sedrickkeh commited on
Commit
c4b4238
·
verified ·
1 Parent(s): 28c702d

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: top_15_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_15_ranking_stackexchange
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.8023
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: top_15_ranking_stackexchange
 
16
 
17
  # top_15_ranking_stackexchange
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/top_15_ranking_stackexchange dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.8023
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9986194201564658,
3
+ "eval_loss": 0.8022779822349548,
4
+ "eval_runtime": 581.0134,
5
+ "eval_samples_per_second": 25.196,
6
+ "eval_steps_per_second": 0.394,
7
+ "total_flos": 2728426293166080.0,
8
+ "train_loss": 0.7854923086710837,
9
+ "train_runtime": 95950.7779,
10
+ "train_samples_per_second": 8.696,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9986194201564658,
3
+ "eval_loss": 0.8022779822349548,
4
+ "eval_runtime": 581.0134,
5
+ "eval_samples_per_second": 25.196,
6
+ "eval_steps_per_second": 0.394
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9986194201564658,
3
+ "total_flos": 2728426293166080.0,
4
+ "train_loss": 0.7854923086710837,
5
+ "train_runtime": 95950.7779,
6
+ "train_samples_per_second": 8.696,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9986194201564658,
5
+ "eval_steps": 500,
6
+ "global_step": 1629,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01840773124712379,
13
+ "grad_norm": 11.495686687617598,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0655,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03681546249424758,
20
+ "grad_norm": 5.414035603637067,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9662,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05522319374137138,
27
+ "grad_norm": 1.7180886181350892,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.9362,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.07363092498849516,
34
+ "grad_norm": 1.795533021117465,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.922,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.09203865623561897,
41
+ "grad_norm": 1.1665142084019502,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.9051,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.11044638748274276,
48
+ "grad_norm": 0.7289439832404309,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8929,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.12885411872986655,
55
+ "grad_norm": 0.9030368777254644,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8821,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.14726184997699032,
62
+ "grad_norm": 0.9425682568991275,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8734,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.16566958122411413,
69
+ "grad_norm": 0.7354391468644993,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8738,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.18407731247123793,
76
+ "grad_norm": 0.6651957250464282,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8724,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2024850437183617,
83
+ "grad_norm": 0.7545639567673004,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8644,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2208927749654855,
90
+ "grad_norm": 0.6185140044329701,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8613,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2393005062126093,
97
+ "grad_norm": 0.6591986758093533,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.8556,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2577082374597331,
104
+ "grad_norm": 0.8491087509246042,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.8539,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.2761159687068569,
111
+ "grad_norm": 0.6531629448196006,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.8562,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.29452369995398064,
118
+ "grad_norm": 0.8438280033874832,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.852,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.31293143120110445,
125
+ "grad_norm": 0.559902696500108,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.8443,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.33133916244822825,
132
+ "grad_norm": 0.5581328727424005,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.8469,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.34974689369535206,
139
+ "grad_norm": 0.6723674628868884,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.8423,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.36815462494247586,
146
+ "grad_norm": 0.5911235299913716,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.8422,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.3865623561895996,
153
+ "grad_norm": 0.6326816480779326,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.8451,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4049700874367234,
160
+ "grad_norm": 0.545823585506014,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.8405,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.4233778186838472,
167
+ "grad_norm": 0.8306189189623202,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.8359,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.441785549930971,
174
+ "grad_norm": 0.7302046699439101,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.843,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.4601932811780948,
181
+ "grad_norm": 0.6097696283103196,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.8442,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4786010124252186,
188
+ "grad_norm": 0.5520157322910384,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.8345,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4970087436723424,
195
+ "grad_norm": 0.8387750998122173,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.8402,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5154164749194662,
202
+ "grad_norm": 0.5831898004809442,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.8393,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.53382420616659,
209
+ "grad_norm": 0.5522040188439342,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.8326,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5522319374137138,
216
+ "grad_norm": 0.5689291080618771,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.8343,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5706396686608376,
223
+ "grad_norm": 0.5585963481358173,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.8285,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5890473999079613,
230
+ "grad_norm": 0.6246406440833802,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.8303,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.6074551311550851,
237
+ "grad_norm": 0.5256671010894053,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.8325,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.6258628624022089,
244
+ "grad_norm": 0.633273666711919,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.8302,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.6442705936493327,
251
+ "grad_norm": 0.8071524979584527,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.8268,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6626783248964565,
258
+ "grad_norm": 0.6298754293534956,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.8274,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6810860561435803,
265
+ "grad_norm": 0.580085422648526,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.8249,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6994937873907041,
272
+ "grad_norm": 0.5237120595233268,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.8267,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.7179015186378279,
279
+ "grad_norm": 0.5205621404905915,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.8281,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.7363092498849517,
286
+ "grad_norm": 0.5609961443767165,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.8294,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.7547169811320755,
293
+ "grad_norm": 0.8113242076381498,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.8294,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7731247123791992,
300
+ "grad_norm": 0.6263734997124686,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.8222,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.791532443626323,
307
+ "grad_norm": 0.5533838940453765,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.8256,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.8099401748734468,
314
+ "grad_norm": 0.5686721562918683,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.8173,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.8283479061205706,
321
+ "grad_norm": 0.48436281066991915,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.8269,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.8467556373676944,
328
+ "grad_norm": 0.5577482524512647,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.8249,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.8651633686148182,
335
+ "grad_norm": 0.5643149386241082,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.8191,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.883571099861942,
342
+ "grad_norm": 0.6614121315928284,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.8176,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.9019788311090658,
349
+ "grad_norm": 0.4888549298926769,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.8183,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.9203865623561897,
356
+ "grad_norm": 0.5740805075207074,
357
+ "learning_rate": 5e-06,
358
+ "loss": 0.8206,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.9387942936033133,
363
+ "grad_norm": 0.49345078862695535,
364
+ "learning_rate": 5e-06,
365
+ "loss": 0.8216,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.9572020248504371,
370
+ "grad_norm": 0.4895624955783029,
371
+ "learning_rate": 5e-06,
372
+ "loss": 0.815,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.975609756097561,
377
+ "grad_norm": 0.5078514624048458,
378
+ "learning_rate": 5e-06,
379
+ "loss": 0.8224,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9940174873446848,
384
+ "grad_norm": 0.49323310639247003,
385
+ "learning_rate": 5e-06,
386
+ "loss": 0.8223,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9995398067188219,
391
+ "eval_loss": 0.8175484538078308,
392
+ "eval_runtime": 577.4655,
393
+ "eval_samples_per_second": 25.35,
394
+ "eval_steps_per_second": 0.397,
395
+ "step": 543
396
+ },
397
+ {
398
+ "epoch": 1.0124252185918086,
399
+ "grad_norm": 0.6931115032757318,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.8486,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.0308329498389324,
406
+ "grad_norm": 0.6510623966802886,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.7745,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.0492406810860562,
413
+ "grad_norm": 0.6616327762994352,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.7798,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.06764841233318,
420
+ "grad_norm": 0.5775037016510299,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.7753,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.0860561435803038,
427
+ "grad_norm": 0.5707136558272301,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.7769,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.1044638748274276,
434
+ "grad_norm": 0.7284560313205218,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.7765,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.1228716060745514,
441
+ "grad_norm": 0.6310103758378874,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.777,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.1412793373216752,
448
+ "grad_norm": 0.515513316541971,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.7736,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.159687068568799,
455
+ "grad_norm": 0.5492113148126704,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.7756,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.1780947998159226,
462
+ "grad_norm": 0.5228104705222637,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.7764,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.1965025310630466,
469
+ "grad_norm": 0.5035050506284052,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.7734,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.2149102623101702,
476
+ "grad_norm": 0.8068687083136943,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.7757,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.233317993557294,
483
+ "grad_norm": 0.5653783132955,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.7746,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.2517257248044178,
490
+ "grad_norm": 0.6662032923342155,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.7744,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.2701334560515416,
497
+ "grad_norm": 0.5501136952057387,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.7727,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.2885411872986654,
504
+ "grad_norm": 0.608620492574905,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.7757,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.3069489185457892,
511
+ "grad_norm": 0.6052951493689271,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.7738,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.325356649792913,
518
+ "grad_norm": 0.6410940625081331,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.7757,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.3437643810400368,
525
+ "grad_norm": 0.5699137555795393,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.7805,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.3621721122871606,
532
+ "grad_norm": 0.5068184484173434,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.7775,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.3805798435342844,
539
+ "grad_norm": 0.4931418205462196,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.7737,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.3989875747814082,
546
+ "grad_norm": 0.5408228174235898,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.7734,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.417395306028532,
553
+ "grad_norm": 0.5380361882479816,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.7753,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.4358030372756558,
560
+ "grad_norm": 0.5840217555045797,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.7747,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.4542107685227796,
567
+ "grad_norm": 0.5362828182722048,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.776,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.4726184997699034,
574
+ "grad_norm": 0.552799353811648,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.7758,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.491026231017027,
581
+ "grad_norm": 0.47793200905569844,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.7751,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.509433962264151,
588
+ "grad_norm": 0.5685715941391194,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.7764,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.5278416935112746,
595
+ "grad_norm": 0.5141942789784186,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.7718,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.5462494247583987,
602
+ "grad_norm": 0.5951320223055838,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.7756,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.5646571560055222,
609
+ "grad_norm": 0.5881625341228633,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.7752,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.5830648872526463,
616
+ "grad_norm": 0.5384295675334821,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.7739,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.6014726184997699,
623
+ "grad_norm": 0.6339064986712926,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.7767,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.6198803497468937,
630
+ "grad_norm": 0.5756524997905831,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.7732,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.6382880809940175,
637
+ "grad_norm": 0.49759423895450694,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.7713,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.6566958122411413,
644
+ "grad_norm": 0.5426358109496824,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.7713,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.675103543488265,
651
+ "grad_norm": 0.5703740061473311,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.7715,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.6935112747353889,
658
+ "grad_norm": 0.6756102849236832,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.7761,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.7119190059825127,
665
+ "grad_norm": 0.6603200364822771,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.7732,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.7303267372296365,
672
+ "grad_norm": 0.6519535812695805,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.7699,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.7487344684767603,
679
+ "grad_norm": 0.5892484328148301,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.7731,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.7671421997238839,
686
+ "grad_norm": 0.6054216291145197,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.7765,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.785549930971008,
693
+ "grad_norm": 0.5359072557829287,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.7694,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.8039576622181315,
700
+ "grad_norm": 0.48947344008413946,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.7716,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.8223653934652555,
707
+ "grad_norm": 0.5552327718140667,
708
+ "learning_rate": 5e-06,
709
+ "loss": 0.7715,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.840773124712379,
714
+ "grad_norm": 0.49129147603369394,
715
+ "learning_rate": 5e-06,
716
+ "loss": 0.7696,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.859180855959503,
721
+ "grad_norm": 0.6177309925844156,
722
+ "learning_rate": 5e-06,
723
+ "loss": 0.7753,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.8775885872066267,
728
+ "grad_norm": 0.556337075656538,
729
+ "learning_rate": 5e-06,
730
+ "loss": 0.7724,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.8959963184537507,
735
+ "grad_norm": 0.6337348248265403,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.7724,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.9144040497008743,
742
+ "grad_norm": 0.5237811675039271,
743
+ "learning_rate": 5e-06,
744
+ "loss": 0.7744,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.932811780947998,
749
+ "grad_norm": 0.493087641177435,
750
+ "learning_rate": 5e-06,
751
+ "loss": 0.7732,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.951219512195122,
756
+ "grad_norm": 0.5743317560990825,
757
+ "learning_rate": 5e-06,
758
+ "loss": 0.7738,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.9696272434422457,
763
+ "grad_norm": 0.6056942269519802,
764
+ "learning_rate": 5e-06,
765
+ "loss": 0.7731,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.9880349746893695,
770
+ "grad_norm": 0.5324789923627218,
771
+ "learning_rate": 5e-06,
772
+ "loss": 0.7689,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.9990796134376438,
777
+ "eval_loss": 0.8038221001625061,
778
+ "eval_runtime": 578.6774,
779
+ "eval_samples_per_second": 25.297,
780
+ "eval_steps_per_second": 0.396,
781
+ "step": 1086
782
+ },
783
+ {
784
+ "epoch": 2.0064427059364935,
785
+ "grad_norm": 0.7880104184820911,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.8114,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.024850437183617,
792
+ "grad_norm": 0.6486016931410004,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.7261,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.0432581684307407,
799
+ "grad_norm": 0.6854700908189261,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.7268,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.0616658996778647,
806
+ "grad_norm": 0.6011201615337006,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.7268,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.0800736309249883,
813
+ "grad_norm": 0.5369071090939471,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.7284,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.0984813621721123,
820
+ "grad_norm": 0.5656204024525643,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.725,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.116889093419236,
827
+ "grad_norm": 0.6303299238534352,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.7303,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.13529682466636,
834
+ "grad_norm": 0.5123557643767893,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.7289,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.1537045559134835,
841
+ "grad_norm": 0.5538382553645407,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.7279,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.1721122871606076,
848
+ "grad_norm": 0.5168659565290504,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.726,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.190520018407731,
855
+ "grad_norm": 0.5149057222016729,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.7298,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.208927749654855,
862
+ "grad_norm": 0.5554533749205715,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.7287,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.2273354809019787,
869
+ "grad_norm": 0.5330943850283596,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.7344,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.2457432121491028,
876
+ "grad_norm": 0.8391731239503334,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.7267,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.2641509433962264,
883
+ "grad_norm": 0.7660636226540483,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.7263,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.2825586746433504,
890
+ "grad_norm": 0.7685620801521849,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.7313,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.300966405890474,
897
+ "grad_norm": 0.5495938135890535,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.7304,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.319374137137598,
904
+ "grad_norm": 0.5378287623942755,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.7272,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.3377818683847216,
911
+ "grad_norm": 0.4910879337814261,
912
+ "learning_rate": 5e-06,
913
+ "loss": 0.7282,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.356189599631845,
918
+ "grad_norm": 0.5133127271923346,
919
+ "learning_rate": 5e-06,
920
+ "loss": 0.7269,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.374597330878969,
925
+ "grad_norm": 0.47595606060751855,
926
+ "learning_rate": 5e-06,
927
+ "loss": 0.7339,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.393005062126093,
932
+ "grad_norm": 0.6100252730125039,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.7345,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.411412793373217,
939
+ "grad_norm": 0.7026268817947412,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.7337,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.4298205246203404,
946
+ "grad_norm": 0.5079596124965767,
947
+ "learning_rate": 5e-06,
948
+ "loss": 0.7302,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.4482282558674644,
953
+ "grad_norm": 0.6696005064461804,
954
+ "learning_rate": 5e-06,
955
+ "loss": 0.7326,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.466635987114588,
960
+ "grad_norm": 0.5305091535929889,
961
+ "learning_rate": 5e-06,
962
+ "loss": 0.7341,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.485043718361712,
967
+ "grad_norm": 0.5614144854915857,
968
+ "learning_rate": 5e-06,
969
+ "loss": 0.7307,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.5034514496088356,
974
+ "grad_norm": 0.5298924392144096,
975
+ "learning_rate": 5e-06,
976
+ "loss": 0.7267,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.5218591808559596,
981
+ "grad_norm": 0.5471748009635868,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.7313,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.540266912103083,
988
+ "grad_norm": 0.5294197001366643,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.7306,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.5586746433502072,
995
+ "grad_norm": 0.5154792682728118,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.7307,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.577082374597331,
1002
+ "grad_norm": 0.5789014770833831,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.7301,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.595490105844455,
1009
+ "grad_norm": 0.5711167242239414,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.7303,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.6138978370915784,
1016
+ "grad_norm": 0.5106168370499636,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.7334,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.632305568338702,
1023
+ "grad_norm": 0.5255898569302698,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.7304,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.650713299585826,
1030
+ "grad_norm": 0.6031837728823062,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.7312,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.66912103083295,
1037
+ "grad_norm": 0.5493271504786518,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.7286,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.6875287620800736,
1044
+ "grad_norm": 0.5359957110816633,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.7333,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.705936493327197,
1051
+ "grad_norm": 0.5315084537350974,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.7346,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.7243442245743212,
1058
+ "grad_norm": 0.5584346211293773,
1059
+ "learning_rate": 5e-06,
1060
+ "loss": 0.7323,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.7427519558214453,
1065
+ "grad_norm": 0.5792409356580582,
1066
+ "learning_rate": 5e-06,
1067
+ "loss": 0.7379,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.761159687068569,
1072
+ "grad_norm": 0.5984704825439037,
1073
+ "learning_rate": 5e-06,
1074
+ "loss": 0.7304,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.7795674183156924,
1079
+ "grad_norm": 0.6745195268654445,
1080
+ "learning_rate": 5e-06,
1081
+ "loss": 0.7279,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.7979751495628165,
1086
+ "grad_norm": 0.5840202368947607,
1087
+ "learning_rate": 5e-06,
1088
+ "loss": 0.7285,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.81638288080994,
1093
+ "grad_norm": 0.5808419078842372,
1094
+ "learning_rate": 5e-06,
1095
+ "loss": 0.7327,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.834790612057064,
1100
+ "grad_norm": 0.5702913394525961,
1101
+ "learning_rate": 5e-06,
1102
+ "loss": 0.7359,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.8531983433041876,
1107
+ "grad_norm": 0.5655041029108082,
1108
+ "learning_rate": 5e-06,
1109
+ "loss": 0.7314,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.8716060745513117,
1114
+ "grad_norm": 0.5207693095861798,
1115
+ "learning_rate": 5e-06,
1116
+ "loss": 0.7305,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.8900138057984353,
1121
+ "grad_norm": 0.5547333755102506,
1122
+ "learning_rate": 5e-06,
1123
+ "loss": 0.7316,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.9084215370455593,
1128
+ "grad_norm": 0.5475003571941236,
1129
+ "learning_rate": 5e-06,
1130
+ "loss": 0.7288,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.926829268292683,
1135
+ "grad_norm": 0.6206903635935059,
1136
+ "learning_rate": 5e-06,
1137
+ "loss": 0.7371,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.945236999539807,
1142
+ "grad_norm": 0.5473171408927406,
1143
+ "learning_rate": 5e-06,
1144
+ "loss": 0.7342,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.9636447307869305,
1149
+ "grad_norm": 0.5167351817484509,
1150
+ "learning_rate": 5e-06,
1151
+ "loss": 0.7313,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.982052462034054,
1156
+ "grad_norm": 0.549878401014801,
1157
+ "learning_rate": 5e-06,
1158
+ "loss": 0.7326,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.9986194201564658,
1163
+ "eval_loss": 0.8022779822349548,
1164
+ "eval_runtime": 574.4981,
1165
+ "eval_samples_per_second": 25.481,
1166
+ "eval_steps_per_second": 0.399,
1167
+ "step": 1629
1168
+ },
1169
+ {
1170
+ "epoch": 2.9986194201564658,
1171
+ "step": 1629,
1172
+ "total_flos": 2728426293166080.0,
1173
+ "train_loss": 0.7854923086710837,
1174
+ "train_runtime": 95950.7779,
1175
+ "train_samples_per_second": 8.696,
1176
+ "train_steps_per_second": 0.017
1177
+ }
1178
+ ],
1179
+ "logging_steps": 10,
1180
+ "max_steps": 1629,
1181
+ "num_input_tokens_seen": 0,
1182
+ "num_train_epochs": 3,
1183
+ "save_steps": 500,
1184
+ "stateful_callbacks": {
1185
+ "TrainerControl": {
1186
+ "args": {
1187
+ "should_epoch_stop": false,
1188
+ "should_evaluate": false,
1189
+ "should_log": false,
1190
+ "should_save": true,
1191
+ "should_training_stop": true
1192
+ },
1193
+ "attributes": {}
1194
+ }
1195
+ },
1196
+ "total_flos": 2728426293166080.0,
1197
+ "train_batch_size": 8,
1198
+ "trial_name": null,
1199
+ "trial_params": null
1200
+ }
training_eval_loss.png ADDED
training_loss.png ADDED