Hugging Face's logo

GaetanMichelet
/
Llama-31-8B_task-2_60-samples_config-2_full_auto

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
GaetanMichelet commited on
Commit
5751184
•
1 Parent(s): 001298b

Model save

Browse files
Files changed (5) hide show
  1. README.md +88 -0
  2. adapter_model.safetensors +1 -1
  3. all_results.json +9 -0
  4. train_results.json +9 -0
  5. trainer_state.json +488 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ license: llama3.1
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Llama-31-8B_task-2_60-samples_config-2_full_auto
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
+ # Llama-31-8B_task-2_60-samples_config-2_full_auto
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.0466
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
+ - distributed_type: multi-GPU
45
+ - gradient_accumulation_steps: 16
46
+ - total_train_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 50
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-------:|:----:|:---------------:|
56
+ | 1.5031 | 0.6957 | 2 | 1.5181 |
57
+ | 1.4986 | 1.7391 | 5 | 1.4719 |
58
+ | 1.4173 | 2.7826 | 8 | 1.3915 |
59
+ | 1.3451 | 3.8261 | 11 | 1.3186 |
60
+ | 1.2588 | 4.8696 | 14 | 1.2547 |
61
+ | 1.2035 | 5.9130 | 17 | 1.1920 |
62
+ | 1.1045 | 6.9565 | 20 | 1.1348 |
63
+ | 1.074 | 8.0 | 23 | 1.0886 |
64
+ | 1.0261 | 8.6957 | 25 | 1.0743 |
65
+ | 0.9858 | 9.7391 | 28 | 1.0616 |
66
+ | 0.9944 | 10.7826 | 31 | 1.0531 |
67
+ | 0.9706 | 11.8261 | 34 | 1.0463 |
68
+ | 0.9367 | 12.8696 | 37 | 1.0399 |
69
+ | 0.9372 | 13.9130 | 40 | 1.0353 |
70
+ | 0.9054 | 14.9565 | 43 | 1.0335 |
71
+ | 0.9095 | 16.0 | 46 | 1.0299 |
72
+ | 0.8691 | 16.6957 | 48 | 1.0291 |
73
+ | 0.8796 | 17.7391 | 51 | 1.0303 |
74
+ | 0.865 | 18.7826 | 54 | 1.0309 |
75
+ | 0.8473 | 19.8261 | 57 | 1.0353 |
76
+ | 0.8304 | 20.8696 | 60 | 1.0361 |
77
+ | 0.8259 | 21.9130 | 63 | 1.0386 |
78
+ | 0.8022 | 22.9565 | 66 | 1.0422 |
79
+ | 0.7948 | 24.0 | 69 | 1.0466 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - PEFT 0.12.0
85
+ - Transformers 4.44.0
86
+ - Pytorch 2.1.2+cu121
87
+ - Datasets 2.20.0
88
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa97c0c15b864338f6977c3fdf4d3e874b962aecb54a96a3219c5dbdc3a08f3c
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7bdf226c0f782c5217a4a73ac9d881bda9f9e48fb166abed2befbb6364e6d3
3
  size 167832240
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 24.0,
3
+ "total_flos": 1.1107117705252045e+17,
4
+ "train_loss": 1.030163572318312,
5
+ "train_runtime": 3968.8733,
6
+ "train_samples": 46,
7
+ "train_samples_per_second": 0.58,
8
+ "train_steps_per_second": 0.025
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 24.0,
3
+ "total_flos": 1.1107117705252045e+17,
4
+ "train_loss": 1.030163572318312,
5
+ "train_runtime": 3968.8733,
6
+ "train_samples": 46,
7
+ "train_samples_per_second": 0.58,
8
+ "train_steps_per_second": 0.025
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,488 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0291489362716675,
3
+ "best_model_checkpoint": "data/Llama-31-8B_task-2_60-samples_config-2_full_auto/checkpoint-48",
4
+ "epoch": 24.0,
5
+ "eval_steps": 500,
6
+ "global_step": 69,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.34782608695652173,
13
+ "grad_norm": 0.47617512941360474,
14
+ "learning_rate": 1e-05,
15
+ "loss": 1.5298,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.6956521739130435,
20
+ "grad_norm": 0.442937433719635,
21
+ "learning_rate": 2e-05,
22
+ "loss": 1.5031,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.6956521739130435,
27
+ "eval_loss": 1.5181411504745483,
28
+ "eval_runtime": 13.3343,
29
+ "eval_samples_per_second": 0.9,
30
+ "eval_steps_per_second": 0.9,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 1.391304347826087,
35
+ "grad_norm": 0.38801026344299316,
36
+ "learning_rate": 4e-05,
37
+ "loss": 1.4986,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 1.7391304347826086,
42
+ "eval_loss": 1.4718869924545288,
43
+ "eval_runtime": 13.339,
44
+ "eval_samples_per_second": 0.9,
45
+ "eval_steps_per_second": 0.9,
46
+ "step": 5
47
+ },
48
+ {
49
+ "epoch": 2.0869565217391304,
50
+ "grad_norm": 0.4467742145061493,
51
+ "learning_rate": 6e-05,
52
+ "loss": 1.4876,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 2.782608695652174,
57
+ "grad_norm": 0.39712953567504883,
58
+ "learning_rate": 8e-05,
59
+ "loss": 1.4173,
60
+ "step": 8
61
+ },
62
+ {
63
+ "epoch": 2.782608695652174,
64
+ "eval_loss": 1.3914693593978882,
65
+ "eval_runtime": 13.3356,
66
+ "eval_samples_per_second": 0.9,
67
+ "eval_steps_per_second": 0.9,
68
+ "step": 8
69
+ },
70
+ {
71
+ "epoch": 3.4782608695652173,
72
+ "grad_norm": 0.29091253876686096,
73
+ "learning_rate": 0.0001,
74
+ "loss": 1.3451,
75
+ "step": 10
76
+ },
77
+ {
78
+ "epoch": 3.8260869565217392,
79
+ "eval_loss": 1.3186070919036865,
80
+ "eval_runtime": 13.3314,
81
+ "eval_samples_per_second": 0.9,
82
+ "eval_steps_per_second": 0.9,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 4.173913043478261,
87
+ "grad_norm": 0.22598174214363098,
88
+ "learning_rate": 9.987820251299122e-05,
89
+ "loss": 1.3144,
90
+ "step": 12
91
+ },
92
+ {
93
+ "epoch": 4.869565217391305,
94
+ "grad_norm": 0.2439185380935669,
95
+ "learning_rate": 9.951340343707852e-05,
96
+ "loss": 1.2588,
97
+ "step": 14
98
+ },
99
+ {
100
+ "epoch": 4.869565217391305,
101
+ "eval_loss": 1.2547359466552734,
102
+ "eval_runtime": 13.3342,
103
+ "eval_samples_per_second": 0.9,
104
+ "eval_steps_per_second": 0.9,
105
+ "step": 14
106
+ },
107
+ {
108
+ "epoch": 5.565217391304348,
109
+ "grad_norm": 0.21214520931243896,
110
+ "learning_rate": 9.890738003669029e-05,
111
+ "loss": 1.2035,
112
+ "step": 16
113
+ },
114
+ {
115
+ "epoch": 5.913043478260869,
116
+ "eval_loss": 1.1919747591018677,
117
+ "eval_runtime": 13.332,
118
+ "eval_samples_per_second": 0.9,
119
+ "eval_steps_per_second": 0.9,
120
+ "step": 17
121
+ },
122
+ {
123
+ "epoch": 6.260869565217392,
124
+ "grad_norm": 0.22111687064170837,
125
+ "learning_rate": 9.806308479691595e-05,
126
+ "loss": 1.1523,
127
+ "step": 18
128
+ },
129
+ {
130
+ "epoch": 6.956521739130435,
131
+ "grad_norm": 0.23274613916873932,
132
+ "learning_rate": 9.698463103929542e-05,
133
+ "loss": 1.1045,
134
+ "step": 20
135
+ },
136
+ {
137
+ "epoch": 6.956521739130435,
138
+ "eval_loss": 1.1348336935043335,
139
+ "eval_runtime": 13.3318,
140
+ "eval_samples_per_second": 0.9,
141
+ "eval_steps_per_second": 0.9,
142
+ "step": 20
143
+ },
144
+ {
145
+ "epoch": 7.6521739130434785,
146
+ "grad_norm": 0.2069660723209381,
147
+ "learning_rate": 9.567727288213005e-05,
148
+ "loss": 1.074,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_loss": 1.0885711908340454,
154
+ "eval_runtime": 13.3353,
155
+ "eval_samples_per_second": 0.9,
156
+ "eval_steps_per_second": 0.9,
157
+ "step": 23
158
+ },
159
+ {
160
+ "epoch": 8.347826086956522,
161
+ "grad_norm": 0.18615713715553284,
162
+ "learning_rate": 9.414737964294636e-05,
163
+ "loss": 1.0261,
164
+ "step": 24
165
+ },
166
+ {
167
+ "epoch": 8.695652173913043,
168
+ "eval_loss": 1.0742846727371216,
169
+ "eval_runtime": 13.3285,
170
+ "eval_samples_per_second": 0.9,
171
+ "eval_steps_per_second": 0.9,
172
+ "step": 25
173
+ },
174
+ {
175
+ "epoch": 9.043478260869565,
176
+ "grad_norm": 0.13092510402202606,
177
+ "learning_rate": 9.24024048078213e-05,
178
+ "loss": 1.0054,
179
+ "step": 26
180
+ },
181
+ {
182
+ "epoch": 9.73913043478261,
183
+ "grad_norm": 0.12971077859401703,
184
+ "learning_rate": 9.045084971874738e-05,
185
+ "loss": 0.9858,
186
+ "step": 28
187
+ },
188
+ {
189
+ "epoch": 9.73913043478261,
190
+ "eval_loss": 1.0615901947021484,
191
+ "eval_runtime": 13.3324,
192
+ "eval_samples_per_second": 0.9,
193
+ "eval_steps_per_second": 0.9,
194
+ "step": 28
195
+ },
196
+ {
197
+ "epoch": 10.434782608695652,
198
+ "grad_norm": 0.11712505668401718,
199
+ "learning_rate": 8.83022221559489e-05,
200
+ "loss": 0.9944,
201
+ "step": 30
202
+ },
203
+ {
204
+ "epoch": 10.782608695652174,
205
+ "eval_loss": 1.05305016040802,
206
+ "eval_runtime": 13.3316,
207
+ "eval_samples_per_second": 0.9,
208
+ "eval_steps_per_second": 0.9,
209
+ "step": 31
210
+ },
211
+ {
212
+ "epoch": 11.130434782608695,
213
+ "grad_norm": 0.13746364414691925,
214
+ "learning_rate": 8.596699001693255e-05,
215
+ "loss": 0.9476,
216
+ "step": 32
217
+ },
218
+ {
219
+ "epoch": 11.826086956521738,
220
+ "grad_norm": 0.11521344631910324,
221
+ "learning_rate": 8.345653031794292e-05,
222
+ "loss": 0.9706,
223
+ "step": 34
224
+ },
225
+ {
226
+ "epoch": 11.826086956521738,
227
+ "eval_loss": 1.0463008880615234,
228
+ "eval_runtime": 13.3346,
229
+ "eval_samples_per_second": 0.9,
230
+ "eval_steps_per_second": 0.9,
231
+ "step": 34
232
+ },
233
+ {
234
+ "epoch": 12.521739130434783,
235
+ "grad_norm": 0.1206565722823143,
236
+ "learning_rate": 8.07830737662829e-05,
237
+ "loss": 0.9367,
238
+ "step": 36
239
+ },
240
+ {
241
+ "epoch": 12.869565217391305,
242
+ "eval_loss": 1.0399166345596313,
243
+ "eval_runtime": 13.3354,
244
+ "eval_samples_per_second": 0.9,
245
+ "eval_steps_per_second": 0.9,
246
+ "step": 37
247
+ },
248
+ {
249
+ "epoch": 13.217391304347826,
250
+ "grad_norm": 0.126475527882576,
251
+ "learning_rate": 7.795964517353735e-05,
252
+ "loss": 0.9462,
253
+ "step": 38
254
+ },
255
+ {
256
+ "epoch": 13.91304347826087,
257
+ "grad_norm": 0.1225828230381012,
258
+ "learning_rate": 7.500000000000001e-05,
259
+ "loss": 0.9372,
260
+ "step": 40
261
+ },
262
+ {
263
+ "epoch": 13.91304347826087,
264
+ "eval_loss": 1.0352905988693237,
265
+ "eval_runtime": 13.3325,
266
+ "eval_samples_per_second": 0.9,
267
+ "eval_steps_per_second": 0.9,
268
+ "step": 40
269
+ },
270
+ {
271
+ "epoch": 14.608695652173914,
272
+ "grad_norm": 0.12201306223869324,
273
+ "learning_rate": 7.191855733945387e-05,
274
+ "loss": 0.9054,
275
+ "step": 42
276
+ },
277
+ {
278
+ "epoch": 14.956521739130435,
279
+ "eval_loss": 1.0334912538528442,
280
+ "eval_runtime": 13.3321,
281
+ "eval_samples_per_second": 0.9,
282
+ "eval_steps_per_second": 0.9,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 15.304347826086957,
287
+ "grad_norm": 0.13440456986427307,
288
+ "learning_rate": 6.873032967079561e-05,
289
+ "loss": 0.911,
290
+ "step": 44
291
+ },
292
+ {
293
+ "epoch": 16.0,
294
+ "grad_norm": 0.12997311353683472,
295
+ "learning_rate": 6.545084971874738e-05,
296
+ "loss": 0.9095,
297
+ "step": 46
298
+ },
299
+ {
300
+ "epoch": 16.0,
301
+ "eval_loss": 1.029860019683838,
302
+ "eval_runtime": 13.3341,
303
+ "eval_samples_per_second": 0.9,
304
+ "eval_steps_per_second": 0.9,
305
+ "step": 46
306
+ },
307
+ {
308
+ "epoch": 16.695652173913043,
309
+ "grad_norm": 0.14405840635299683,
310
+ "learning_rate": 6.209609477998338e-05,
311
+ "loss": 0.8691,
312
+ "step": 48
313
+ },
314
+ {
315
+ "epoch": 16.695652173913043,
316
+ "eval_loss": 1.0291489362716675,
317
+ "eval_runtime": 13.3349,
318
+ "eval_samples_per_second": 0.9,
319
+ "eval_steps_per_second": 0.9,
320
+ "step": 48
321
+ },
322
+ {
323
+ "epoch": 17.391304347826086,
324
+ "grad_norm": 0.14434926211833954,
325
+ "learning_rate": 5.868240888334653e-05,
326
+ "loss": 0.8796,
327
+ "step": 50
328
+ },
329
+ {
330
+ "epoch": 17.73913043478261,
331
+ "eval_loss": 1.0302618741989136,
332
+ "eval_runtime": 13.3338,
333
+ "eval_samples_per_second": 0.9,
334
+ "eval_steps_per_second": 0.9,
335
+ "step": 51
336
+ },
337
+ {
338
+ "epoch": 18.08695652173913,
339
+ "grad_norm": 0.13976463675498962,
340
+ "learning_rate": 5.522642316338268e-05,
341
+ "loss": 0.8911,
342
+ "step": 52
343
+ },
344
+ {
345
+ "epoch": 18.782608695652176,
346
+ "grad_norm": 0.14080481231212616,
347
+ "learning_rate": 5.174497483512506e-05,
348
+ "loss": 0.865,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 18.782608695652176,
353
+ "eval_loss": 1.030932068824768,
354
+ "eval_runtime": 13.3346,
355
+ "eval_samples_per_second": 0.9,
356
+ "eval_steps_per_second": 0.9,
357
+ "step": 54
358
+ },
359
+ {
360
+ "epoch": 19.47826086956522,
361
+ "grad_norm": 0.15428860485553741,
362
+ "learning_rate": 4.825502516487497e-05,
363
+ "loss": 0.8473,
364
+ "step": 56
365
+ },
366
+ {
367
+ "epoch": 19.82608695652174,
368
+ "eval_loss": 1.035332202911377,
369
+ "eval_runtime": 13.3375,
370
+ "eval_samples_per_second": 0.9,
371
+ "eval_steps_per_second": 0.9,
372
+ "step": 57
373
+ },
374
+ {
375
+ "epoch": 20.17391304347826,
376
+ "grad_norm": 0.1614825427532196,
377
+ "learning_rate": 4.477357683661734e-05,
378
+ "loss": 0.8544,
379
+ "step": 58
380
+ },
381
+ {
382
+ "epoch": 20.869565217391305,
383
+ "grad_norm": 0.1666206270456314,
384
+ "learning_rate": 4.131759111665349e-05,
385
+ "loss": 0.8304,
386
+ "step": 60
387
+ },
388
+ {
389
+ "epoch": 20.869565217391305,
390
+ "eval_loss": 1.0361390113830566,
391
+ "eval_runtime": 13.3356,
392
+ "eval_samples_per_second": 0.9,
393
+ "eval_steps_per_second": 0.9,
394
+ "step": 60
395
+ },
396
+ {
397
+ "epoch": 21.565217391304348,
398
+ "grad_norm": 0.16533945500850677,
399
+ "learning_rate": 3.790390522001662e-05,
400
+ "loss": 0.8259,
401
+ "step": 62
402
+ },
403
+ {
404
+ "epoch": 21.91304347826087,
405
+ "eval_loss": 1.0386301279067993,
406
+ "eval_runtime": 13.3309,
407
+ "eval_samples_per_second": 0.9,
408
+ "eval_steps_per_second": 0.9,
409
+ "step": 63
410
+ },
411
+ {
412
+ "epoch": 22.26086956521739,
413
+ "grad_norm": 0.17483672499656677,
414
+ "learning_rate": 3.4549150281252636e-05,
415
+ "loss": 0.8189,
416
+ "step": 64
417
+ },
418
+ {
419
+ "epoch": 22.956521739130434,
420
+ "grad_norm": 0.18155451118946075,
421
+ "learning_rate": 3.12696703292044e-05,
422
+ "loss": 0.8022,
423
+ "step": 66
424
+ },
425
+ {
426
+ "epoch": 22.956521739130434,
427
+ "eval_loss": 1.0422089099884033,
428
+ "eval_runtime": 13.3328,
429
+ "eval_samples_per_second": 0.9,
430
+ "eval_steps_per_second": 0.9,
431
+ "step": 66
432
+ },
433
+ {
434
+ "epoch": 23.652173913043477,
435
+ "grad_norm": 0.18215659260749817,
436
+ "learning_rate": 2.8081442660546125e-05,
437
+ "loss": 0.7948,
438
+ "step": 68
439
+ },
440
+ {
441
+ "epoch": 24.0,
442
+ "eval_loss": 1.04664945602417,
443
+ "eval_runtime": 13.3335,
444
+ "eval_samples_per_second": 0.9,
445
+ "eval_steps_per_second": 0.9,
446
+ "step": 69
447
+ },
448
+ {
449
+ "epoch": 24.0,
450
+ "step": 69,
451
+ "total_flos": 1.1107117705252045e+17,
452
+ "train_loss": 1.030163572318312,
453
+ "train_runtime": 3968.8733,
454
+ "train_samples_per_second": 0.58,
455
+ "train_steps_per_second": 0.025
456
+ }
457
+ ],
458
+ "logging_steps": 2,
459
+ "max_steps": 100,
460
+ "num_input_tokens_seen": 0,
461
+ "num_train_epochs": 50,
462
+ "save_steps": 25,
463
+ "stateful_callbacks": {
464
+ "EarlyStoppingCallback": {
465
+ "args": {
466
+ "early_stopping_patience": 7,
467
+ "early_stopping_threshold": 0.0
468
+ },
469
+ "attributes": {
470
+ "early_stopping_patience_counter": 0
471
+ }
472
+ },
473
+ "TrainerControl": {
474
+ "args": {
475
+ "should_epoch_stop": false,
476
+ "should_evaluate": false,
477
+ "should_log": false,
478
+ "should_save": true,
479
+ "should_training_stop": true
480
+ },
481
+ "attributes": {}
482
+ }
483
+ },
484
+ "total_flos": 1.1107117705252045e+17,
485
+ "train_batch_size": 1,
486
+ "trial_name": null,
487
+ "trial_params": null
488
+ }