sedrickkeh commited on
Commit
679b3a3
·
verified ·
1 Parent(s): 598e11a

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +252 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: difficulty_sorting_easy_seed_math
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # difficulty_sorting_easy_seed_math
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: difficulty_sorting_easy_seed_math
 
16
 
17
  # difficulty_sorting_easy_seed_math
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/difficulty_sorting_easy_seed_math dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.857142857142857,
3
+ "total_flos": 18265262981120.0,
4
+ "train_loss": 0.8729538798332215,
5
+ "train_runtime": 1411.7731,
6
+ "train_samples_per_second": 2.125,
7
+ "train_steps_per_second": 0.021
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.857142857142857,
3
+ "total_flos": 18265262981120.0,
4
+ "train_loss": 0.8729538798332215,
5
+ "train_runtime": 1411.7731,
6
+ "train_samples_per_second": 2.125,
7
+ "train_steps_per_second": 0.021
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,252 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.857142857142857,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09523809523809523,
13
+ "grad_norm": 7.422213554382324,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 1.1578,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.19047619047619047,
20
+ "grad_norm": 7.41135835647583,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 1.1462,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.2857142857142857,
27
+ "grad_norm": 6.774180889129639,
28
+ "learning_rate": 1e-05,
29
+ "loss": 1.1284,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.38095238095238093,
34
+ "grad_norm": 3.161284923553467,
35
+ "learning_rate": 9.966191788709716e-06,
36
+ "loss": 0.9639,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.47619047619047616,
41
+ "grad_norm": 5.829282283782959,
42
+ "learning_rate": 9.86522435289912e-06,
43
+ "loss": 0.9276,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.5714285714285714,
48
+ "grad_norm": 6.1610026359558105,
49
+ "learning_rate": 9.698463103929542e-06,
50
+ "loss": 0.9728,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.6666666666666666,
55
+ "grad_norm": 5.902828693389893,
56
+ "learning_rate": 9.468163201617063e-06,
57
+ "loss": 0.9381,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.7619047619047619,
62
+ "grad_norm": 3.9850664138793945,
63
+ "learning_rate": 9.177439057064684e-06,
64
+ "loss": 0.8628,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.8571428571428571,
69
+ "grad_norm": 3.0481746196746826,
70
+ "learning_rate": 8.83022221559489e-06,
71
+ "loss": 0.8703,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.9523809523809523,
76
+ "grad_norm": 2.660543918609619,
77
+ "learning_rate": 8.43120818934367e-06,
78
+ "loss": 0.8566,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.0476190476190477,
83
+ "grad_norm": 4.1810712814331055,
84
+ "learning_rate": 7.985792958513932e-06,
85
+ "loss": 1.2228,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.1428571428571428,
90
+ "grad_norm": 1.5916192531585693,
91
+ "learning_rate": 7.500000000000001e-06,
92
+ "loss": 0.8184,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.2380952380952381,
97
+ "grad_norm": 1.6117875576019287,
98
+ "learning_rate": 6.980398830195785e-06,
99
+ "loss": 0.7946,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.3333333333333333,
104
+ "grad_norm": 1.920135736465454,
105
+ "learning_rate": 6.434016163555452e-06,
106
+ "loss": 0.854,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.4285714285714286,
111
+ "grad_norm": 1.4394092559814453,
112
+ "learning_rate": 5.8682408883346535e-06,
113
+ "loss": 0.7038,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.5238095238095237,
118
+ "grad_norm": 1.194329023361206,
119
+ "learning_rate": 5.290724144552379e-06,
120
+ "loss": 0.8028,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.619047619047619,
125
+ "grad_norm": 0.8754922747612,
126
+ "learning_rate": 4.7092758554476215e-06,
127
+ "loss": 0.8274,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.7142857142857144,
132
+ "grad_norm": 1.3135168552398682,
133
+ "learning_rate": 4.131759111665349e-06,
134
+ "loss": 0.9132,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.8095238095238095,
139
+ "grad_norm": 0.9727711081504822,
140
+ "learning_rate": 3.5659838364445505e-06,
141
+ "loss": 0.7172,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.9047619047619047,
146
+ "grad_norm": 0.8970598578453064,
147
+ "learning_rate": 3.019601169804216e-06,
148
+ "loss": 0.856,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.0,
153
+ "grad_norm": 1.207399606704712,
154
+ "learning_rate": 2.5000000000000015e-06,
155
+ "loss": 1.0469,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.0952380952380953,
160
+ "grad_norm": 0.7883663177490234,
161
+ "learning_rate": 2.0142070414860704e-06,
162
+ "loss": 0.7511,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 2.1904761904761907,
167
+ "grad_norm": 0.8058299422264099,
168
+ "learning_rate": 1.5687918106563326e-06,
169
+ "loss": 0.6867,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 2.2857142857142856,
174
+ "grad_norm": 0.7209040522575378,
175
+ "learning_rate": 1.1697777844051105e-06,
176
+ "loss": 0.7337,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 2.380952380952381,
181
+ "grad_norm": 0.6205177307128906,
182
+ "learning_rate": 8.225609429353187e-07,
183
+ "loss": 0.8412,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 2.4761904761904763,
188
+ "grad_norm": 0.5686010718345642,
189
+ "learning_rate": 5.318367983829393e-07,
190
+ "loss": 0.7219,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 2.571428571428571,
195
+ "grad_norm": 0.5568851828575134,
196
+ "learning_rate": 3.015368960704584e-07,
197
+ "loss": 0.7787,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.6666666666666665,
202
+ "grad_norm": 0.5523302555084229,
203
+ "learning_rate": 1.3477564710088097e-07,
204
+ "loss": 0.8023,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.761904761904762,
209
+ "grad_norm": 0.5608894228935242,
210
+ "learning_rate": 3.3808211290284886e-08,
211
+ "loss": 0.7005,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.857142857142857,
216
+ "grad_norm": 0.5216653347015381,
217
+ "learning_rate": 0.0,
218
+ "loss": 0.7909,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.857142857142857,
223
+ "step": 30,
224
+ "total_flos": 18265262981120.0,
225
+ "train_loss": 0.8729538798332215,
226
+ "train_runtime": 1411.7731,
227
+ "train_samples_per_second": 2.125,
228
+ "train_steps_per_second": 0.021
229
+ }
230
+ ],
231
+ "logging_steps": 1.0,
232
+ "max_steps": 30,
233
+ "num_input_tokens_seen": 0,
234
+ "num_train_epochs": 3,
235
+ "save_steps": 500,
236
+ "stateful_callbacks": {
237
+ "TrainerControl": {
238
+ "args": {
239
+ "should_epoch_stop": false,
240
+ "should_evaluate": false,
241
+ "should_log": false,
242
+ "should_save": true,
243
+ "should_training_stop": true
244
+ },
245
+ "attributes": {}
246
+ }
247
+ },
248
+ "total_flos": 18265262981120.0,
249
+ "train_batch_size": 1,
250
+ "trial_name": null,
251
+ "trial_params": null
252
+ }
training_loss.png ADDED