Hugging Face's logo

tttx
/
problem-10-upgrade-torch-ttt-step-1

PEFT
Safetensors
qwen2
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Community
aadityap commited on
Commit
145b861
·
verified ·
1 Parent(s): 30a999f

Model save

Browse files
Files changed (4) hide show
  1. README.md +61 -0
  2. all_results.json +9 -0
  3. train_results.json +9 -0
  4. trainer_state.json +266 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: problem-10-upgrade-torch-ttt-step-1
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
+ # problem-10-upgrade-torch-ttt-step-1
18
+
19
+ This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on an unknown dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 16
45
+ - total_eval_batch_size: 8
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: 2
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.13.2
58
+ - Transformers 4.47.0.dev0
59
+ - Pytorch 2.4.0+cu121
60
+ - Datasets 3.1.0
61
+ - Tokenizers 0.20.3
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 614948268933120.0,
4
+ "train_loss": 0.14902637084014714,
5
+ "train_runtime": 1084.9601,
6
+ "train_samples": 250,
7
+ "train_samples_per_second": 0.461,
8
+ "train_steps_per_second": 0.029
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 614948268933120.0,
4
+ "train_loss": 0.14902637084014714,
5
+ "train_runtime": 1084.9601,
6
+ "train_samples": 250,
7
+ "train_samples_per_second": 0.461,
8
+ "train_steps_per_second": 0.029
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 32,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0625,
13
+ "grad_norm": 0.04113317007945081,
14
+ "learning_rate": 1.25e-05,
15
+ "loss": 0.1767,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.125,
20
+ "grad_norm": 0.042219935316768153,
21
+ "learning_rate": 2.5e-05,
22
+ "loss": 0.188,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.1875,
27
+ "grad_norm": 0.04292721294346761,
28
+ "learning_rate": 3.7500000000000003e-05,
29
+ "loss": 0.1893,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.25,
34
+ "grad_norm": 0.04056717413915702,
35
+ "learning_rate": 5e-05,
36
+ "loss": 0.187,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.3125,
41
+ "grad_norm": 0.04330821122698837,
42
+ "learning_rate": 4.984280524733107e-05,
43
+ "loss": 0.1753,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.375,
48
+ "grad_norm": 0.0452810422313244,
49
+ "learning_rate": 4.937319780454559e-05,
50
+ "loss": 0.1875,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.4375,
55
+ "grad_norm": 0.039289995019635204,
56
+ "learning_rate": 4.8597083257709194e-05,
57
+ "loss": 0.1687,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5,
62
+ "grad_norm": 0.027002440254188315,
63
+ "learning_rate": 4.752422169756048e-05,
64
+ "loss": 0.1663,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.5625,
69
+ "grad_norm": 0.02494347654011703,
70
+ "learning_rate": 4.6168104980707107e-05,
71
+ "loss": 0.1695,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.625,
76
+ "grad_norm": 0.028920303836423092,
77
+ "learning_rate": 4.454578706170075e-05,
78
+ "loss": 0.1579,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.6875,
83
+ "grad_norm": 0.03943765297659361,
84
+ "learning_rate": 4.267766952966369e-05,
85
+ "loss": 0.1568,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.75,
90
+ "grad_norm": 0.039468128072595324,
91
+ "learning_rate": 4.058724504646834e-05,
92
+ "loss": 0.1499,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.8125,
97
+ "grad_norm": 0.04907120045337006,
98
+ "learning_rate": 3.830080191288342e-05,
99
+ "loss": 0.1463,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.875,
104
+ "grad_norm": 0.03536941711454614,
105
+ "learning_rate": 3.5847093477938956e-05,
106
+ "loss": 0.1513,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.9375,
111
+ "grad_norm": 0.023098349626014137,
112
+ "learning_rate": 3.3256976548879184e-05,
113
+ "loss": 0.1378,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.0,
118
+ "grad_norm": 0.017512339127206115,
119
+ "learning_rate": 3.056302334890786e-05,
120
+ "loss": 0.1374,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.0625,
125
+ "grad_norm": 0.017368083265511706,
126
+ "learning_rate": 2.7799111902582696e-05,
127
+ "loss": 0.1505,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.125,
132
+ "grad_norm": 0.016989863234842244,
133
+ "learning_rate": 2.5e-05,
134
+ "loss": 0.1349,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.1875,
139
+ "grad_norm": 0.01845190519100938,
140
+ "learning_rate": 2.2200888097417307e-05,
141
+ "loss": 0.1356,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.25,
146
+ "grad_norm": 0.021100699063456414,
147
+ "learning_rate": 1.9436976651092144e-05,
148
+ "loss": 0.136,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.3125,
153
+ "grad_norm": 0.018945233559077897,
154
+ "learning_rate": 1.6743023451120832e-05,
155
+ "loss": 0.1453,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.375,
160
+ "grad_norm": 0.019023748911866034,
161
+ "learning_rate": 1.4152906522061048e-05,
162
+ "loss": 0.1297,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.4375,
167
+ "grad_norm": 0.01983379100230869,
168
+ "learning_rate": 1.1699198087116589e-05,
169
+ "loss": 0.1288,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.5,
174
+ "grad_norm": 0.020004728526161076,
175
+ "learning_rate": 9.412754953531663e-06,
176
+ "loss": 0.1372,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.5625,
181
+ "grad_norm": 0.018644802377325877,
182
+ "learning_rate": 7.3223304703363135e-06,
183
+ "loss": 0.1264,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.625,
188
+ "grad_norm": 0.018974115353534597,
189
+ "learning_rate": 5.454212938299255e-06,
190
+ "loss": 0.1223,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.6875,
195
+ "grad_norm": 0.02101774905754192,
196
+ "learning_rate": 3.831895019292897e-06,
197
+ "loss": 0.1242,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 1.75,
202
+ "grad_norm": 0.020105790792392823,
203
+ "learning_rate": 2.475778302439524e-06,
204
+ "loss": 0.1253,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 1.8125,
209
+ "grad_norm": 0.02049360956396613,
210
+ "learning_rate": 1.4029167422908107e-06,
211
+ "loss": 0.1437,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 1.875,
216
+ "grad_norm": 0.022791100110954515,
217
+ "learning_rate": 6.268021954544096e-07,
218
+ "loss": 0.1283,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 1.9375,
223
+ "grad_norm": 0.018080427643756062,
224
+ "learning_rate": 1.571947526689349e-07,
225
+ "loss": 0.1283,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.0,
230
+ "grad_norm": 0.01817465286562608,
231
+ "learning_rate": 0.0,
232
+ "loss": 0.1267,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.0,
237
+ "step": 32,
238
+ "total_flos": 614948268933120.0,
239
+ "train_loss": 0.14902637084014714,
240
+ "train_runtime": 1084.9601,
241
+ "train_samples_per_second": 0.461,
242
+ "train_steps_per_second": 0.029
243
+ }
244
+ ],
245
+ "logging_steps": 1,
246
+ "max_steps": 32,
247
+ "num_input_tokens_seen": 0,
248
+ "num_train_epochs": 2,
249
+ "save_steps": 500,
250
+ "stateful_callbacks": {
251
+ "TrainerControl": {
252
+ "args": {
253
+ "should_epoch_stop": false,
254
+ "should_evaluate": false,
255
+ "should_log": false,
256
+ "should_save": true,
257
+ "should_training_stop": true
258
+ },
259
+ "attributes": {}
260
+ }
261
+ },
262
+ "total_flos": 614948268933120.0,
263
+ "train_batch_size": 2,
264
+ "trial_name": null,
265
+ "trial_params": null
266
+ }