qchapp commited on
Commit
1797ec4
·
verified ·
1 Parent(s): 3e441bb

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -38,3 +38,4 @@ checkpoint-2871/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  checkpoint-7600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  checkpoint-9570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
38
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  checkpoint-7600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  checkpoint-9570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-400/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-400/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
checkpoint-400/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.51.3"
6
+ }
checkpoint-400/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c849dd1749ed49e122001df3569c3a3e2b2e78796c5e16c4bfb5b3fe08a47916
3
+ size 2384234968
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d906aceb07d4090078ba5c305cf54dac872825c46c59f052cec270ed2c4334
3
+ size 4768662910
checkpoint-400/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-400/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:838de4f027f36a4b12ab0e9f358cc378dc395db718efa9d64869f27ced70790c
3
+ size 988
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d4f2123a36b7b17a33036b536aa7749267e2ed5e0b4707fcb54737d1bc7f8c
3
+ size 1064
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352a863cd2761388ccc58f1432467ba6a1037bf12df9069889b142fa246471f6
3
+ size 11422752
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|endoftext|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 400,
3
+ "best_metric": 1.5967378616333008,
4
+ "best_model_checkpoint": "models/MNLP_M3_rag_model_test/checkpoint-400",
5
+ "epoch": 2.08355091383812,
6
+ "eval_steps": 200,
7
+ "global_step": 400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.05221932114882506,
14
+ "grad_norm": 7.428971767425537,
15
+ "learning_rate": 6.206896551724138e-06,
16
+ "loss": 3.5132,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.10443864229765012,
21
+ "grad_norm": 6.059654712677002,
22
+ "learning_rate": 1.310344827586207e-05,
23
+ "loss": 3.0338,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.1566579634464752,
28
+ "grad_norm": 5.7227091789245605,
29
+ "learning_rate": 2e-05,
30
+ "loss": 2.9247,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.20887728459530025,
35
+ "grad_norm": 6.097289085388184,
36
+ "learning_rate": 1.9632352941176472e-05,
37
+ "loss": 2.7247,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.26109660574412535,
42
+ "grad_norm": 6.7676849365234375,
43
+ "learning_rate": 1.9264705882352943e-05,
44
+ "loss": 2.649,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.3133159268929504,
49
+ "grad_norm": 6.696221351623535,
50
+ "learning_rate": 1.8897058823529413e-05,
51
+ "loss": 2.5119,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.36553524804177545,
56
+ "grad_norm": 6.6193108558654785,
57
+ "learning_rate": 1.8529411764705884e-05,
58
+ "loss": 2.482,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.4177545691906005,
63
+ "grad_norm": 6.831273555755615,
64
+ "learning_rate": 1.8161764705882355e-05,
65
+ "loss": 2.3116,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.4699738903394256,
70
+ "grad_norm": 6.834325790405273,
71
+ "learning_rate": 1.783088235294118e-05,
72
+ "loss": 2.2966,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.5221932114882507,
77
+ "grad_norm": 6.186923027038574,
78
+ "learning_rate": 1.7463235294117647e-05,
79
+ "loss": 2.1808,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.5744125326370757,
84
+ "grad_norm": 5.660542964935303,
85
+ "learning_rate": 1.7095588235294118e-05,
86
+ "loss": 2.0213,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.6266318537859008,
91
+ "grad_norm": 7.235581398010254,
92
+ "learning_rate": 1.672794117647059e-05,
93
+ "loss": 1.9806,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.6788511749347258,
98
+ "grad_norm": 5.797588348388672,
99
+ "learning_rate": 1.636029411764706e-05,
100
+ "loss": 2.0965,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.7310704960835509,
105
+ "grad_norm": 7.213879585266113,
106
+ "learning_rate": 1.5992647058823533e-05,
107
+ "loss": 2.075,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.783289817232376,
112
+ "grad_norm": 6.168433666229248,
113
+ "learning_rate": 1.5625e-05,
114
+ "loss": 2.0189,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.835509138381201,
119
+ "grad_norm": 6.239176273345947,
120
+ "learning_rate": 1.5257352941176471e-05,
121
+ "loss": 1.918,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.8877284595300261,
126
+ "grad_norm": 6.878653526306152,
127
+ "learning_rate": 1.4889705882352943e-05,
128
+ "loss": 2.1624,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.9399477806788512,
133
+ "grad_norm": 5.984134197235107,
134
+ "learning_rate": 1.4522058823529412e-05,
135
+ "loss": 1.7616,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.9921671018276762,
140
+ "grad_norm": 6.3687825202941895,
141
+ "learning_rate": 1.4154411764705885e-05,
142
+ "loss": 1.902,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 1.04177545691906,
147
+ "grad_norm": 8.597973823547363,
148
+ "learning_rate": 1.3786764705882353e-05,
149
+ "loss": 1.5014,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 1.04177545691906,
154
+ "eval_loss": 1.7825424671173096,
155
+ "eval_runtime": 4.8649,
156
+ "eval_samples_per_second": 35.15,
157
+ "eval_steps_per_second": 4.522,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 1.0939947780678851,
162
+ "grad_norm": 6.6663336753845215,
163
+ "learning_rate": 1.3419117647058824e-05,
164
+ "loss": 1.3655,
165
+ "step": 210
166
+ },
167
+ {
168
+ "epoch": 1.1462140992167102,
169
+ "grad_norm": 6.472996711730957,
170
+ "learning_rate": 1.3051470588235295e-05,
171
+ "loss": 1.4386,
172
+ "step": 220
173
+ },
174
+ {
175
+ "epoch": 1.1984334203655354,
176
+ "grad_norm": 6.847625255584717,
177
+ "learning_rate": 1.2683823529411765e-05,
178
+ "loss": 1.265,
179
+ "step": 230
180
+ },
181
+ {
182
+ "epoch": 1.2506527415143602,
183
+ "grad_norm": 8.223856925964355,
184
+ "learning_rate": 1.2316176470588238e-05,
185
+ "loss": 1.39,
186
+ "step": 240
187
+ },
188
+ {
189
+ "epoch": 1.3028720626631853,
190
+ "grad_norm": 6.357968807220459,
191
+ "learning_rate": 1.1948529411764707e-05,
192
+ "loss": 1.3307,
193
+ "step": 250
194
+ },
195
+ {
196
+ "epoch": 1.3550913838120104,
197
+ "grad_norm": 5.952621936798096,
198
+ "learning_rate": 1.1580882352941179e-05,
199
+ "loss": 1.3974,
200
+ "step": 260
201
+ },
202
+ {
203
+ "epoch": 1.4073107049608355,
204
+ "grad_norm": 6.150119781494141,
205
+ "learning_rate": 1.1213235294117648e-05,
206
+ "loss": 1.2827,
207
+ "step": 270
208
+ },
209
+ {
210
+ "epoch": 1.4595300261096606,
211
+ "grad_norm": 7.437598705291748,
212
+ "learning_rate": 1.0845588235294118e-05,
213
+ "loss": 1.4003,
214
+ "step": 280
215
+ },
216
+ {
217
+ "epoch": 1.5117493472584855,
218
+ "grad_norm": 6.825808525085449,
219
+ "learning_rate": 1.0477941176470589e-05,
220
+ "loss": 1.2258,
221
+ "step": 290
222
+ },
223
+ {
224
+ "epoch": 1.5639686684073109,
225
+ "grad_norm": 6.366878986358643,
226
+ "learning_rate": 1.011029411764706e-05,
227
+ "loss": 1.3887,
228
+ "step": 300
229
+ },
230
+ {
231
+ "epoch": 1.6161879895561357,
232
+ "grad_norm": 6.928258895874023,
233
+ "learning_rate": 9.74264705882353e-06,
234
+ "loss": 1.2123,
235
+ "step": 310
236
+ },
237
+ {
238
+ "epoch": 1.6684073107049608,
239
+ "grad_norm": 6.122648239135742,
240
+ "learning_rate": 9.375000000000001e-06,
241
+ "loss": 1.239,
242
+ "step": 320
243
+ },
244
+ {
245
+ "epoch": 1.720626631853786,
246
+ "grad_norm": 6.110084056854248,
247
+ "learning_rate": 9.007352941176471e-06,
248
+ "loss": 1.3535,
249
+ "step": 330
250
+ },
251
+ {
252
+ "epoch": 1.7728459530026108,
253
+ "grad_norm": 7.0101704597473145,
254
+ "learning_rate": 8.639705882352942e-06,
255
+ "loss": 1.3841,
256
+ "step": 340
257
+ },
258
+ {
259
+ "epoch": 1.8250652741514362,
260
+ "grad_norm": 7.713141918182373,
261
+ "learning_rate": 8.272058823529413e-06,
262
+ "loss": 1.429,
263
+ "step": 350
264
+ },
265
+ {
266
+ "epoch": 1.877284595300261,
267
+ "grad_norm": 6.069569110870361,
268
+ "learning_rate": 7.904411764705883e-06,
269
+ "loss": 1.2837,
270
+ "step": 360
271
+ },
272
+ {
273
+ "epoch": 1.9295039164490861,
274
+ "grad_norm": 6.877740383148193,
275
+ "learning_rate": 7.536764705882353e-06,
276
+ "loss": 1.2482,
277
+ "step": 370
278
+ },
279
+ {
280
+ "epoch": 1.9817232375979112,
281
+ "grad_norm": 6.056829929351807,
282
+ "learning_rate": 7.169117647058825e-06,
283
+ "loss": 1.1995,
284
+ "step": 380
285
+ },
286
+ {
287
+ "epoch": 2.031331592689295,
288
+ "grad_norm": 5.879096508026123,
289
+ "learning_rate": 6.801470588235295e-06,
290
+ "loss": 0.9507,
291
+ "step": 390
292
+ },
293
+ {
294
+ "epoch": 2.08355091383812,
295
+ "grad_norm": 6.686075687408447,
296
+ "learning_rate": 6.433823529411766e-06,
297
+ "loss": 0.9641,
298
+ "step": 400
299
+ },
300
+ {
301
+ "epoch": 2.08355091383812,
302
+ "eval_loss": 1.5967378616333008,
303
+ "eval_runtime": 4.6644,
304
+ "eval_samples_per_second": 36.66,
305
+ "eval_steps_per_second": 4.717,
306
+ "step": 400
307
+ }
308
+ ],
309
+ "logging_steps": 10,
310
+ "max_steps": 573,
311
+ "num_input_tokens_seen": 0,
312
+ "num_train_epochs": 3,
313
+ "save_steps": 200,
314
+ "stateful_callbacks": {
315
+ "TrainerControl": {
316
+ "args": {
317
+ "should_epoch_stop": false,
318
+ "should_evaluate": false,
319
+ "should_log": false,
320
+ "should_save": true,
321
+ "should_training_stop": false
322
+ },
323
+ "attributes": {}
324
+ }
325
+ },
326
+ "total_flos": 4316440119214080.0,
327
+ "train_batch_size": 2,
328
+ "trial_name": null,
329
+ "trial_params": null
330
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a10906fb4c76d8e4098cc3cdfc04222e9b4283035d49ad4873af994a45bf332
3
+ size 5240
checkpoint-400/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2562dba8fc3a8b0f3820b67c2f6aa74be796e0e1f8411d161557cc2581c497dd
3
  size 2384234968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c849dd1749ed49e122001df3569c3a3e2b2e78796c5e16c4bfb5b3fe08a47916
3
  size 2384234968
tokenizer_config.json CHANGED
@@ -232,13 +232,9 @@
232
  "eos_token": "<|endoftext|>",
233
  "errors": "replace",
234
  "extra_special_tokens": {},
235
- "max_length": 512,
236
  "model_max_length": 131072,
237
  "pad_token": "<|endoftext|>",
238
  "split_special_tokens": false,
239
- "stride": 0,
240
  "tokenizer_class": "Qwen2Tokenizer",
241
- "truncation_side": "right",
242
- "truncation_strategy": "longest_first",
243
  "unk_token": null
244
  }
 
232
  "eos_token": "<|endoftext|>",
233
  "errors": "replace",
234
  "extra_special_tokens": {},
 
235
  "model_max_length": 131072,
236
  "pad_token": "<|endoftext|>",
237
  "split_special_tokens": false,
 
238
  "tokenizer_class": "Qwen2Tokenizer",
 
 
239
  "unk_token": null
240
  }