": 3.0972855717715134e-06,
3266
+ "loss": 2.4841,
3267
+ "step": 462
3268
+ },
3269
+ {
3270
+ "epoch": 0.9227703039362232,
3271
+ "grad_norm": 0.08719190210103989,
3272
+ "learning_rate": 2.9412600878402697e-06,
3273
+ "loss": 2.4404,
3274
+ "step": 463
3275
+ },
3276
+ {
3277
+ "epoch": 0.9247633283507724,
3278
+ "grad_norm": 0.06846871227025986,
3279
+ "learning_rate": 2.789208073815608e-06,
3280
+ "loss": 2.3661,
3281
+ "step": 464
3282
+ },
3283
+ {
3284
+ "epoch": 0.9267563527653214,
3285
+ "grad_norm": 0.08408292382955551,
3286
+ "learning_rate": 2.6411357545269577e-06,
3287
+ "loss": 2.4225,
3288
+ "step": 465
3289
+ },
3290
+ {
3291
+ "epoch": 0.9287493771798705,
3292
+ "grad_norm": 0.0859316885471344,
3293
+ "learning_rate": 2.4970491918797854e-06,
3294
+ "loss": 2.35,
3295
+ "step": 466
3296
+ },
3297
+ {
3298
+ "epoch": 0.9307424015944196,
3299
+ "grad_norm": 0.08102748543024063,
3300
+ "learning_rate": 2.35695428460736e-06,
3301
+ "loss": 2.4138,
3302
+ "step": 467
3303
+ },
3304
+ {
3305
+ "epoch": 0.9327354260089686,
3306
+ "grad_norm": 0.09345877170562744,
3307
+ "learning_rate": 2.2208567680293667e-06,
3308
+ "loss": 2.4157,
3309
+ "step": 468
3310
+ },
3311
+ {
3312
+ "epoch": 0.9347284504235177,
3313
+ "grad_norm": 0.09558593481779099,
3314
+ "learning_rate": 2.088762213816986e-06,
3315
+ "loss": 2.2846,
3316
+ "step": 469
3317
+ },
3318
+ {
3319
+ "epoch": 0.9367214748380668,
3320
+ "grad_norm": 0.07203153520822525,
3321
+ "learning_rate": 1.960676029764874e-06,
3322
+ "loss": 2.293,
3323
+ "step": 470
3324
+ },
3325
+ {
3326
+ "epoch": 0.9387144992526159,
3327
+ "grad_norm": 0.07482384145259857,
3328
+ "learning_rate": 1.8366034595698078e-06,
3329
+ "loss": 2.5189,
3330
+ "step": 471
3331
+ },
3332
+ {
3333
+ "epoch": 0.9407075236671649,
3334
+ "grad_norm": 0.07780031859874725,
3335
+ "learning_rate": 1.7165495826158896e-06,
3336
+ "loss": 2.3622,
3337
+ "step": 472
3338
+ },
3339
+ {
3340
+ "epoch": 0.942700548081714,
3341
+ "grad_norm": 0.08634981513023376,
3342
+ "learning_rate": 1.600519313766724e-06,
3343
+ "loss": 2.3279,
3344
+ "step": 473
3345
+ },
3346
+ {
3347
+ "epoch": 0.9446935724962631,
3348
+ "grad_norm": 0.09694086015224457,
3349
+ "learning_rate": 1.4885174031641469e-06,
3350
+ "loss": 2.4172,
3351
+ "step": 474
3352
+ },
3353
+ {
3354
+ "epoch": 0.9466865969108121,
3355
+ "grad_norm": 0.0686231181025505,
3356
+ "learning_rate": 1.3805484360337906e-06,
3357
+ "loss": 2.3377,
3358
+ "step": 475
3359
+ },
3360
+ {
3361
+ "epoch": 0.9486796213253612,
3362
+ "grad_norm": 0.07658665627241135,
3363
+ "learning_rate": 1.276616832497346e-06,
3364
+ "loss": 2.3592,
3365
+ "step": 476
3366
+ },
3367
+ {
3368
+ "epoch": 0.9506726457399103,
3369
+ "grad_norm": 0.0743999257683754,
3370
+ "learning_rate": 1.1767268473916182e-06,
3371
+ "loss": 2.4892,
3372
+ "step": 477
3373
+ },
3374
+ {
3375
+ "epoch": 0.9526656701544594,
3376
+ "grad_norm": 0.08805029094219208,
3377
+ "learning_rate": 1.0808825700943438e-06,
3378
+ "loss": 2.4991,
3379
+ "step": 478
3380
+ },
3381
+ {
3382
+ "epoch": 0.9546586945690084,
3383
+ "grad_norm": 0.09332336485385895,
3384
+ "learning_rate": 9.890879243567686e-07,
3385
+ "loss": 2.4089,
3386
+ "step": 479
3387
+ },
3388
+ {
3389
+ "epoch": 0.9566517189835575,
3390
+ "grad_norm": 0.0877373144030571,
3391
+ "learning_rate": 9.013466681429994e-07,
3392
+ "loss": 2.3899,
3393
+ "step": 480
3394
+ },
3395
+ {
3396
+ "epoch": 0.9586447433981067,
3397
+ "grad_norm": 0.07606255263090134,
3398
+ "learning_rate": 8.17662393476204e-07,
3399
+ "loss": 2.3917,
3400
+ "step": 481
3401
+ },
3402
+ {
3403
+ "epoch": 0.9606377678126558,
3404
+ "grad_norm": 0.07790535688400269,
3405
+ "learning_rate": 7.380385262915179e-07,
3406
+ "loss": 2.3676,
3407
+ "step": 482
3408
+ },
3409
+ {
3410
+ "epoch": 0.9626307922272048,
3411
+ "grad_norm": 0.07609371840953827,
3412
+ "learning_rate": 6.624783262958012e-07,
3413
+ "loss": 2.4131,
3414
+ "step": 483
3415
+ },
3416
+ {
3417
+ "epoch": 0.9646238166417539,
3418
+ "grad_norm": 0.08657480031251907,
3419
+ "learning_rate": 5.909848868341783e-07,
3420
+ "loss": 2.3388,
3421
+ "step": 484
3422
+ },
3423
+ {
3424
+ "epoch": 0.966616841056303,
3425
+ "grad_norm": 0.07786071300506592,
3426
+ "learning_rate": 5.235611347634172e-07,
3427
+ "loss": 2.426,
3428
+ "step": 485
3429
+ },
3430
+ {
3431
+ "epoch": 0.968609865470852,
3432
+ "grad_norm": 0.08031103760004044,
3433
+ "learning_rate": 4.602098303321256e-07,
3434
+ "loss": 2.3265,
3435
+ "step": 486
3436
+ },
3437
+ {
3438
+ "epoch": 0.9706028898854011,
3439
+ "grad_norm": 0.08088498562574387,
3440
+ "learning_rate": 4.00933567067685e-07,
3441
+ "loss": 2.4426,
3442
+ "step": 487
3443
+ },
3444
+ {
3445
+ "epoch": 0.9725959142999502,
3446
+ "grad_norm": 0.08056242018938065,
3447
+ "learning_rate": 3.4573477167015866e-07,
3448
+ "loss": 2.3804,
3449
+ "step": 488
3450
+ },
3451
+ {
3452
+ "epoch": 0.9745889387144993,
3453
+ "grad_norm": 0.09492980688810349,
3454
+ "learning_rate": 2.9461570391287055e-07,
3455
+ "loss": 2.3571,
3456
+ "step": 489
3457
+ },
3458
+ {
3459
+ "epoch": 0.9765819631290483,
3460
+ "grad_norm": 0.08370451629161835,
3461
+ "learning_rate": 2.4757845654992397e-07,
3462
+ "loss": 2.39,
3463
+ "step": 490
3464
+ },
3465
+ {
3466
+ "epoch": 0.9785749875435974,
3467
+ "grad_norm": 0.08111421018838882,
3468
+ "learning_rate": 2.0462495523057011e-07,
3469
+ "loss": 2.3549,
3470
+ "step": 491
3471
+ },
3472
+ {
3473
+ "epoch": 0.9805680119581465,
3474
+ "grad_norm": 0.07262679189443588,
3475
+ "learning_rate": 1.6575695842027117e-07,
3476
+ "loss": 2.3554,
3477
+ "step": 492
3478
+ },
3479
+ {
3480
+ "epoch": 0.9825610363726955,
3481
+ "grad_norm": 0.08637802302837372,
3482
+ "learning_rate": 1.3097605732882435e-07,
3483
+ "loss": 2.529,
3484
+ "step": 493
3485
+ },
3486
+ {
3487
+ "epoch": 0.9845540607872446,
3488
+ "grad_norm": 0.07385995984077454,
3489
+ "learning_rate": 1.0028367584512532e-07,
3490
+ "loss": 2.4134,
3491
+ "step": 494
3492
+ },
3493
+ {
3494
+ "epoch": 0.9865470852017937,
3495
+ "grad_norm": 0.07876549661159515,
3496
+ "learning_rate": 7.368107047894812e-08,
3497
+ "loss": 2.3922,
3498
+ "step": 495
3499
+ },
3500
+ {
3501
+ "epoch": 0.9885401096163428,
3502
+ "grad_norm": 0.08003538101911545,
3503
+ "learning_rate": 5.116933030946402e-08,
3504
+ "loss": 2.3405,
3505
+ "step": 496
3506
+ },
3507
+ {
3508
+ "epoch": 0.9905331340308918,
3509
+ "grad_norm": 0.07788538187742233,
3510
+ "learning_rate": 3.2749376940655054e-08,
3511
+ "loss": 2.4301,
3512
+ "step": 497
3513
+ },
3514
+ {
3515
+ "epoch": 0.992526158445441,
3516
+ "grad_norm": 0.08138438314199448,
3517
+ "learning_rate": 1.8421964463610774e-08,
3518
+ "loss": 2.2946,
3519
+ "step": 498
3520
+ },
3521
+ {
3522
+ "epoch": 0.9945191828599901,
3523
+ "grad_norm": 0.0711507648229599,
3524
+ "learning_rate": 8.187679425630812e-09,
3525
+ "loss": 2.4029,
3526
+ "step": 499
3527
+ },
3528
+ {
3529
+ "epoch": 0.9965122072745392,
3530
+ "grad_norm": 0.0825885534286499,
3531
+ "learning_rate": 2.046940806244013e-09,
3532
+ "loss": 2.4437,
3533
+ "step": 500
3534
+ },
3535
+ {
3536
+ "epoch": 0.9985052316890882,
3537
+ "grad_norm": 0.0885770171880722,
3538
+ "learning_rate": 0.0,
3539
+ "loss": 2.3519,
3540
+ "step": 501
3541
+ },
3542
+ {
3543
+ "epoch": 0.9985052316890882,
3544
+ "eval_loss": 2.3817989826202393,
3545
+ "eval_runtime": 41.8036,
3546
+ "eval_samples_per_second": 20.214,
3547
+ "eval_steps_per_second": 2.536,
3548
+ "step": 501
3549
+ }
3550
+ ],
3551
+ "logging_steps": 1,
3552
+ "max_steps": 501,
3553
+ "num_input_tokens_seen": 0,
3554
+ "num_train_epochs": 1,
3555
+ "save_steps": 500,
3556
+ "stateful_callbacks": {
3557
+ "TrainerControl": {
3558
+ "args": {
3559
+ "should_epoch_stop": false,
3560
+ "should_evaluate": false,
3561
+ "should_log": false,
3562
+ "should_save": true,
3563
+ "should_training_stop": true
3564
+ },
3565
+ "attributes": {}
3566
+ }
3567
+ },
3568
+ "total_flos": 2.712289814815703e+17,
3569
+ "train_batch_size": 2,
3570
+ "trial_name": null,
3571
+ "trial_params": null
3572
+ }
checkpoint-501/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a92eb83c0ee92247610a68776b23269c9412e6ec65632733c9393c8082a4d7
3
+ size 6200
checkpoint-501/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merged/added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|PAD_TOKEN|>": 151665,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
merged/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Qwen2.5-Coder-7B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 28,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 4,
18
+ "pad_token_id": 151665,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.42.3",
25
+ "unsloth_fixed": true,
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
merged/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_length": 32768,
6
+ "max_new_tokens": 2048,
7
+ "pad_token_id": 151665,
8
+ "transformers_version": "4.42.3"
9
+ }
merged/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
merged/pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a593b6f56a935b7aca892cd266a7d9f929cade43680084dfd69cdf9113e7175a
3
+ size 4877684182
merged/pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e574f6de500409890c6a0351f24fbf4dfd05ac0318fe000cc99aa10e9bbf808d
3
+ size 4932778600
merged/pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a789a0e694af82c27e9c8e92f875b231a41dca24a85e2e429f840dd77bc90794
3
+ size 4330890394
merged/pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd68d987354aed98165e625e6aea7ac7e24fd37f36fff0917f7b836b74fee943
3
+ size 1089996165
merged/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
27
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
28
+ "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
29
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
30
+ "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
31
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
32
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
33
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
34
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
104
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
105
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
106
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
107
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
108
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
109
+ "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
110
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
111
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
112
+ "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
113
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
114
+ "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
115
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
116
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
117
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
118
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
119
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
120
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
121
+ "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
122
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
123
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
124
+ "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
125
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
126
+ "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
127
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
129
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
131
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
132
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
133
+ "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
134
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
135
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
136
+ "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
137
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
138
+ "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
139
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
140
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
142
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
143
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
145
+ "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
149
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
153
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
154
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
155
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
156
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
157
+ "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
158
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
159
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
160
+ "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
161
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
162
+ "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
163
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
164
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
170
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
171
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
212
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
216
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
217
+ "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
218
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
219
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
220
+ "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
221
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
222
+ "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
223
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
224
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
234
+ "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
235
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
238
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
239
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
240
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
241
+ "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
242
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
243
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
244
+ "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
245
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
246
+ "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
247
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
248
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
249
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
250
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
251
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
252
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
253
+ "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
254
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
255
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
256
+ "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
257
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
258
+ "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
259
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
260
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
261
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
262
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
263
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
264
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
265
+ "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
266
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
267
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
268
+ "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
269
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
270
+ "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
271
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
272
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
273
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
274
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
275
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
277
+ "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
278
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
279
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
280
+ "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
281
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
282
+ "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
283
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
284
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
285
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
286
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
287
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
288
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
289
+ "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
290
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
291
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
292
+ "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
293
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
294
+ "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
295
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
296
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
297
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
298
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
299
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
300
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
301
+ "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
302
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
303
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
304
+ "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
305
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
306
+ "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
307
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
308
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
309
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
310
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
311
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
312
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
313
+ "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
314
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
315
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
316
+ "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
317
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
318
+ "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
319
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
320
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
321
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
322
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
323
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
324
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
325
+ "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
326
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
327
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
328
+ "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
329
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
330
+ "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
331
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
332
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
333
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
334
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
335
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
336
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
337
+ "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
338
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
339
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
340
+ "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
341
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
342
+ "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
343
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
344
+ "model.norm.weight": "pytorch_model-00003-of-00004.bin"
345
+ }
346
+ }
merged/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|PAD_TOKEN|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
merged/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
merged/tokenizer_config.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|PAD_TOKEN|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
+ ],
205
+ "bos_token": null,
206
+ "clean_up_tokenization_spaces": false,
207
+ "eos_token": "<|endoftext|>",
208
+ "errors": "replace",
209
+ "model_max_length": 131072,
210
+ "pad_token": "<|PAD_TOKEN|>",
211
+ "padding_side": "left",
212
+ "split_special_tokens": false,
213
+ "tokenizer_class": "Qwen2Tokenizer",
214
+ "unk_token": null
215
+ }
merged/vocab.json ADDED
The diff for this file is too large to render. See raw diff