xiaosena commited on
Commit
0681559
·
verified ·
1 Parent(s): 7a026f3

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. README.md +65 -3
  3. added_tokens.json +24 -0
  4. all_results.json +12 -0
  5. checkpoint-1000/added_tokens.json +24 -0
  6. checkpoint-1000/config.json +29 -0
  7. checkpoint-1000/generation_config.json +14 -0
  8. checkpoint-1000/merges.txt +0 -0
  9. checkpoint-1000/model.safetensors +3 -0
  10. checkpoint-1000/optimizer.pt +3 -0
  11. checkpoint-1000/rng_state.pth +3 -0
  12. checkpoint-1000/scheduler.pt +3 -0
  13. checkpoint-1000/special_tokens_map.json +31 -0
  14. checkpoint-1000/tokenizer.json +3 -0
  15. checkpoint-1000/tokenizer_config.json +208 -0
  16. checkpoint-1000/trainer_state.json +749 -0
  17. checkpoint-1000/training_args.bin +3 -0
  18. checkpoint-1000/vocab.json +0 -0
  19. checkpoint-1350/added_tokens.json +24 -0
  20. checkpoint-1350/config.json +29 -0
  21. checkpoint-1350/generation_config.json +14 -0
  22. checkpoint-1350/merges.txt +0 -0
  23. checkpoint-1350/model.safetensors +3 -0
  24. checkpoint-1350/optimizer.pt +3 -0
  25. checkpoint-1350/rng_state.pth +3 -0
  26. checkpoint-1350/scheduler.pt +3 -0
  27. checkpoint-1350/special_tokens_map.json +31 -0
  28. checkpoint-1350/tokenizer.json +3 -0
  29. checkpoint-1350/tokenizer_config.json +208 -0
  30. checkpoint-1350/trainer_state.json +994 -0
  31. checkpoint-1350/training_args.bin +3 -0
  32. checkpoint-1350/vocab.json +0 -0
  33. checkpoint-500/added_tokens.json +24 -0
  34. checkpoint-500/config.json +29 -0
  35. checkpoint-500/generation_config.json +14 -0
  36. checkpoint-500/merges.txt +0 -0
  37. checkpoint-500/model.safetensors +3 -0
  38. checkpoint-500/optimizer.pt +3 -0
  39. checkpoint-500/rng_state.pth +3 -0
  40. checkpoint-500/scheduler.pt +3 -0
  41. checkpoint-500/special_tokens_map.json +31 -0
  42. checkpoint-500/tokenizer.json +3 -0
  43. checkpoint-500/tokenizer_config.json +208 -0
  44. checkpoint-500/trainer_state.json +391 -0
  45. checkpoint-500/training_args.bin +3 -0
  46. checkpoint-500/vocab.json +0 -0
  47. config.json +29 -0
  48. eval_results.json +7 -0
  49. generation_config.json +14 -0
  50. merges.txt +0 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-1350/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,65 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ librar_yname: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-1.5B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - freeze
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: output
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # output
18
+
19
+ This model is a fine-tuned version of [/home/Qwen/Qwen2___5-1___5B-Instruct](https://huggingface.co//home/Qwen/Qwen2___5-1___5B-Instruct) on the alpaca_zh_demo dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.9959
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 2
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 3.0
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 1.0102 | 1.1111 | 500 | 1.7723 |
57
+ | 0.5375 | 2.2222 | 1000 | 1.9768 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.46.1
63
+ - Pytorch 2.3.0+cu121
64
+ - Datasets 3.0.2
65
+ - Tokenizers 0.20.3
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.9959301948547363,
4
+ "eval_runtime": 4.3369,
5
+ "eval_samples_per_second": 23.058,
6
+ "eval_steps_per_second": 23.058,
7
+ "total_flos": 3120728157462528.0,
8
+ "train_loss": 1.0846350595686172,
9
+ "train_runtime": 255.809,
10
+ "train_samples_per_second": 10.555,
11
+ "train_steps_per_second": 5.277
12
+ }
checkpoint-1000/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-1000/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/Qwen/Qwen2___5-1___5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151936
29
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
checkpoint-1000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdd584a02c6a00dbfb1223eb2872e815d578f47777fff14529e8f78ad3f3a2a
3
+ size 3274658144
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e345f5bf24557797185b34e06f305708d8b60a5bb3afe728400b5b5e4662830
3
+ size 748785878
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aa6ed279c268865bfc83dcdeae41c4635536d448c1bd86db50ae0a78dcce16b
3
+ size 1064
checkpoint-1000/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": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-1000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,749 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.2222222222222223,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.022222222222222223,
13
+ "grad_norm": 6.603886604309082,
14
+ "learning_rate": 7.4074074074074075e-06,
15
+ "loss": 1.7454,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.044444444444444446,
20
+ "grad_norm": 4.177036285400391,
21
+ "learning_rate": 1.4814814814814815e-05,
22
+ "loss": 1.5071,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06666666666666667,
27
+ "grad_norm": 6.5375285148620605,
28
+ "learning_rate": 2.2222222222222223e-05,
29
+ "loss": 1.6012,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08888888888888889,
34
+ "grad_norm": 2.4201414585113525,
35
+ "learning_rate": 2.8888888888888888e-05,
36
+ "loss": 1.543,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.1111111111111111,
41
+ "grad_norm": 8.420122146606445,
42
+ "learning_rate": 3.62962962962963e-05,
43
+ "loss": 1.6806,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13333333333333333,
48
+ "grad_norm": 2.9238393306732178,
49
+ "learning_rate": 4.3703703703703705e-05,
50
+ "loss": 1.4376,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15555555555555556,
55
+ "grad_norm": 4.334264278411865,
56
+ "learning_rate": 5.111111111111111e-05,
57
+ "loss": 1.5629,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.17777777777777778,
62
+ "grad_norm": 4.047328472137451,
63
+ "learning_rate": 5.851851851851852e-05,
64
+ "loss": 1.5502,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.2,
69
+ "grad_norm": 6.695739269256592,
70
+ "learning_rate": 6.592592592592593e-05,
71
+ "loss": 1.5744,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2222222222222222,
76
+ "grad_norm": 2.579887628555298,
77
+ "learning_rate": 7.333333333333333e-05,
78
+ "loss": 1.4887,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.24444444444444444,
83
+ "grad_norm": 8.655933380126953,
84
+ "learning_rate": 8.074074074074075e-05,
85
+ "loss": 1.4432,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.26666666666666666,
90
+ "grad_norm": 2.3287596702575684,
91
+ "learning_rate": 8.814814814814815e-05,
92
+ "loss": 1.7349,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.28888888888888886,
97
+ "grad_norm": 3.626464366912842,
98
+ "learning_rate": 9.555555555555557e-05,
99
+ "loss": 1.8419,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3111111111111111,
104
+ "grad_norm": 13.17669677734375,
105
+ "learning_rate": 9.999732574196451e-05,
106
+ "loss": 1.7434,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3333333333333333,
111
+ "grad_norm": 2.938781261444092,
112
+ "learning_rate": 9.996724362426075e-05,
113
+ "loss": 1.7345,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.35555555555555557,
118
+ "grad_norm": 3.3643951416015625,
119
+ "learning_rate": 9.990375674425109e-05,
120
+ "loss": 1.6652,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.37777777777777777,
125
+ "grad_norm": 4.0528178215026855,
126
+ "learning_rate": 9.980690754502393e-05,
127
+ "loss": 1.6247,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4,
132
+ "grad_norm": 3.2510921955108643,
133
+ "learning_rate": 9.96767607734863e-05,
134
+ "loss": 1.9226,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4222222222222222,
139
+ "grad_norm": 3.1616647243499756,
140
+ "learning_rate": 9.951340343707852e-05,
141
+ "loss": 1.9507,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4444444444444444,
146
+ "grad_norm": 2.816512107849121,
147
+ "learning_rate": 9.931694474560686e-05,
148
+ "loss": 1.5901,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4666666666666667,
153
+ "grad_norm": 3.0883939266204834,
154
+ "learning_rate": 9.908751603823301e-05,
155
+ "loss": 1.7762,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4888888888888889,
160
+ "grad_norm": 3.496539354324341,
161
+ "learning_rate": 9.882527069566965e-05,
162
+ "loss": 1.7833,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5111111111111111,
167
+ "grad_norm": 3.6071531772613525,
168
+ "learning_rate": 9.853038403764021e-05,
169
+ "loss": 1.5891,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5333333333333333,
174
+ "grad_norm": 3.1297965049743652,
175
+ "learning_rate": 9.820305320567192e-05,
176
+ "loss": 1.7261,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5555555555555556,
181
+ "grad_norm": 2.707146167755127,
182
+ "learning_rate": 9.784349703130007e-05,
183
+ "loss": 1.6448,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5777777777777777,
188
+ "grad_norm": 3.1915082931518555,
189
+ "learning_rate": 9.745195588977192e-05,
190
+ "loss": 1.9097,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6,
195
+ "grad_norm": 2.056610584259033,
196
+ "learning_rate": 9.702869153934782e-05,
197
+ "loss": 1.6173,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6222222222222222,
202
+ "grad_norm": 3.044048309326172,
203
+ "learning_rate": 9.657398694630712e-05,
204
+ "loss": 1.8324,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6444444444444445,
209
+ "grad_norm": 3.3219234943389893,
210
+ "learning_rate": 9.608814609577585e-05,
211
+ "loss": 1.818,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6666666666666666,
216
+ "grad_norm": 2.5632572174072266,
217
+ "learning_rate": 9.557149378850254e-05,
218
+ "loss": 1.618,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6888888888888889,
223
+ "grad_norm": 2.3387904167175293,
224
+ "learning_rate": 9.502437542371812e-05,
225
+ "loss": 1.6228,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7111111111111111,
230
+ "grad_norm": 2.6883046627044678,
231
+ "learning_rate": 9.444715676822501e-05,
232
+ "loss": 1.7307,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7333333333333333,
237
+ "grad_norm": 2.9449591636657715,
238
+ "learning_rate": 9.384022371187003e-05,
239
+ "loss": 1.7338,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7555555555555555,
244
+ "grad_norm": 2.4884233474731445,
245
+ "learning_rate": 9.320398200956403e-05,
246
+ "loss": 1.4941,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7777777777777778,
251
+ "grad_norm": 5.446136951446533,
252
+ "learning_rate": 9.253885701002134e-05,
253
+ "loss": 1.9377,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8,
258
+ "grad_norm": 3.122303009033203,
259
+ "learning_rate": 9.184529337140002e-05,
260
+ "loss": 1.5295,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8222222222222222,
265
+ "grad_norm": 3.4902145862579346,
266
+ "learning_rate": 9.112375476403312e-05,
267
+ "loss": 1.688,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8444444444444444,
272
+ "grad_norm": 3.041170597076416,
273
+ "learning_rate": 9.037472356044962e-05,
274
+ "loss": 1.7526,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8666666666666667,
279
+ "grad_norm": 2.029374837875366,
280
+ "learning_rate": 8.959870051289241e-05,
281
+ "loss": 1.5125,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8888888888888888,
286
+ "grad_norm": 4.354530334472656,
287
+ "learning_rate": 8.879620441854872e-05,
288
+ "loss": 1.6507,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9111111111111111,
293
+ "grad_norm": 3.2502028942108154,
294
+ "learning_rate": 8.796777177271708e-05,
295
+ "loss": 1.6118,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9333333333333333,
300
+ "grad_norm": 2.198453903198242,
301
+ "learning_rate": 8.711395641014228e-05,
302
+ "loss": 1.6589,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9555555555555556,
307
+ "grad_norm": 3.6842291355133057,
308
+ "learning_rate": 8.623532913475847e-05,
309
+ "loss": 1.6891,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9777777777777777,
314
+ "grad_norm": 2.3169732093811035,
315
+ "learning_rate": 8.533247733808776e-05,
316
+ "loss": 1.5275,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.0,
321
+ "grad_norm": 5.430471897125244,
322
+ "learning_rate": 8.440600460654958e-05,
323
+ "loss": 1.7984,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 1.0222222222222221,
328
+ "grad_norm": 4.782519817352295,
329
+ "learning_rate": 8.345653031794292e-05,
330
+ "loss": 0.9174,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.0444444444444445,
335
+ "grad_norm": 3.547177314758301,
336
+ "learning_rate": 8.248468922737188e-05,
337
+ "loss": 1.3878,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 1.0666666666666667,
342
+ "grad_norm": 2.446197748184204,
343
+ "learning_rate": 8.149113104289063e-05,
344
+ "loss": 1.1277,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.0888888888888888,
349
+ "grad_norm": 3.3164918422698975,
350
+ "learning_rate": 8.047651999115217e-05,
351
+ "loss": 1.0124,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.1111111111111112,
356
+ "grad_norm": 7.3411359786987305,
357
+ "learning_rate": 7.944153437335057e-05,
358
+ "loss": 1.0102,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.1111111111111112,
363
+ "eval_loss": 1.7722898721694946,
364
+ "eval_runtime": 4.268,
365
+ "eval_samples_per_second": 23.43,
366
+ "eval_steps_per_second": 23.43,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.1333333333333333,
371
+ "grad_norm": 3.1477370262145996,
372
+ "learning_rate": 7.838686611175421e-05,
373
+ "loss": 1.1386,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1555555555555554,
378
+ "grad_norm": 3.3324782848358154,
379
+ "learning_rate": 7.73132202871327e-05,
380
+ "loss": 1.0376,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1777777777777778,
385
+ "grad_norm": 4.7969136238098145,
386
+ "learning_rate": 7.6221314667387e-05,
387
+ "loss": 1.2585,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2,
392
+ "grad_norm": 3.488189697265625,
393
+ "learning_rate": 7.511187922769768e-05,
394
+ "loss": 1.2203,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2222222222222223,
399
+ "grad_norm": 3.5396199226379395,
400
+ "learning_rate": 7.398565566251232e-05,
401
+ "loss": 1.1651,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2444444444444445,
406
+ "grad_norm": 4.660005569458008,
407
+ "learning_rate": 7.284339688969809e-05,
408
+ "loss": 1.1229,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2666666666666666,
413
+ "grad_norm": 6.269535541534424,
414
+ "learning_rate": 7.168586654719117e-05,
415
+ "loss": 1.1348,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2888888888888888,
420
+ "grad_norm": 5.864573955535889,
421
+ "learning_rate": 7.051383848247942e-05,
422
+ "loss": 1.1637,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3111111111111111,
427
+ "grad_norm": 3.3166041374206543,
428
+ "learning_rate": 6.944726507547169e-05,
429
+ "loss": 1.0358,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.3333333333333333,
434
+ "grad_norm": 4.742485523223877,
435
+ "learning_rate": 6.824985757903016e-05,
436
+ "loss": 1.0499,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3555555555555556,
441
+ "grad_norm": 2.5902740955352783,
442
+ "learning_rate": 6.704024944652537e-05,
443
+ "loss": 0.9614,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3777777777777778,
448
+ "grad_norm": 4.31684684753418,
449
+ "learning_rate": 6.581924934117782e-05,
450
+ "loss": 1.2387,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.4,
455
+ "grad_norm": 6.753187656402588,
456
+ "learning_rate": 6.458767354212036e-05,
457
+ "loss": 0.9807,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4222222222222223,
462
+ "grad_norm": 4.625970363616943,
463
+ "learning_rate": 6.334634539868836e-05,
464
+ "loss": 1.047,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4444444444444444,
469
+ "grad_norm": 4.617323875427246,
470
+ "learning_rate": 6.22214975761865e-05,
471
+ "loss": 1.1423,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4666666666666668,
476
+ "grad_norm": 5.007408142089844,
477
+ "learning_rate": 6.096393120939516e-05,
478
+ "loss": 1.1181,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.488888888888889,
483
+ "grad_norm": 6.361126899719238,
484
+ "learning_rate": 5.969903509036172e-05,
485
+ "loss": 0.8642,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.511111111111111,
490
+ "grad_norm": 3.4635279178619385,
491
+ "learning_rate": 5.842765484416237e-05,
492
+ "loss": 0.9609,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.5333333333333332,
497
+ "grad_norm": 2.583265781402588,
498
+ "learning_rate": 5.715064043072771e-05,
499
+ "loss": 0.9543,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5555555555555556,
504
+ "grad_norm": 3.2295000553131104,
505
+ "learning_rate": 5.586884557661638e-05,
506
+ "loss": 1.3545,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5777777777777777,
511
+ "grad_norm": 3.589311361312866,
512
+ "learning_rate": 5.458312720427037e-05,
513
+ "loss": 1.1898,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.6,
518
+ "grad_norm": 3.749166965484619,
519
+ "learning_rate": 5.329434485913393e-05,
520
+ "loss": 0.9212,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6222222222222222,
525
+ "grad_norm": 5.566150665283203,
526
+ "learning_rate": 5.200336013501898e-05,
527
+ "loss": 1.0051,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.6444444444444444,
532
+ "grad_norm": 4.666942596435547,
533
+ "learning_rate": 5.07110360981009e-05,
534
+ "loss": 0.9947,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6666666666666665,
539
+ "grad_norm": 4.7450737953186035,
540
+ "learning_rate": 4.941823670993016e-05,
541
+ "loss": 1.2966,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.6888888888888889,
546
+ "grad_norm": 3.922316551208496,
547
+ "learning_rate": 4.8125826249845375e-05,
548
+ "loss": 0.9482,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.7111111111111112,
553
+ "grad_norm": 2.466024398803711,
554
+ "learning_rate": 4.683466873717379e-05,
555
+ "loss": 1.1203,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7333333333333334,
560
+ "grad_norm": 3.1226003170013428,
561
+ "learning_rate": 4.55456273536057e-05,
562
+ "loss": 0.9876,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.7555555555555555,
567
+ "grad_norm": 3.574613571166992,
568
+ "learning_rate": 4.4259563866128754e-05,
569
+ "loss": 0.9708,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.7777777777777777,
574
+ "grad_norm": 4.307621002197266,
575
+ "learning_rate": 4.297733805090819e-05,
576
+ "loss": 1.1659,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.8,
581
+ "grad_norm": 3.263989210128784,
582
+ "learning_rate": 4.169980711849781e-05,
583
+ "loss": 1.0767,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8222222222222222,
588
+ "grad_norm": 4.091586112976074,
589
+ "learning_rate": 4.0427825140766306e-05,
590
+ "loss": 0.9197,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8444444444444446,
595
+ "grad_norm": 6.540091037750244,
596
+ "learning_rate": 3.916224247992184e-05,
597
+ "loss": 1.0032,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8666666666666667,
602
+ "grad_norm": 3.0093724727630615,
603
+ "learning_rate": 3.790390522001662e-05,
604
+ "loss": 0.9162,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8888888888888888,
609
+ "grad_norm": 3.8956823348999023,
610
+ "learning_rate": 3.665365460131165e-05,
611
+ "loss": 0.9894,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.911111111111111,
616
+ "grad_norm": 6.698014736175537,
617
+ "learning_rate": 3.541232645787964e-05,
618
+ "loss": 1.0847,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9333333333333333,
623
+ "grad_norm": 3.408623218536377,
624
+ "learning_rate": 3.418075065882217e-05,
625
+ "loss": 1.0293,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9555555555555557,
630
+ "grad_norm": 5.4307780265808105,
631
+ "learning_rate": 3.295975055347464e-05,
632
+ "loss": 1.1167,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9777777777777779,
637
+ "grad_norm": 3.301551103591919,
638
+ "learning_rate": 3.175014242096985e-05,
639
+ "loss": 0.9419,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 2.0,
644
+ "grad_norm": 3.311927080154419,
645
+ "learning_rate": 3.0552734924528306e-05,
646
+ "loss": 1.0782,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 2.022222222222222,
651
+ "grad_norm": 3.594782590866089,
652
+ "learning_rate": 2.936832857084003e-05,
653
+ "loss": 0.7008,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 2.0444444444444443,
658
+ "grad_norm": 2.127872943878174,
659
+ "learning_rate": 2.8197715174899185e-05,
660
+ "loss": 0.5128,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 2.066666666666667,
665
+ "grad_norm": 1.7860101461410522,
666
+ "learning_rate": 2.7041677330649407e-05,
667
+ "loss": 0.4185,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 2.088888888888889,
672
+ "grad_norm": 5.212789058685303,
673
+ "learning_rate": 2.590098788779396e-05,
674
+ "loss": 0.52,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 2.111111111111111,
679
+ "grad_norm": 2.7228968143463135,
680
+ "learning_rate": 2.4776409435119775e-05,
681
+ "loss": 0.7065,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 2.1333333333333333,
686
+ "grad_norm": 2.3301429748535156,
687
+ "learning_rate": 2.3668693790681634e-05,
688
+ "loss": 0.3988,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 2.1555555555555554,
693
+ "grad_norm": 3.8069827556610107,
694
+ "learning_rate": 2.257858149918688e-05,
695
+ "loss": 0.6353,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 2.1777777777777776,
700
+ "grad_norm": 3.177034854888916,
701
+ "learning_rate": 2.15068013369166e-05,
702
+ "loss": 0.4815,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 2.2,
707
+ "grad_norm": 2.7649686336517334,
708
+ "learning_rate": 2.0454069824514444e-05,
709
+ "loss": 0.5903,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 2.2222222222222223,
714
+ "grad_norm": 3.8075079917907715,
715
+ "learning_rate": 1.942109074796888e-05,
716
+ "loss": 0.5375,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 2.2222222222222223,
721
+ "eval_loss": 1.9768437147140503,
722
+ "eval_runtime": 4.0891,
723
+ "eval_samples_per_second": 24.455,
724
+ "eval_steps_per_second": 24.455,
725
+ "step": 1000
726
+ }
727
+ ],
728
+ "logging_steps": 10,
729
+ "max_steps": 1350,
730
+ "num_input_tokens_seen": 0,
731
+ "num_train_epochs": 3,
732
+ "save_steps": 500,
733
+ "stateful_callbacks": {
734
+ "TrainerControl": {
735
+ "args": {
736
+ "should_epoch_stop": false,
737
+ "should_evaluate": false,
738
+ "should_log": false,
739
+ "should_save": true,
740
+ "should_training_stop": false
741
+ },
742
+ "attributes": {}
743
+ }
744
+ },
745
+ "total_flos": 2314334064574464.0,
746
+ "train_batch_size": 1,
747
+ "trial_name": null,
748
+ "trial_params": null
749
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def63747f8477e39f6ef96a6ad566084968ec6425a4470e3c135aaa92492a7f4
3
+ size 5368
checkpoint-1000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1350/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-1350/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/Qwen/Qwen2___5-1___5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151936
29
+ }
checkpoint-1350/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
checkpoint-1350/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1350/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ec2edd8e38a8d62dd10271e458ceede3d87c27b323d7789489b01c4f025b08
3
+ size 3274658144
checkpoint-1350/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea1e5baa46c00e57303b072e594a61f5022ed9c570de34b39916e0a3c074702
3
+ size 748785878
checkpoint-1350/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
3
+ size 14244
checkpoint-1350/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a604098274ccadc84addd0ec65c3ddc1b4e8baaaef713bffa4e8720a94ebf2f
3
+ size 1064
checkpoint-1350/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": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-1350/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-1350/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-1350/trainer_state.json ADDED
@@ -0,0 +1,994 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1350,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.022222222222222223,
13
+ "grad_norm": 6.603886604309082,
14
+ "learning_rate": 7.4074074074074075e-06,
15
+ "loss": 1.7454,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.044444444444444446,
20
+ "grad_norm": 4.177036285400391,
21
+ "learning_rate": 1.4814814814814815e-05,
22
+ "loss": 1.5071,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06666666666666667,
27
+ "grad_norm": 6.5375285148620605,
28
+ "learning_rate": 2.2222222222222223e-05,
29
+ "loss": 1.6012,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08888888888888889,
34
+ "grad_norm": 2.4201414585113525,
35
+ "learning_rate": 2.8888888888888888e-05,
36
+ "loss": 1.543,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.1111111111111111,
41
+ "grad_norm": 8.420122146606445,
42
+ "learning_rate": 3.62962962962963e-05,
43
+ "loss": 1.6806,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13333333333333333,
48
+ "grad_norm": 2.9238393306732178,
49
+ "learning_rate": 4.3703703703703705e-05,
50
+ "loss": 1.4376,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15555555555555556,
55
+ "grad_norm": 4.334264278411865,
56
+ "learning_rate": 5.111111111111111e-05,
57
+ "loss": 1.5629,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.17777777777777778,
62
+ "grad_norm": 4.047328472137451,
63
+ "learning_rate": 5.851851851851852e-05,
64
+ "loss": 1.5502,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.2,
69
+ "grad_norm": 6.695739269256592,
70
+ "learning_rate": 6.592592592592593e-05,
71
+ "loss": 1.5744,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2222222222222222,
76
+ "grad_norm": 2.579887628555298,
77
+ "learning_rate": 7.333333333333333e-05,
78
+ "loss": 1.4887,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.24444444444444444,
83
+ "grad_norm": 8.655933380126953,
84
+ "learning_rate": 8.074074074074075e-05,
85
+ "loss": 1.4432,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.26666666666666666,
90
+ "grad_norm": 2.3287596702575684,
91
+ "learning_rate": 8.814814814814815e-05,
92
+ "loss": 1.7349,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.28888888888888886,
97
+ "grad_norm": 3.626464366912842,
98
+ "learning_rate": 9.555555555555557e-05,
99
+ "loss": 1.8419,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3111111111111111,
104
+ "grad_norm": 13.17669677734375,
105
+ "learning_rate": 9.999732574196451e-05,
106
+ "loss": 1.7434,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3333333333333333,
111
+ "grad_norm": 2.938781261444092,
112
+ "learning_rate": 9.996724362426075e-05,
113
+ "loss": 1.7345,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.35555555555555557,
118
+ "grad_norm": 3.3643951416015625,
119
+ "learning_rate": 9.990375674425109e-05,
120
+ "loss": 1.6652,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.37777777777777777,
125
+ "grad_norm": 4.0528178215026855,
126
+ "learning_rate": 9.980690754502393e-05,
127
+ "loss": 1.6247,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4,
132
+ "grad_norm": 3.2510921955108643,
133
+ "learning_rate": 9.96767607734863e-05,
134
+ "loss": 1.9226,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4222222222222222,
139
+ "grad_norm": 3.1616647243499756,
140
+ "learning_rate": 9.951340343707852e-05,
141
+ "loss": 1.9507,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4444444444444444,
146
+ "grad_norm": 2.816512107849121,
147
+ "learning_rate": 9.931694474560686e-05,
148
+ "loss": 1.5901,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4666666666666667,
153
+ "grad_norm": 3.0883939266204834,
154
+ "learning_rate": 9.908751603823301e-05,
155
+ "loss": 1.7762,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4888888888888889,
160
+ "grad_norm": 3.496539354324341,
161
+ "learning_rate": 9.882527069566965e-05,
162
+ "loss": 1.7833,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5111111111111111,
167
+ "grad_norm": 3.6071531772613525,
168
+ "learning_rate": 9.853038403764021e-05,
169
+ "loss": 1.5891,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5333333333333333,
174
+ "grad_norm": 3.1297965049743652,
175
+ "learning_rate": 9.820305320567192e-05,
176
+ "loss": 1.7261,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5555555555555556,
181
+ "grad_norm": 2.707146167755127,
182
+ "learning_rate": 9.784349703130007e-05,
183
+ "loss": 1.6448,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5777777777777777,
188
+ "grad_norm": 3.1915082931518555,
189
+ "learning_rate": 9.745195588977192e-05,
190
+ "loss": 1.9097,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6,
195
+ "grad_norm": 2.056610584259033,
196
+ "learning_rate": 9.702869153934782e-05,
197
+ "loss": 1.6173,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6222222222222222,
202
+ "grad_norm": 3.044048309326172,
203
+ "learning_rate": 9.657398694630712e-05,
204
+ "loss": 1.8324,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6444444444444445,
209
+ "grad_norm": 3.3219234943389893,
210
+ "learning_rate": 9.608814609577585e-05,
211
+ "loss": 1.818,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6666666666666666,
216
+ "grad_norm": 2.5632572174072266,
217
+ "learning_rate": 9.557149378850254e-05,
218
+ "loss": 1.618,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6888888888888889,
223
+ "grad_norm": 2.3387904167175293,
224
+ "learning_rate": 9.502437542371812e-05,
225
+ "loss": 1.6228,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7111111111111111,
230
+ "grad_norm": 2.6883046627044678,
231
+ "learning_rate": 9.444715676822501e-05,
232
+ "loss": 1.7307,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7333333333333333,
237
+ "grad_norm": 2.9449591636657715,
238
+ "learning_rate": 9.384022371187003e-05,
239
+ "loss": 1.7338,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7555555555555555,
244
+ "grad_norm": 2.4884233474731445,
245
+ "learning_rate": 9.320398200956403e-05,
246
+ "loss": 1.4941,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7777777777777778,
251
+ "grad_norm": 5.446136951446533,
252
+ "learning_rate": 9.253885701002134e-05,
253
+ "loss": 1.9377,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8,
258
+ "grad_norm": 3.122303009033203,
259
+ "learning_rate": 9.184529337140002e-05,
260
+ "loss": 1.5295,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8222222222222222,
265
+ "grad_norm": 3.4902145862579346,
266
+ "learning_rate": 9.112375476403312e-05,
267
+ "loss": 1.688,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8444444444444444,
272
+ "grad_norm": 3.041170597076416,
273
+ "learning_rate": 9.037472356044962e-05,
274
+ "loss": 1.7526,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8666666666666667,
279
+ "grad_norm": 2.029374837875366,
280
+ "learning_rate": 8.959870051289241e-05,
281
+ "loss": 1.5125,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8888888888888888,
286
+ "grad_norm": 4.354530334472656,
287
+ "learning_rate": 8.879620441854872e-05,
288
+ "loss": 1.6507,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9111111111111111,
293
+ "grad_norm": 3.2502028942108154,
294
+ "learning_rate": 8.796777177271708e-05,
295
+ "loss": 1.6118,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9333333333333333,
300
+ "grad_norm": 2.198453903198242,
301
+ "learning_rate": 8.711395641014228e-05,
302
+ "loss": 1.6589,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9555555555555556,
307
+ "grad_norm": 3.6842291355133057,
308
+ "learning_rate": 8.623532913475847e-05,
309
+ "loss": 1.6891,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9777777777777777,
314
+ "grad_norm": 2.3169732093811035,
315
+ "learning_rate": 8.533247733808776e-05,
316
+ "loss": 1.5275,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.0,
321
+ "grad_norm": 5.430471897125244,
322
+ "learning_rate": 8.440600460654958e-05,
323
+ "loss": 1.7984,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 1.0222222222222221,
328
+ "grad_norm": 4.782519817352295,
329
+ "learning_rate": 8.345653031794292e-05,
330
+ "loss": 0.9174,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.0444444444444445,
335
+ "grad_norm": 3.547177314758301,
336
+ "learning_rate": 8.248468922737188e-05,
337
+ "loss": 1.3878,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 1.0666666666666667,
342
+ "grad_norm": 2.446197748184204,
343
+ "learning_rate": 8.149113104289063e-05,
344
+ "loss": 1.1277,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.0888888888888888,
349
+ "grad_norm": 3.3164918422698975,
350
+ "learning_rate": 8.047651999115217e-05,
351
+ "loss": 1.0124,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.1111111111111112,
356
+ "grad_norm": 7.3411359786987305,
357
+ "learning_rate": 7.944153437335057e-05,
358
+ "loss": 1.0102,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.1111111111111112,
363
+ "eval_loss": 1.7722898721694946,
364
+ "eval_runtime": 4.268,
365
+ "eval_samples_per_second": 23.43,
366
+ "eval_steps_per_second": 23.43,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.1333333333333333,
371
+ "grad_norm": 3.1477370262145996,
372
+ "learning_rate": 7.838686611175421e-05,
373
+ "loss": 1.1386,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1555555555555554,
378
+ "grad_norm": 3.3324782848358154,
379
+ "learning_rate": 7.73132202871327e-05,
380
+ "loss": 1.0376,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1777777777777778,
385
+ "grad_norm": 4.7969136238098145,
386
+ "learning_rate": 7.6221314667387e-05,
387
+ "loss": 1.2585,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2,
392
+ "grad_norm": 3.488189697265625,
393
+ "learning_rate": 7.511187922769768e-05,
394
+ "loss": 1.2203,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2222222222222223,
399
+ "grad_norm": 3.5396199226379395,
400
+ "learning_rate": 7.398565566251232e-05,
401
+ "loss": 1.1651,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2444444444444445,
406
+ "grad_norm": 4.660005569458008,
407
+ "learning_rate": 7.284339688969809e-05,
408
+ "loss": 1.1229,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2666666666666666,
413
+ "grad_norm": 6.269535541534424,
414
+ "learning_rate": 7.168586654719117e-05,
415
+ "loss": 1.1348,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2888888888888888,
420
+ "grad_norm": 5.864573955535889,
421
+ "learning_rate": 7.051383848247942e-05,
422
+ "loss": 1.1637,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3111111111111111,
427
+ "grad_norm": 3.3166041374206543,
428
+ "learning_rate": 6.944726507547169e-05,
429
+ "loss": 1.0358,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.3333333333333333,
434
+ "grad_norm": 4.742485523223877,
435
+ "learning_rate": 6.824985757903016e-05,
436
+ "loss": 1.0499,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3555555555555556,
441
+ "grad_norm": 2.5902740955352783,
442
+ "learning_rate": 6.704024944652537e-05,
443
+ "loss": 0.9614,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3777777777777778,
448
+ "grad_norm": 4.31684684753418,
449
+ "learning_rate": 6.581924934117782e-05,
450
+ "loss": 1.2387,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.4,
455
+ "grad_norm": 6.753187656402588,
456
+ "learning_rate": 6.458767354212036e-05,
457
+ "loss": 0.9807,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4222222222222223,
462
+ "grad_norm": 4.625970363616943,
463
+ "learning_rate": 6.334634539868836e-05,
464
+ "loss": 1.047,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4444444444444444,
469
+ "grad_norm": 4.617323875427246,
470
+ "learning_rate": 6.22214975761865e-05,
471
+ "loss": 1.1423,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4666666666666668,
476
+ "grad_norm": 5.007408142089844,
477
+ "learning_rate": 6.096393120939516e-05,
478
+ "loss": 1.1181,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.488888888888889,
483
+ "grad_norm": 6.361126899719238,
484
+ "learning_rate": 5.969903509036172e-05,
485
+ "loss": 0.8642,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.511111111111111,
490
+ "grad_norm": 3.4635279178619385,
491
+ "learning_rate": 5.842765484416237e-05,
492
+ "loss": 0.9609,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.5333333333333332,
497
+ "grad_norm": 2.583265781402588,
498
+ "learning_rate": 5.715064043072771e-05,
499
+ "loss": 0.9543,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5555555555555556,
504
+ "grad_norm": 3.2295000553131104,
505
+ "learning_rate": 5.586884557661638e-05,
506
+ "loss": 1.3545,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5777777777777777,
511
+ "grad_norm": 3.589311361312866,
512
+ "learning_rate": 5.458312720427037e-05,
513
+ "loss": 1.1898,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.6,
518
+ "grad_norm": 3.749166965484619,
519
+ "learning_rate": 5.329434485913393e-05,
520
+ "loss": 0.9212,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6222222222222222,
525
+ "grad_norm": 5.566150665283203,
526
+ "learning_rate": 5.200336013501898e-05,
527
+ "loss": 1.0051,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.6444444444444444,
532
+ "grad_norm": 4.666942596435547,
533
+ "learning_rate": 5.07110360981009e-05,
534
+ "loss": 0.9947,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6666666666666665,
539
+ "grad_norm": 4.7450737953186035,
540
+ "learning_rate": 4.941823670993016e-05,
541
+ "loss": 1.2966,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.6888888888888889,
546
+ "grad_norm": 3.922316551208496,
547
+ "learning_rate": 4.8125826249845375e-05,
548
+ "loss": 0.9482,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.7111111111111112,
553
+ "grad_norm": 2.466024398803711,
554
+ "learning_rate": 4.683466873717379e-05,
555
+ "loss": 1.1203,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7333333333333334,
560
+ "grad_norm": 3.1226003170013428,
561
+ "learning_rate": 4.55456273536057e-05,
562
+ "loss": 0.9876,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.7555555555555555,
567
+ "grad_norm": 3.574613571166992,
568
+ "learning_rate": 4.4259563866128754e-05,
569
+ "loss": 0.9708,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.7777777777777777,
574
+ "grad_norm": 4.307621002197266,
575
+ "learning_rate": 4.297733805090819e-05,
576
+ "loss": 1.1659,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.8,
581
+ "grad_norm": 3.263989210128784,
582
+ "learning_rate": 4.169980711849781e-05,
583
+ "loss": 1.0767,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8222222222222222,
588
+ "grad_norm": 4.091586112976074,
589
+ "learning_rate": 4.0427825140766306e-05,
590
+ "loss": 0.9197,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8444444444444446,
595
+ "grad_norm": 6.540091037750244,
596
+ "learning_rate": 3.916224247992184e-05,
597
+ "loss": 1.0032,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8666666666666667,
602
+ "grad_norm": 3.0093724727630615,
603
+ "learning_rate": 3.790390522001662e-05,
604
+ "loss": 0.9162,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8888888888888888,
609
+ "grad_norm": 3.8956823348999023,
610
+ "learning_rate": 3.665365460131165e-05,
611
+ "loss": 0.9894,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.911111111111111,
616
+ "grad_norm": 6.698014736175537,
617
+ "learning_rate": 3.541232645787964e-05,
618
+ "loss": 1.0847,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9333333333333333,
623
+ "grad_norm": 3.408623218536377,
624
+ "learning_rate": 3.418075065882217e-05,
625
+ "loss": 1.0293,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9555555555555557,
630
+ "grad_norm": 5.4307780265808105,
631
+ "learning_rate": 3.295975055347464e-05,
632
+ "loss": 1.1167,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9777777777777779,
637
+ "grad_norm": 3.301551103591919,
638
+ "learning_rate": 3.175014242096985e-05,
639
+ "loss": 0.9419,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 2.0,
644
+ "grad_norm": 3.311927080154419,
645
+ "learning_rate": 3.0552734924528306e-05,
646
+ "loss": 1.0782,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 2.022222222222222,
651
+ "grad_norm": 3.594782590866089,
652
+ "learning_rate": 2.936832857084003e-05,
653
+ "loss": 0.7008,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 2.0444444444444443,
658
+ "grad_norm": 2.127872943878174,
659
+ "learning_rate": 2.8197715174899185e-05,
660
+ "loss": 0.5128,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 2.066666666666667,
665
+ "grad_norm": 1.7860101461410522,
666
+ "learning_rate": 2.7041677330649407e-05,
667
+ "loss": 0.4185,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 2.088888888888889,
672
+ "grad_norm": 5.212789058685303,
673
+ "learning_rate": 2.590098788779396e-05,
674
+ "loss": 0.52,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 2.111111111111111,
679
+ "grad_norm": 2.7228968143463135,
680
+ "learning_rate": 2.4776409435119775e-05,
681
+ "loss": 0.7065,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 2.1333333333333333,
686
+ "grad_norm": 2.3301429748535156,
687
+ "learning_rate": 2.3668693790681634e-05,
688
+ "loss": 0.3988,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 2.1555555555555554,
693
+ "grad_norm": 3.8069827556610107,
694
+ "learning_rate": 2.257858149918688e-05,
695
+ "loss": 0.6353,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 2.1777777777777776,
700
+ "grad_norm": 3.177034854888916,
701
+ "learning_rate": 2.15068013369166e-05,
702
+ "loss": 0.4815,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 2.2,
707
+ "grad_norm": 2.7649686336517334,
708
+ "learning_rate": 2.0454069824514444e-05,
709
+ "loss": 0.5903,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 2.2222222222222223,
714
+ "grad_norm": 3.8075079917907715,
715
+ "learning_rate": 1.942109074796888e-05,
716
+ "loss": 0.5375,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 2.2222222222222223,
721
+ "eval_loss": 1.9768437147140503,
722
+ "eval_runtime": 4.0891,
723
+ "eval_samples_per_second": 24.455,
724
+ "eval_steps_per_second": 24.455,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.2444444444444445,
729
+ "grad_norm": 4.101439476013184,
730
+ "learning_rate": 1.8408554688108786e-05,
731
+ "loss": 0.4914,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.2666666666666666,
736
+ "grad_norm": 4.174548149108887,
737
+ "learning_rate": 1.7417138558927244e-05,
738
+ "loss": 0.6643,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.2888888888888888,
743
+ "grad_norm": 2.903629779815674,
744
+ "learning_rate": 1.6447505155042088e-05,
745
+ "loss": 0.4727,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.311111111111111,
750
+ "grad_norm": 5.127641201019287,
751
+ "learning_rate": 1.5500302708595648e-05,
752
+ "loss": 0.5654,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.3333333333333335,
757
+ "grad_norm": 5.86013126373291,
758
+ "learning_rate": 1.4576164455890013e-05,
759
+ "loss": 0.4691,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.3555555555555556,
764
+ "grad_norm": 5.229647159576416,
765
+ "learning_rate": 1.3675708214047578e-05,
766
+ "loss": 0.5061,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.3777777777777778,
771
+ "grad_norm": 5.425754070281982,
772
+ "learning_rate": 1.2799535967979747e-05,
773
+ "loss": 0.4352,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.4,
778
+ "grad_norm": 5.084753513336182,
779
+ "learning_rate": 1.194823346793998e-05,
780
+ "loss": 0.5483,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.422222222222222,
785
+ "grad_norm": 4.754981517791748,
786
+ "learning_rate": 1.1122369837930363e-05,
787
+ "loss": 0.4424,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4444444444444446,
792
+ "grad_norm": 3.03784441947937,
793
+ "learning_rate": 1.0322497195223285e-05,
794
+ "loss": 0.4717,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.466666666666667,
799
+ "grad_norm": 9.531596183776855,
800
+ "learning_rate": 9.549150281252633e-06,
801
+ "loss": 0.4239,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.488888888888889,
806
+ "grad_norm": 8.69981575012207,
807
+ "learning_rate": 8.802846104121477e-06,
808
+ "loss": 0.6657,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.511111111111111,
813
+ "grad_norm": 3.9578542709350586,
814
+ "learning_rate": 8.084083592964942e-06,
815
+ "loss": 0.4603,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.533333333333333,
820
+ "grad_norm": 2.537245273590088,
821
+ "learning_rate": 7.393343264399438e-06,
822
+ "loss": 0.4783,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5555555555555554,
827
+ "grad_norm": 3.6952104568481445,
828
+ "learning_rate": 6.7310869012814585e-06,
829
+ "loss": 0.5769,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5777777777777775,
834
+ "grad_norm": 4.507468223571777,
835
+ "learning_rate": 6.097757243990321e-06,
836
+ "loss": 0.6047,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.6,
841
+ "grad_norm": 4.901561260223389,
842
+ "learning_rate": 5.493777694441521e-06,
843
+ "loss": 0.3204,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.6222222222222222,
848
+ "grad_norm": 5.785924434661865,
849
+ "learning_rate": 4.919552033028513e-06,
850
+ "loss": 0.4655,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6444444444444444,
855
+ "grad_norm": 7.03330659866333,
856
+ "learning_rate": 4.375464148682096e-06,
857
+ "loss": 0.5527,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.6666666666666665,
862
+ "grad_norm": 3.337351083755493,
863
+ "learning_rate": 3.861877782227885e-06,
864
+ "loss": 0.5065,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.688888888888889,
869
+ "grad_norm": 3.3279948234558105,
870
+ "learning_rate": 3.3791362832135133e-06,
871
+ "loss": 0.4094,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.7111111111111112,
876
+ "grad_norm": 3.116320848464966,
877
+ "learning_rate": 2.9275623803680596e-06,
878
+ "loss": 0.6052,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.7333333333333334,
883
+ "grad_norm": 2.5365102291107178,
884
+ "learning_rate": 2.5074579658471266e-06,
885
+ "loss": 0.491,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.7555555555555555,
890
+ "grad_norm": 4.173516750335693,
891
+ "learning_rate": 2.1191038934079643e-06,
892
+ "loss": 0.5293,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.7777777777777777,
897
+ "grad_norm": 4.494065284729004,
898
+ "learning_rate": 1.7627597906493654e-06,
899
+ "loss": 0.5024,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.8,
904
+ "grad_norm": 2.712306499481201,
905
+ "learning_rate": 1.438663885441982e-06,
906
+ "loss": 0.4411,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.822222222222222,
911
+ "grad_norm": 1.7787264585494995,
912
+ "learning_rate": 1.1470328466651304e-06,
913
+ "loss": 0.616,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8444444444444446,
918
+ "grad_norm": 2.3278346061706543,
919
+ "learning_rate": 8.880616393563967e-07,
920
+ "loss": 0.5948,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.8666666666666667,
925
+ "grad_norm": 3.4088244438171387,
926
+ "learning_rate": 6.61923394371039e-07,
927
+ "loss": 0.4361,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.888888888888889,
932
+ "grad_norm": 3.020115613937378,
933
+ "learning_rate": 4.6876929263829915e-07,
934
+ "loss": 0.4553,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.911111111111111,
939
+ "grad_norm": 2.950218915939331,
940
+ "learning_rate": 3.087284640918786e-07,
941
+ "loss": 0.407,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.9333333333333336,
946
+ "grad_norm": 4.008513450622559,
947
+ "learning_rate": 1.819079013423153e-07,
948
+ "loss": 0.4567,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.9555555555555557,
953
+ "grad_norm": 2.7357242107391357,
954
+ "learning_rate": 8.839238814886685e-08,
955
+ "loss": 0.5011,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.977777777777778,
960
+ "grad_norm": 5.6999006271362305,
961
+ "learning_rate": 2.824444273875071e-08,
962
+ "loss": 0.5416,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 3.0,
967
+ "grad_norm": 3.6127123832702637,
968
+ "learning_rate": 1.5042760116212861e-09,
969
+ "loss": 0.4591,
970
+ "step": 1350
971
+ }
972
+ ],
973
+ "logging_steps": 10,
974
+ "max_steps": 1350,
975
+ "num_input_tokens_seen": 0,
976
+ "num_train_epochs": 3,
977
+ "save_steps": 500,
978
+ "stateful_callbacks": {
979
+ "TrainerControl": {
980
+ "args": {
981
+ "should_epoch_stop": false,
982
+ "should_evaluate": false,
983
+ "should_log": false,
984
+ "should_save": true,
985
+ "should_training_stop": true
986
+ },
987
+ "attributes": {}
988
+ }
989
+ },
990
+ "total_flos": 3120728157462528.0,
991
+ "train_batch_size": 1,
992
+ "trial_name": null,
993
+ "trial_params": null
994
+ }
checkpoint-1350/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def63747f8477e39f6ef96a6ad566084968ec6425a4470e3c135aaa92492a7f4
3
+ size 5368
checkpoint-1350/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-500/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/Qwen/Qwen2___5-1___5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151936
29
+ }
checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a03db46151377415e1e13e3e9d636e1c80e103bff1723984e0653c959621017
3
+ size 3274658144
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b4b5307aac5a682fb5273c88eac297f3fd95d64cb41e5f6d0e9471c19aef6e
3
+ size 748785878
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61bcd51559f932406b03030f24e7d85f5824d1bc96d984bad3995c622ed78953
3
+ size 1064
checkpoint-500/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": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,391 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.1111111111111112,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.022222222222222223,
13
+ "grad_norm": 6.603886604309082,
14
+ "learning_rate": 7.4074074074074075e-06,
15
+ "loss": 1.7454,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.044444444444444446,
20
+ "grad_norm": 4.177036285400391,
21
+ "learning_rate": 1.4814814814814815e-05,
22
+ "loss": 1.5071,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06666666666666667,
27
+ "grad_norm": 6.5375285148620605,
28
+ "learning_rate": 2.2222222222222223e-05,
29
+ "loss": 1.6012,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08888888888888889,
34
+ "grad_norm": 2.4201414585113525,
35
+ "learning_rate": 2.8888888888888888e-05,
36
+ "loss": 1.543,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.1111111111111111,
41
+ "grad_norm": 8.420122146606445,
42
+ "learning_rate": 3.62962962962963e-05,
43
+ "loss": 1.6806,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13333333333333333,
48
+ "grad_norm": 2.9238393306732178,
49
+ "learning_rate": 4.3703703703703705e-05,
50
+ "loss": 1.4376,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15555555555555556,
55
+ "grad_norm": 4.334264278411865,
56
+ "learning_rate": 5.111111111111111e-05,
57
+ "loss": 1.5629,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.17777777777777778,
62
+ "grad_norm": 4.047328472137451,
63
+ "learning_rate": 5.851851851851852e-05,
64
+ "loss": 1.5502,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.2,
69
+ "grad_norm": 6.695739269256592,
70
+ "learning_rate": 6.592592592592593e-05,
71
+ "loss": 1.5744,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2222222222222222,
76
+ "grad_norm": 2.579887628555298,
77
+ "learning_rate": 7.333333333333333e-05,
78
+ "loss": 1.4887,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.24444444444444444,
83
+ "grad_norm": 8.655933380126953,
84
+ "learning_rate": 8.074074074074075e-05,
85
+ "loss": 1.4432,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.26666666666666666,
90
+ "grad_norm": 2.3287596702575684,
91
+ "learning_rate": 8.814814814814815e-05,
92
+ "loss": 1.7349,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.28888888888888886,
97
+ "grad_norm": 3.626464366912842,
98
+ "learning_rate": 9.555555555555557e-05,
99
+ "loss": 1.8419,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3111111111111111,
104
+ "grad_norm": 13.17669677734375,
105
+ "learning_rate": 9.999732574196451e-05,
106
+ "loss": 1.7434,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3333333333333333,
111
+ "grad_norm": 2.938781261444092,
112
+ "learning_rate": 9.996724362426075e-05,
113
+ "loss": 1.7345,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.35555555555555557,
118
+ "grad_norm": 3.3643951416015625,
119
+ "learning_rate": 9.990375674425109e-05,
120
+ "loss": 1.6652,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.37777777777777777,
125
+ "grad_norm": 4.0528178215026855,
126
+ "learning_rate": 9.980690754502393e-05,
127
+ "loss": 1.6247,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4,
132
+ "grad_norm": 3.2510921955108643,
133
+ "learning_rate": 9.96767607734863e-05,
134
+ "loss": 1.9226,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4222222222222222,
139
+ "grad_norm": 3.1616647243499756,
140
+ "learning_rate": 9.951340343707852e-05,
141
+ "loss": 1.9507,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4444444444444444,
146
+ "grad_norm": 2.816512107849121,
147
+ "learning_rate": 9.931694474560686e-05,
148
+ "loss": 1.5901,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4666666666666667,
153
+ "grad_norm": 3.0883939266204834,
154
+ "learning_rate": 9.908751603823301e-05,
155
+ "loss": 1.7762,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4888888888888889,
160
+ "grad_norm": 3.496539354324341,
161
+ "learning_rate": 9.882527069566965e-05,
162
+ "loss": 1.7833,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5111111111111111,
167
+ "grad_norm": 3.6071531772613525,
168
+ "learning_rate": 9.853038403764021e-05,
169
+ "loss": 1.5891,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5333333333333333,
174
+ "grad_norm": 3.1297965049743652,
175
+ "learning_rate": 9.820305320567192e-05,
176
+ "loss": 1.7261,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5555555555555556,
181
+ "grad_norm": 2.707146167755127,
182
+ "learning_rate": 9.784349703130007e-05,
183
+ "loss": 1.6448,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5777777777777777,
188
+ "grad_norm": 3.1915082931518555,
189
+ "learning_rate": 9.745195588977192e-05,
190
+ "loss": 1.9097,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6,
195
+ "grad_norm": 2.056610584259033,
196
+ "learning_rate": 9.702869153934782e-05,
197
+ "loss": 1.6173,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6222222222222222,
202
+ "grad_norm": 3.044048309326172,
203
+ "learning_rate": 9.657398694630712e-05,
204
+ "loss": 1.8324,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6444444444444445,
209
+ "grad_norm": 3.3219234943389893,
210
+ "learning_rate": 9.608814609577585e-05,
211
+ "loss": 1.818,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6666666666666666,
216
+ "grad_norm": 2.5632572174072266,
217
+ "learning_rate": 9.557149378850254e-05,
218
+ "loss": 1.618,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6888888888888889,
223
+ "grad_norm": 2.3387904167175293,
224
+ "learning_rate": 9.502437542371812e-05,
225
+ "loss": 1.6228,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7111111111111111,
230
+ "grad_norm": 2.6883046627044678,
231
+ "learning_rate": 9.444715676822501e-05,
232
+ "loss": 1.7307,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7333333333333333,
237
+ "grad_norm": 2.9449591636657715,
238
+ "learning_rate": 9.384022371187003e-05,
239
+ "loss": 1.7338,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7555555555555555,
244
+ "grad_norm": 2.4884233474731445,
245
+ "learning_rate": 9.320398200956403e-05,
246
+ "loss": 1.4941,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7777777777777778,
251
+ "grad_norm": 5.446136951446533,
252
+ "learning_rate": 9.253885701002134e-05,
253
+ "loss": 1.9377,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8,
258
+ "grad_norm": 3.122303009033203,
259
+ "learning_rate": 9.184529337140002e-05,
260
+ "loss": 1.5295,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8222222222222222,
265
+ "grad_norm": 3.4902145862579346,
266
+ "learning_rate": 9.112375476403312e-05,
267
+ "loss": 1.688,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8444444444444444,
272
+ "grad_norm": 3.041170597076416,
273
+ "learning_rate": 9.037472356044962e-05,
274
+ "loss": 1.7526,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8666666666666667,
279
+ "grad_norm": 2.029374837875366,
280
+ "learning_rate": 8.959870051289241e-05,
281
+ "loss": 1.5125,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8888888888888888,
286
+ "grad_norm": 4.354530334472656,
287
+ "learning_rate": 8.879620441854872e-05,
288
+ "loss": 1.6507,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9111111111111111,
293
+ "grad_norm": 3.2502028942108154,
294
+ "learning_rate": 8.796777177271708e-05,
295
+ "loss": 1.6118,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9333333333333333,
300
+ "grad_norm": 2.198453903198242,
301
+ "learning_rate": 8.711395641014228e-05,
302
+ "loss": 1.6589,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9555555555555556,
307
+ "grad_norm": 3.6842291355133057,
308
+ "learning_rate": 8.623532913475847e-05,
309
+ "loss": 1.6891,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9777777777777777,
314
+ "grad_norm": 2.3169732093811035,
315
+ "learning_rate": 8.533247733808776e-05,
316
+ "loss": 1.5275,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.0,
321
+ "grad_norm": 5.430471897125244,
322
+ "learning_rate": 8.440600460654958e-05,
323
+ "loss": 1.7984,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 1.0222222222222221,
328
+ "grad_norm": 4.782519817352295,
329
+ "learning_rate": 8.345653031794292e-05,
330
+ "loss": 0.9174,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.0444444444444445,
335
+ "grad_norm": 3.547177314758301,
336
+ "learning_rate": 8.248468922737188e-05,
337
+ "loss": 1.3878,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 1.0666666666666667,
342
+ "grad_norm": 2.446197748184204,
343
+ "learning_rate": 8.149113104289063e-05,
344
+ "loss": 1.1277,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.0888888888888888,
349
+ "grad_norm": 3.3164918422698975,
350
+ "learning_rate": 8.047651999115217e-05,
351
+ "loss": 1.0124,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.1111111111111112,
356
+ "grad_norm": 7.3411359786987305,
357
+ "learning_rate": 7.944153437335057e-05,
358
+ "loss": 1.0102,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.1111111111111112,
363
+ "eval_loss": 1.7722898721694946,
364
+ "eval_runtime": 4.268,
365
+ "eval_samples_per_second": 23.43,
366
+ "eval_steps_per_second": 23.43,
367
+ "step": 500
368
+ }
369
+ ],
370
+ "logging_steps": 10,
371
+ "max_steps": 1350,
372
+ "num_input_tokens_seen": 0,
373
+ "num_train_epochs": 3,
374
+ "save_steps": 500,
375
+ "stateful_callbacks": {
376
+ "TrainerControl": {
377
+ "args": {
378
+ "should_epoch_stop": false,
379
+ "should_evaluate": false,
380
+ "should_log": false,
381
+ "should_save": true,
382
+ "should_training_stop": false
383
+ },
384
+ "attributes": {}
385
+ }
386
+ },
387
+ "total_flos": 1154148007526400.0,
388
+ "train_batch_size": 1,
389
+ "trial_name": null,
390
+ "trial_params": null
391
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def63747f8477e39f6ef96a6ad566084968ec6425a4470e3c135aaa92492a7f4
3
+ size 5368
checkpoint-500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/Qwen/Qwen2___5-1___5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151936
29
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.9959301948547363,
4
+ "eval_runtime": 4.3369,
5
+ "eval_samples_per_second": 23.058,
6
+ "eval_steps_per_second": 23.058
7
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff