OpenLeecher commited on
Commit
9263bfe
·
verified ·
1 Parent(s): 040caa7

End of training

Browse files
Files changed (5) hide show
  1. README.md +3 -2
  2. all_results.json +12 -0
  3. eval_results.json +7 -0
  4. train_results.json +8 -0
  5. trainer_state.json +1270 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Llama-3.1-8B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: llama_8b_lima_44
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # llama_8b_lima_44
17
 
18
- This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9046
21
 
22
  ## Model description
23
 
 
4
  base_model: meta-llama/Llama-3.1-8B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: llama_8b_lima_44
 
16
 
17
  # llama_8b_lima_44
18
 
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the open_webui_dataset dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.9029
22
 
23
  ## Model description
24
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997970367363507,
3
+ "eval_loss": 0.9028599262237549,
4
+ "eval_runtime": 10.0893,
5
+ "eval_samples_per_second": 19.823,
6
+ "eval_steps_per_second": 4.956,
7
+ "total_flos": 1.4841304991137792e+17,
8
+ "train_loss": 1.0157385155576737,
9
+ "train_runtime": 6062.254,
10
+ "train_samples_per_second": 4.876,
11
+ "train_steps_per_second": 0.135
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997970367363507,
3
+ "eval_loss": 0.9028599262237549,
4
+ "eval_runtime": 10.0893,
5
+ "eval_samples_per_second": 19.823,
6
+ "eval_steps_per_second": 4.956
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997970367363507,
3
+ "total_flos": 1.4841304991137792e+17,
4
+ "train_loss": 1.0157385155576737,
5
+ "train_runtime": 6062.254,
6
+ "train_samples_per_second": 4.876,
7
+ "train_steps_per_second": 0.135
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1270 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9997970367363507,
5
+ "eval_steps": 80,
6
+ "global_step": 821,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.006088897909478384,
13
+ "grad_norm": 3.566783556339775,
14
+ "learning_rate": 5.5e-07,
15
+ "loss": 1.1009,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.012177795818956769,
20
+ "grad_norm": 3.472124035548172,
21
+ "learning_rate": 1.1e-06,
22
+ "loss": 1.0381,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.018266693728435153,
27
+ "grad_norm": 2.9811017753128577,
28
+ "learning_rate": 1.6499999999999999e-06,
29
+ "loss": 0.9465,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.024355591637913537,
34
+ "grad_norm": 2.922160623410553,
35
+ "learning_rate": 2.2e-06,
36
+ "loss": 1.2107,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.03044448954739192,
41
+ "grad_norm": 2.4899147411553546,
42
+ "learning_rate": 2.75e-06,
43
+ "loss": 1.1834,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.036533387456870306,
48
+ "grad_norm": 2.4171440435334826,
49
+ "learning_rate": 3.2999999999999997e-06,
50
+ "loss": 1.0345,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.04262228536634869,
55
+ "grad_norm": 2.3631050864525105,
56
+ "learning_rate": 3.8499999999999996e-06,
57
+ "loss": 0.8937,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.048711183275827075,
62
+ "grad_norm": 2.367215460791824,
63
+ "learning_rate": 4.4e-06,
64
+ "loss": 1.0384,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.05480008118530546,
69
+ "grad_norm": 2.3735664390744695,
70
+ "learning_rate": 4.95e-06,
71
+ "loss": 0.8559,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.06088897909478384,
76
+ "grad_norm": 2.1106128418644574,
77
+ "learning_rate": 5.5e-06,
78
+ "loss": 1.0974,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.06697787700426223,
83
+ "grad_norm": 2.4447079098341042,
84
+ "learning_rate": 5.416103509565232e-06,
85
+ "loss": 1.0212,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.07306677491374061,
90
+ "grad_norm": 2.4511103681763307,
91
+ "learning_rate": 5.333024453086441e-06,
92
+ "loss": 0.9416,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.079155672823219,
97
+ "grad_norm": 2.2384105642036918,
98
+ "learning_rate": 5.250760158320862e-06,
99
+ "loss": 1.2031,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.08524457073269738,
104
+ "grad_norm": 3.119602266469178,
105
+ "learning_rate": 5.16930794423241e-06,
106
+ "loss": 0.8486,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.09133346864217577,
111
+ "grad_norm": 2.5881641097806862,
112
+ "learning_rate": 5.088665120904279e-06,
113
+ "loss": 1.1537,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.09742236655165415,
118
+ "grad_norm": 2.2055002770457657,
119
+ "learning_rate": 5.008828989450109e-06,
120
+ "loss": 1.0313,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.09742236655165415,
125
+ "eval_loss": 0.9289844036102295,
126
+ "eval_runtime": 10.8703,
127
+ "eval_samples_per_second": 18.399,
128
+ "eval_steps_per_second": 4.6,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 0.10351126446113254,
133
+ "grad_norm": 2.415544688492964,
134
+ "learning_rate": 4.92979684192366e-06,
135
+ "loss": 0.9282,
136
+ "step": 85
137
+ },
138
+ {
139
+ "epoch": 0.10960016237061092,
140
+ "grad_norm": 1.7793675433556284,
141
+ "learning_rate": 4.851565961226947e-06,
142
+ "loss": 0.8977,
143
+ "step": 90
144
+ },
145
+ {
146
+ "epoch": 0.11568906028008931,
147
+ "grad_norm": 2.8859944584710293,
148
+ "learning_rate": 4.774133621016826e-06,
149
+ "loss": 0.9419,
150
+ "step": 95
151
+ },
152
+ {
153
+ "epoch": 0.12177795818956769,
154
+ "grad_norm": 2.469055183117004,
155
+ "learning_rate": 4.69749708560997e-06,
156
+ "loss": 0.9848,
157
+ "step": 100
158
+ },
159
+ {
160
+ "epoch": 0.12786685609904608,
161
+ "grad_norm": 2.2447776512327544,
162
+ "learning_rate": 4.621653609886213e-06,
163
+ "loss": 1.215,
164
+ "step": 105
165
+ },
166
+ {
167
+ "epoch": 0.13395575400852447,
168
+ "grad_norm": 2.531579161423441,
169
+ "learning_rate": 4.5466004391902066e-06,
170
+ "loss": 1.1061,
171
+ "step": 110
172
+ },
173
+ {
174
+ "epoch": 0.14004465191800283,
175
+ "grad_norm": 1.9522000168289182,
176
+ "learning_rate": 4.472334809231365e-06,
177
+ "loss": 0.9953,
178
+ "step": 115
179
+ },
180
+ {
181
+ "epoch": 0.14613354982748122,
182
+ "grad_norm": 2.5590272228727136,
183
+ "learning_rate": 4.398853945982053e-06,
184
+ "loss": 0.6939,
185
+ "step": 120
186
+ },
187
+ {
188
+ "epoch": 0.15222244773695962,
189
+ "grad_norm": 2.801526994914379,
190
+ "learning_rate": 4.326155065573944e-06,
191
+ "loss": 0.9363,
192
+ "step": 125
193
+ },
194
+ {
195
+ "epoch": 0.158311345646438,
196
+ "grad_norm": 1.8373874255277394,
197
+ "learning_rate": 4.254235374192553e-06,
198
+ "loss": 1.195,
199
+ "step": 130
200
+ },
201
+ {
202
+ "epoch": 0.16440024355591637,
203
+ "grad_norm": 2.236882560839364,
204
+ "learning_rate": 4.183092067969859e-06,
205
+ "loss": 0.9793,
206
+ "step": 135
207
+ },
208
+ {
209
+ "epoch": 0.17048914146539476,
210
+ "grad_norm": 3.3065776583087643,
211
+ "learning_rate": 4.112722332874986e-06,
212
+ "loss": 0.9404,
213
+ "step": 140
214
+ },
215
+ {
216
+ "epoch": 0.17657803937487315,
217
+ "grad_norm": 2.5409656409615695,
218
+ "learning_rate": 4.043123344602879e-06,
219
+ "loss": 0.7751,
220
+ "step": 145
221
+ },
222
+ {
223
+ "epoch": 0.18266693728435154,
224
+ "grad_norm": 2.6275401841731814,
225
+ "learning_rate": 3.974292268460949e-06,
226
+ "loss": 0.874,
227
+ "step": 150
228
+ },
229
+ {
230
+ "epoch": 0.1887558351938299,
231
+ "grad_norm": 2.8046791101602007,
232
+ "learning_rate": 3.906226259253599e-06,
233
+ "loss": 0.9028,
234
+ "step": 155
235
+ },
236
+ {
237
+ "epoch": 0.1948447331033083,
238
+ "grad_norm": 2.1392572989093006,
239
+ "learning_rate": 3.838922461164612e-06,
240
+ "loss": 0.985,
241
+ "step": 160
242
+ },
243
+ {
244
+ "epoch": 0.1948447331033083,
245
+ "eval_loss": 0.9194434881210327,
246
+ "eval_runtime": 10.0404,
247
+ "eval_samples_per_second": 19.919,
248
+ "eval_steps_per_second": 4.98,
249
+ "step": 160
250
+ },
251
+ {
252
+ "epoch": 0.2009336310127867,
253
+ "grad_norm": 1.937352853882511,
254
+ "learning_rate": 3.772378007637317e-06,
255
+ "loss": 1.2669,
256
+ "step": 165
257
+ },
258
+ {
259
+ "epoch": 0.20702252892226508,
260
+ "grad_norm": 2.31447918391138,
261
+ "learning_rate": 3.7065900212524865e-06,
262
+ "loss": 0.8301,
263
+ "step": 170
264
+ },
265
+ {
266
+ "epoch": 0.21311142683174344,
267
+ "grad_norm": 1.9170456106220028,
268
+ "learning_rate": 3.6415556136039017e-06,
269
+ "loss": 0.9021,
270
+ "step": 175
271
+ },
272
+ {
273
+ "epoch": 0.21920032474122184,
274
+ "grad_norm": 2.2610666535764716,
275
+ "learning_rate": 3.57727188517153e-06,
276
+ "loss": 0.925,
277
+ "step": 180
278
+ },
279
+ {
280
+ "epoch": 0.22528922265070023,
281
+ "grad_norm": 2.4930543513110566,
282
+ "learning_rate": 3.513735925192236e-06,
283
+ "loss": 0.861,
284
+ "step": 185
285
+ },
286
+ {
287
+ "epoch": 0.23137812056017862,
288
+ "grad_norm": 2.1552816913331334,
289
+ "learning_rate": 3.4509448115279674e-06,
290
+ "loss": 1.1969,
291
+ "step": 190
292
+ },
293
+ {
294
+ "epoch": 0.23746701846965698,
295
+ "grad_norm": 1.8621642100291538,
296
+ "learning_rate": 3.388895610531349e-06,
297
+ "loss": 0.8704,
298
+ "step": 195
299
+ },
300
+ {
301
+ "epoch": 0.24355591637913537,
302
+ "grad_norm": 2.1209832615085285,
303
+ "learning_rate": 3.3275853769086063e-06,
304
+ "loss": 0.9503,
305
+ "step": 200
306
+ },
307
+ {
308
+ "epoch": 0.24964481428861376,
309
+ "grad_norm": 2.237393861143882,
310
+ "learning_rate": 3.267011153579745e-06,
311
+ "loss": 0.9347,
312
+ "step": 205
313
+ },
314
+ {
315
+ "epoch": 0.25573371219809216,
316
+ "grad_norm": 2.2028682955334964,
317
+ "learning_rate": 3.2071699715359122e-06,
318
+ "loss": 0.8733,
319
+ "step": 210
320
+ },
321
+ {
322
+ "epoch": 0.2618226101075705,
323
+ "grad_norm": 2.1266652440547475,
324
+ "learning_rate": 3.148058849693859e-06,
325
+ "loss": 1.065,
326
+ "step": 215
327
+ },
328
+ {
329
+ "epoch": 0.26791150801704894,
330
+ "grad_norm": 2.285707011170251,
331
+ "learning_rate": 3.0896747947474105e-06,
332
+ "loss": 0.9307,
333
+ "step": 220
334
+ },
335
+ {
336
+ "epoch": 0.2740004059265273,
337
+ "grad_norm": 2.5710181491838737,
338
+ "learning_rate": 3.0320148010158774e-06,
339
+ "loss": 1.0314,
340
+ "step": 225
341
+ },
342
+ {
343
+ "epoch": 0.28008930383600567,
344
+ "grad_norm": 2.292322109336443,
345
+ "learning_rate": 2.975075850289298e-06,
346
+ "loss": 0.9115,
347
+ "step": 230
348
+ },
349
+ {
350
+ "epoch": 0.2861782017454841,
351
+ "grad_norm": 2.1450080532027025,
352
+ "learning_rate": 2.9188549116704386e-06,
353
+ "loss": 1.0111,
354
+ "step": 235
355
+ },
356
+ {
357
+ "epoch": 0.29226709965496245,
358
+ "grad_norm": 2.1135370162342717,
359
+ "learning_rate": 2.8633489414134293e-06,
360
+ "loss": 1.091,
361
+ "step": 240
362
+ },
363
+ {
364
+ "epoch": 0.29226709965496245,
365
+ "eval_loss": 0.9108514189720154,
366
+ "eval_runtime": 10.044,
367
+ "eval_samples_per_second": 19.912,
368
+ "eval_steps_per_second": 4.978,
369
+ "step": 240
370
+ },
371
+ {
372
+ "epoch": 0.2983559975644408,
373
+ "grad_norm": 1.8496992962121142,
374
+ "learning_rate": 2.8085548827589632e-06,
375
+ "loss": 0.9449,
376
+ "step": 245
377
+ },
378
+ {
379
+ "epoch": 0.30444489547391923,
380
+ "grad_norm": 2.2350891035464615,
381
+ "learning_rate": 2.7544696657659385e-06,
382
+ "loss": 1.0587,
383
+ "step": 250
384
+ },
385
+ {
386
+ "epoch": 0.3105337933833976,
387
+ "grad_norm": 2.6722037220078767,
388
+ "learning_rate": 2.7010902071394348e-06,
389
+ "loss": 0.7525,
390
+ "step": 255
391
+ },
392
+ {
393
+ "epoch": 0.316622691292876,
394
+ "grad_norm": 2.277080303923668,
395
+ "learning_rate": 2.6484134100549204e-06,
396
+ "loss": 0.8815,
397
+ "step": 260
398
+ },
399
+ {
400
+ "epoch": 0.3227115892023544,
401
+ "grad_norm": 2.0493281130802616,
402
+ "learning_rate": 2.5964361639785647e-06,
403
+ "loss": 1.1089,
404
+ "step": 265
405
+ },
406
+ {
407
+ "epoch": 0.32880048711183274,
408
+ "grad_norm": 2.042407938817224,
409
+ "learning_rate": 2.5451553444835415e-06,
410
+ "loss": 1.0962,
411
+ "step": 270
412
+ },
413
+ {
414
+ "epoch": 0.33488938502131116,
415
+ "grad_norm": 2.4634190870687287,
416
+ "learning_rate": 2.4945678130621847e-06,
417
+ "loss": 0.981,
418
+ "step": 275
419
+ },
420
+ {
421
+ "epoch": 0.3409782829307895,
422
+ "grad_norm": 2.260346564740007,
423
+ "learning_rate": 2.4446704169338846e-06,
424
+ "loss": 0.8348,
425
+ "step": 280
426
+ },
427
+ {
428
+ "epoch": 0.3470671808402679,
429
+ "grad_norm": 2.1046411435401806,
430
+ "learning_rate": 2.3954599888485643e-06,
431
+ "loss": 0.7611,
432
+ "step": 285
433
+ },
434
+ {
435
+ "epoch": 0.3531560787497463,
436
+ "grad_norm": 2.192608175141679,
437
+ "learning_rate": 2.3469333468856106e-06,
438
+ "loss": 1.1149,
439
+ "step": 290
440
+ },
441
+ {
442
+ "epoch": 0.35924497665922467,
443
+ "grad_norm": 1.9896811996512633,
444
+ "learning_rate": 2.299087294248103e-06,
445
+ "loss": 0.8705,
446
+ "step": 295
447
+ },
448
+ {
449
+ "epoch": 0.3653338745687031,
450
+ "grad_norm": 2.342371852699277,
451
+ "learning_rate": 2.25191861905219e-06,
452
+ "loss": 0.7842,
453
+ "step": 300
454
+ },
455
+ {
456
+ "epoch": 0.37142277247818145,
457
+ "grad_norm": 2.7056358054268945,
458
+ "learning_rate": 2.205424094111439e-06,
459
+ "loss": 0.9357,
460
+ "step": 305
461
+ },
462
+ {
463
+ "epoch": 0.3775116703876598,
464
+ "grad_norm": 1.827000174010884,
465
+ "learning_rate": 2.1596004767160085e-06,
466
+ "loss": 1.088,
467
+ "step": 310
468
+ },
469
+ {
470
+ "epoch": 0.38360056829713823,
471
+ "grad_norm": 2.11667666402572,
472
+ "learning_rate": 2.1144445084064565e-06,
473
+ "loss": 1.0323,
474
+ "step": 315
475
+ },
476
+ {
477
+ "epoch": 0.3896894662066166,
478
+ "grad_norm": 1.9194964413075437,
479
+ "learning_rate": 2.069952914741992e-06,
480
+ "loss": 0.9087,
481
+ "step": 320
482
+ },
483
+ {
484
+ "epoch": 0.3896894662066166,
485
+ "eval_loss": 0.9030415415763855,
486
+ "eval_runtime": 10.0588,
487
+ "eval_samples_per_second": 19.883,
488
+ "eval_steps_per_second": 4.971,
489
+ "step": 320
490
+ },
491
+ {
492
+ "epoch": 0.39577836411609496,
493
+ "grad_norm": 2.379416328048356,
494
+ "learning_rate": 2.026122405062999e-06,
495
+ "loss": 0.9356,
496
+ "step": 325
497
+ },
498
+ {
499
+ "epoch": 0.4018672620255734,
500
+ "grad_norm": 2.3051629049862967,
501
+ "learning_rate": 1.982949672247615e-06,
502
+ "loss": 0.9179,
503
+ "step": 330
504
+ },
505
+ {
506
+ "epoch": 0.40795615993505174,
507
+ "grad_norm": 2.2745740533676724,
508
+ "learning_rate": 1.940431392462155e-06,
509
+ "loss": 0.9632,
510
+ "step": 335
511
+ },
512
+ {
513
+ "epoch": 0.41404505784453016,
514
+ "grad_norm": 2.2794095449818252,
515
+ "learning_rate": 1.8985642249051713e-06,
516
+ "loss": 0.8374,
517
+ "step": 340
518
+ },
519
+ {
520
+ "epoch": 0.4201339557540085,
521
+ "grad_norm": 1.9892966603109936,
522
+ "learning_rate": 1.8573448115449084e-06,
523
+ "loss": 0.8853,
524
+ "step": 345
525
+ },
526
+ {
527
+ "epoch": 0.4262228536634869,
528
+ "grad_norm": 1.9076114123449572,
529
+ "learning_rate": 1.8167697768499194e-06,
530
+ "loss": 1.006,
531
+ "step": 350
532
+ },
533
+ {
534
+ "epoch": 0.4323117515729653,
535
+ "grad_norm": 2.4400224099994183,
536
+ "learning_rate": 1.7768357275125856e-06,
537
+ "loss": 0.7937,
538
+ "step": 355
539
+ },
540
+ {
541
+ "epoch": 0.43840064948244367,
542
+ "grad_norm": 1.9229232682741382,
543
+ "learning_rate": 1.737539252165281e-06,
544
+ "loss": 0.937,
545
+ "step": 360
546
+ },
547
+ {
548
+ "epoch": 0.44448954739192204,
549
+ "grad_norm": 2.482169188918342,
550
+ "learning_rate": 1.6988769210889033e-06,
551
+ "loss": 0.8412,
552
+ "step": 365
553
+ },
554
+ {
555
+ "epoch": 0.45057844530140045,
556
+ "grad_norm": 2.0823727911627117,
557
+ "learning_rate": 1.6608452859134694e-06,
558
+ "loss": 1.0682,
559
+ "step": 370
560
+ },
561
+ {
562
+ "epoch": 0.4566673432108788,
563
+ "grad_norm": 2.1349739191332624,
564
+ "learning_rate": 1.6234408793104964e-06,
565
+ "loss": 0.9272,
566
+ "step": 375
567
+ },
568
+ {
569
+ "epoch": 0.46275624112035724,
570
+ "grad_norm": 2.30837580526881,
571
+ "learning_rate": 1.5866602146768156e-06,
572
+ "loss": 0.8386,
573
+ "step": 380
574
+ },
575
+ {
576
+ "epoch": 0.4688451390298356,
577
+ "grad_norm": 1.998746509174225,
578
+ "learning_rate": 1.55049978580951e-06,
579
+ "loss": 1.0616,
580
+ "step": 385
581
+ },
582
+ {
583
+ "epoch": 0.47493403693931396,
584
+ "grad_norm": 1.7126649948610602,
585
+ "learning_rate": 1.5149560665716053e-06,
586
+ "loss": 0.9667,
587
+ "step": 390
588
+ },
589
+ {
590
+ "epoch": 0.4810229348487924,
591
+ "grad_norm": 5.6311081714105935,
592
+ "learning_rate": 1.4800255105481483e-06,
593
+ "loss": 0.876,
594
+ "step": 395
595
+ },
596
+ {
597
+ "epoch": 0.48711183275827075,
598
+ "grad_norm": 2.3657992350084545,
599
+ "learning_rate": 1.445704550692281e-06,
600
+ "loss": 1.0107,
601
+ "step": 400
602
+ },
603
+ {
604
+ "epoch": 0.48711183275827075,
605
+ "eval_loss": 0.8974834680557251,
606
+ "eval_runtime": 10.0412,
607
+ "eval_samples_per_second": 19.918,
608
+ "eval_steps_per_second": 4.979,
609
+ "step": 400
610
+ },
611
+ {
612
+ "epoch": 0.4932007306677491,
613
+ "grad_norm": 1.7698636674115102,
614
+ "learning_rate": 1.4119895989608974e-06,
615
+ "loss": 0.9153,
616
+ "step": 405
617
+ },
618
+ {
619
+ "epoch": 0.49928962857722753,
620
+ "grad_norm": 2.054779528570307,
621
+ "learning_rate": 1.3788770459394496e-06,
622
+ "loss": 0.8891,
623
+ "step": 410
624
+ },
625
+ {
626
+ "epoch": 0.5053785264867059,
627
+ "grad_norm": 1.9369644275849407,
628
+ "learning_rate": 1.3463632604554425e-06,
629
+ "loss": 0.9571,
630
+ "step": 415
631
+ },
632
+ {
633
+ "epoch": 0.5114674243961843,
634
+ "grad_norm": 1.8987765645217645,
635
+ "learning_rate": 1.3144445891801363e-06,
636
+ "loss": 0.963,
637
+ "step": 420
638
+ },
639
+ {
640
+ "epoch": 0.5175563223056627,
641
+ "grad_norm": 2.403051805328199,
642
+ "learning_rate": 1.28311735621795e-06,
643
+ "loss": 1.1635,
644
+ "step": 425
645
+ },
646
+ {
647
+ "epoch": 0.523645220215141,
648
+ "grad_norm": 2.109077522246386,
649
+ "learning_rate": 1.252377862683016e-06,
650
+ "loss": 1.0585,
651
+ "step": 430
652
+ },
653
+ {
654
+ "epoch": 0.5297341181246195,
655
+ "grad_norm": 1.874133422791628,
656
+ "learning_rate": 1.222222386262332e-06,
657
+ "loss": 0.9143,
658
+ "step": 435
659
+ },
660
+ {
661
+ "epoch": 0.5358230160340979,
662
+ "grad_norm": 2.1929101428736177,
663
+ "learning_rate": 1.1926471807648967e-06,
664
+ "loss": 0.9188,
665
+ "step": 440
666
+ },
667
+ {
668
+ "epoch": 0.5419119139435762,
669
+ "grad_norm": 1.6260373540934423,
670
+ "learning_rate": 1.1636484756561917e-06,
671
+ "loss": 0.8914,
672
+ "step": 445
673
+ },
674
+ {
675
+ "epoch": 0.5480008118530546,
676
+ "grad_norm": 1.9739709292895855,
677
+ "learning_rate": 1.1352224755773445e-06,
678
+ "loss": 1.0831,
679
+ "step": 450
680
+ },
681
+ {
682
+ "epoch": 0.554089709762533,
683
+ "grad_norm": 2.023310630964453,
684
+ "learning_rate": 1.107365359848245e-06,
685
+ "loss": 1.0402,
686
+ "step": 455
687
+ },
688
+ {
689
+ "epoch": 0.5601786076720113,
690
+ "grad_norm": 2.466428732846668,
691
+ "learning_rate": 1.0800732819538616e-06,
692
+ "loss": 0.9395,
693
+ "step": 460
694
+ },
695
+ {
696
+ "epoch": 0.5662675055814897,
697
+ "grad_norm": 1.9030259115900607,
698
+ "learning_rate": 1.0533423690129516e-06,
699
+ "loss": 0.8586,
700
+ "step": 465
701
+ },
702
+ {
703
+ "epoch": 0.5723564034909682,
704
+ "grad_norm": 2.1592861330197946,
705
+ "learning_rate": 1.0271687212283061e-06,
706
+ "loss": 0.9337,
707
+ "step": 470
708
+ },
709
+ {
710
+ "epoch": 0.5784453014004465,
711
+ "grad_norm": 2.356602817957484,
712
+ "learning_rate": 1.0015484113176207e-06,
713
+ "loss": 0.8562,
714
+ "step": 475
715
+ },
716
+ {
717
+ "epoch": 0.5845341993099249,
718
+ "grad_norm": 1.9750104030522446,
719
+ "learning_rate": 9.764774839240228e-07,
720
+ "loss": 0.9108,
721
+ "step": 480
722
+ },
723
+ {
724
+ "epoch": 0.5845341993099249,
725
+ "eval_loss": 0.8940006494522095,
726
+ "eval_runtime": 10.0627,
727
+ "eval_samples_per_second": 19.875,
728
+ "eval_steps_per_second": 4.969,
729
+ "step": 480
730
+ },
731
+ {
732
+ "epoch": 0.5906230972194033,
733
+ "grad_norm": 2.294181751504768,
734
+ "learning_rate": 9.519519550052165e-07,
735
+ "loss": 0.9483,
736
+ "step": 485
737
+ },
738
+ {
739
+ "epoch": 0.5967119951288816,
740
+ "grad_norm": 2.390172284421488,
741
+ "learning_rate": 9.27967811200154e-07,
742
+ "loss": 0.9252,
743
+ "step": 490
744
+ },
745
+ {
746
+ "epoch": 0.60280089303836,
747
+ "grad_norm": 1.9195131453200192,
748
+ "learning_rate": 9.045210091720488e-07,
749
+ "loss": 1.045,
750
+ "step": 495
751
+ },
752
+ {
753
+ "epoch": 0.6088897909478385,
754
+ "grad_norm": 2.3087652972941957,
755
+ "learning_rate": 8.816074749264782e-07,
756
+ "loss": 0.8324,
757
+ "step": 500
758
+ },
759
+ {
760
+ "epoch": 0.6149786888573169,
761
+ "grad_norm": 1.887331233479458,
762
+ "learning_rate": 8.592231031032369e-07,
763
+ "loss": 0.9797,
764
+ "step": 505
765
+ },
766
+ {
767
+ "epoch": 0.6210675867667952,
768
+ "grad_norm": 2.546311216104545,
769
+ "learning_rate": 8.37363756240493e-07,
770
+ "loss": 0.9758,
771
+ "step": 510
772
+ },
773
+ {
774
+ "epoch": 0.6271564846762736,
775
+ "grad_norm": 2.052324183223674,
776
+ "learning_rate": 8.160252640097203e-07,
777
+ "loss": 0.9379,
778
+ "step": 515
779
+ },
780
+ {
781
+ "epoch": 0.633245382585752,
782
+ "grad_norm": 1.8162505508545923,
783
+ "learning_rate": 7.952034224197429e-07,
784
+ "loss": 1.0445,
785
+ "step": 520
786
+ },
787
+ {
788
+ "epoch": 0.6393342804952303,
789
+ "grad_norm": 1.9039113307487847,
790
+ "learning_rate": 7.748939929881281e-07,
791
+ "loss": 0.9693,
792
+ "step": 525
793
+ },
794
+ {
795
+ "epoch": 0.6454231784047088,
796
+ "grad_norm": 1.7791797404105452,
797
+ "learning_rate": 7.5509270187801e-07,
798
+ "loss": 1.1654,
799
+ "step": 530
800
+ },
801
+ {
802
+ "epoch": 0.6515120763141872,
803
+ "grad_norm": 2.2713665666241023,
804
+ "learning_rate": 7.357952389983003e-07,
805
+ "loss": 1.0812,
806
+ "step": 535
807
+ },
808
+ {
809
+ "epoch": 0.6576009742236655,
810
+ "grad_norm": 2.7771426272207926,
811
+ "learning_rate": 7.169972570650695e-07,
812
+ "loss": 1.0663,
813
+ "step": 540
814
+ },
815
+ {
816
+ "epoch": 0.6636898721331439,
817
+ "grad_norm": 2.1095605296190794,
818
+ "learning_rate": 6.986943706217093e-07,
819
+ "loss": 1.2464,
820
+ "step": 545
821
+ },
822
+ {
823
+ "epoch": 0.6697787700426223,
824
+ "grad_norm": 2.165590845905102,
825
+ "learning_rate": 6.808821550153036e-07,
826
+ "loss": 1.1615,
827
+ "step": 550
828
+ },
829
+ {
830
+ "epoch": 0.6758676679521006,
831
+ "grad_norm": 2.098201375795868,
832
+ "learning_rate": 6.635561453264081e-07,
833
+ "loss": 1.2256,
834
+ "step": 555
835
+ },
836
+ {
837
+ "epoch": 0.681956565861579,
838
+ "grad_norm": 1.597477657082927,
839
+ "learning_rate": 6.467118352492235e-07,
840
+ "loss": 1.1531,
841
+ "step": 560
842
+ },
843
+ {
844
+ "epoch": 0.681956565861579,
845
+ "eval_loss": 0.9038890600204468,
846
+ "eval_runtime": 10.0714,
847
+ "eval_samples_per_second": 19.858,
848
+ "eval_steps_per_second": 4.965,
849
+ "step": 560
850
+ },
851
+ {
852
+ "epoch": 0.6880454637710575,
853
+ "grad_norm": 1.9610561566970353,
854
+ "learning_rate": 6.303446759188759e-07,
855
+ "loss": 1.1032,
856
+ "step": 565
857
+ },
858
+ {
859
+ "epoch": 0.6941343616805358,
860
+ "grad_norm": 1.8771579285205593,
861
+ "learning_rate": 6.14450074682243e-07,
862
+ "loss": 1.0247,
863
+ "step": 570
864
+ },
865
+ {
866
+ "epoch": 0.7002232595900142,
867
+ "grad_norm": 1.9428546209099045,
868
+ "learning_rate": 5.990233938084431e-07,
869
+ "loss": 0.9957,
870
+ "step": 575
871
+ },
872
+ {
873
+ "epoch": 0.7063121574994926,
874
+ "grad_norm": 2.0685369493893453,
875
+ "learning_rate": 5.840599491347582e-07,
876
+ "loss": 1.073,
877
+ "step": 580
878
+ },
879
+ {
880
+ "epoch": 0.712401055408971,
881
+ "grad_norm": 1.4232455246953637,
882
+ "learning_rate": 5.695550086433726e-07,
883
+ "loss": 1.17,
884
+ "step": 585
885
+ },
886
+ {
887
+ "epoch": 0.7184899533184493,
888
+ "grad_norm": 1.9953305653364002,
889
+ "learning_rate": 5.555037909638744e-07,
890
+ "loss": 1.0394,
891
+ "step": 590
892
+ },
893
+ {
894
+ "epoch": 0.7245788512279278,
895
+ "grad_norm": 2.234757544147466,
896
+ "learning_rate": 5.419014637959808e-07,
897
+ "loss": 1.1472,
898
+ "step": 595
899
+ },
900
+ {
901
+ "epoch": 0.7306677491374062,
902
+ "grad_norm": 2.2367049852297876,
903
+ "learning_rate": 5.287431422464098e-07,
904
+ "loss": 1.0496,
905
+ "step": 600
906
+ },
907
+ {
908
+ "epoch": 0.7367566470468845,
909
+ "grad_norm": 2.2212989204910367,
910
+ "learning_rate": 5.160238870732056e-07,
911
+ "loss": 0.9907,
912
+ "step": 605
913
+ },
914
+ {
915
+ "epoch": 0.7428455449563629,
916
+ "grad_norm": 1.8355911585139566,
917
+ "learning_rate": 5.037387028301462e-07,
918
+ "loss": 1.3347,
919
+ "step": 610
920
+ },
921
+ {
922
+ "epoch": 0.7489344428658413,
923
+ "grad_norm": 2.172477947251129,
924
+ "learning_rate": 4.918825359030837e-07,
925
+ "loss": 1.1386,
926
+ "step": 615
927
+ },
928
+ {
929
+ "epoch": 0.7550233407753196,
930
+ "grad_norm": 1.8047316252716201,
931
+ "learning_rate": 4.804502724291952e-07,
932
+ "loss": 1.1201,
933
+ "step": 620
934
+ },
935
+ {
936
+ "epoch": 0.761112238684798,
937
+ "grad_norm": 1.8666031715794023,
938
+ "learning_rate": 4.6943673608912795e-07,
939
+ "loss": 1.0354,
940
+ "step": 625
941
+ },
942
+ {
943
+ "epoch": 0.7672011365942765,
944
+ "grad_norm": 1.948049167249183,
945
+ "learning_rate": 4.588366857608947e-07,
946
+ "loss": 0.9314,
947
+ "step": 630
948
+ },
949
+ {
950
+ "epoch": 0.7732900345037548,
951
+ "grad_norm": 1.9360471601880767,
952
+ "learning_rate": 4.4864481302308764e-07,
953
+ "loss": 1.3016,
954
+ "step": 635
955
+ },
956
+ {
957
+ "epoch": 0.7793789324132332,
958
+ "grad_norm": 1.7603394486420607,
959
+ "learning_rate": 4.388557394934996e-07,
960
+ "loss": 1.2698,
961
+ "step": 640
962
+ },
963
+ {
964
+ "epoch": 0.7793789324132332,
965
+ "eval_loss": 0.9068670868873596,
966
+ "eval_runtime": 10.0454,
967
+ "eval_samples_per_second": 19.91,
968
+ "eval_steps_per_second": 4.977,
969
+ "step": 640
970
+ },
971
+ {
972
+ "epoch": 0.7854678303227116,
973
+ "grad_norm": 1.8121869716312213,
974
+ "learning_rate": 4.2946401398754887e-07,
975
+ "loss": 1.0936,
976
+ "step": 645
977
+ },
978
+ {
979
+ "epoch": 0.7915567282321899,
980
+ "grad_norm": 2.2784724809217116,
981
+ "learning_rate": 4.20464109478947e-07,
982
+ "loss": 1.0688,
983
+ "step": 650
984
+ },
985
+ {
986
+ "epoch": 0.7976456261416683,
987
+ "grad_norm": 1.9511498628400707,
988
+ "learning_rate": 4.118504198427839e-07,
989
+ "loss": 1.2066,
990
+ "step": 655
991
+ },
992
+ {
993
+ "epoch": 0.8037345240511468,
994
+ "grad_norm": 1.6886651269860387,
995
+ "learning_rate": 4.036172563585779e-07,
996
+ "loss": 1.0209,
997
+ "step": 660
998
+ },
999
+ {
1000
+ "epoch": 0.8098234219606252,
1001
+ "grad_norm": 1.770877392703053,
1002
+ "learning_rate": 3.957588439477604e-07,
1003
+ "loss": 1.1583,
1004
+ "step": 665
1005
+ },
1006
+ {
1007
+ "epoch": 0.8159123198701035,
1008
+ "grad_norm": 2.1758718521360385,
1009
+ "learning_rate": 3.8826931711647146e-07,
1010
+ "loss": 1.0352,
1011
+ "step": 670
1012
+ },
1013
+ {
1014
+ "epoch": 0.8220012177795819,
1015
+ "grad_norm": 2.003054070991938,
1016
+ "learning_rate": 3.8114271557029493e-07,
1017
+ "loss": 1.1568,
1018
+ "step": 675
1019
+ },
1020
+ {
1021
+ "epoch": 0.8280901156890603,
1022
+ "grad_norm": 2.167247263874176,
1023
+ "learning_rate": 3.74372979462545e-07,
1024
+ "loss": 1.0868,
1025
+ "step": 680
1026
+ },
1027
+ {
1028
+ "epoch": 0.8341790135985386,
1029
+ "grad_norm": 1.8384381989648775,
1030
+ "learning_rate": 3.679539442317327e-07,
1031
+ "loss": 1.1053,
1032
+ "step": 685
1033
+ },
1034
+ {
1035
+ "epoch": 0.840267911508017,
1036
+ "grad_norm": 2.1673707360409877,
1037
+ "learning_rate": 3.6187933497668937e-07,
1038
+ "loss": 1.1503,
1039
+ "step": 690
1040
+ },
1041
+ {
1042
+ "epoch": 0.8463568094174955,
1043
+ "grad_norm": 1.9246135785489056,
1044
+ "learning_rate": 3.5614276030919706e-07,
1045
+ "loss": 1.0148,
1046
+ "step": 695
1047
+ },
1048
+ {
1049
+ "epoch": 0.8524457073269738,
1050
+ "grad_norm": 1.675592035681543,
1051
+ "learning_rate": 3.507377056135281e-07,
1052
+ "loss": 1.0533,
1053
+ "step": 700
1054
+ },
1055
+ {
1056
+ "epoch": 0.8585346052364522,
1057
+ "grad_norm": 1.58433949898804,
1058
+ "learning_rate": 3.456575256295274e-07,
1059
+ "loss": 0.9223,
1060
+ "step": 705
1061
+ },
1062
+ {
1063
+ "epoch": 0.8646235031459306,
1064
+ "grad_norm": 1.5089882230199272,
1065
+ "learning_rate": 3.408954362601715e-07,
1066
+ "loss": 1.1612,
1067
+ "step": 710
1068
+ },
1069
+ {
1070
+ "epoch": 0.8707124010554089,
1071
+ "grad_norm": 1.8812149702939354,
1072
+ "learning_rate": 3.364445054850564e-07,
1073
+ "loss": 1.1011,
1074
+ "step": 715
1075
+ },
1076
+ {
1077
+ "epoch": 0.8768012989648873,
1078
+ "grad_norm": 1.8009898237225854,
1079
+ "learning_rate": 3.322976432368887e-07,
1080
+ "loss": 1.1988,
1081
+ "step": 720
1082
+ },
1083
+ {
1084
+ "epoch": 0.8768012989648873,
1085
+ "eval_loss": 0.9062988758087158,
1086
+ "eval_runtime": 10.0522,
1087
+ "eval_samples_per_second": 19.896,
1088
+ "eval_steps_per_second": 4.974,
1089
+ "step": 720
1090
+ },
1091
+ {
1092
+ "epoch": 0.8828901968743658,
1093
+ "grad_norm": 2.0516728550272494,
1094
+ "learning_rate": 3.284475900672534e-07,
1095
+ "loss": 1.217,
1096
+ "step": 725
1097
+ },
1098
+ {
1099
+ "epoch": 0.8889790947838441,
1100
+ "grad_norm": 1.8636754853646536,
1101
+ "learning_rate": 3.2488690438860155e-07,
1102
+ "loss": 1.05,
1103
+ "step": 730
1104
+ },
1105
+ {
1106
+ "epoch": 0.8950679926933225,
1107
+ "grad_norm": 2.0197164306265973,
1108
+ "learning_rate": 3.216079480286014e-07,
1109
+ "loss": 1.083,
1110
+ "step": 735
1111
+ },
1112
+ {
1113
+ "epoch": 0.9011568906028009,
1114
+ "grad_norm": 1.7192487834075223,
1115
+ "learning_rate": 3.186028697665536e-07,
1116
+ "loss": 0.9577,
1117
+ "step": 740
1118
+ },
1119
+ {
1120
+ "epoch": 0.9072457885122793,
1121
+ "grad_norm": 1.9547679875155324,
1122
+ "learning_rate": 3.1586358643344154e-07,
1123
+ "loss": 1.0405,
1124
+ "step": 745
1125
+ },
1126
+ {
1127
+ "epoch": 0.9133346864217576,
1128
+ "grad_norm": 2.0062949300387847,
1129
+ "learning_rate": 3.1338176103847303e-07,
1130
+ "loss": 1.1779,
1131
+ "step": 750
1132
+ },
1133
+ {
1134
+ "epoch": 0.919423584331236,
1135
+ "grad_norm": 1.5531676528239142,
1136
+ "learning_rate": 3.111487772222592e-07,
1137
+ "loss": 1.1676,
1138
+ "step": 755
1139
+ },
1140
+ {
1141
+ "epoch": 0.9255124822407145,
1142
+ "grad_norm": 1.5372578345670411,
1143
+ "learning_rate": 3.0915570910938297e-07,
1144
+ "loss": 1.0719,
1145
+ "step": 760
1146
+ },
1147
+ {
1148
+ "epoch": 0.9316013801501928,
1149
+ "grad_norm": 2.1454113233082706,
1150
+ "learning_rate": 3.07393285308207e-07,
1151
+ "loss": 1.0105,
1152
+ "step": 765
1153
+ },
1154
+ {
1155
+ "epoch": 0.9376902780596712,
1156
+ "grad_norm": 1.5547170974986044,
1157
+ "learning_rate": 3.0585184532967033e-07,
1158
+ "loss": 1.0721,
1159
+ "step": 770
1160
+ },
1161
+ {
1162
+ "epoch": 0.9437791759691496,
1163
+ "grad_norm": 1.852645012921805,
1164
+ "learning_rate": 3.045212859784411e-07,
1165
+ "loss": 1.0933,
1166
+ "step": 775
1167
+ },
1168
+ {
1169
+ "epoch": 0.9498680738786279,
1170
+ "grad_norm": 1.8094221288522232,
1171
+ "learning_rate": 3.033909941480833e-07,
1172
+ "loss": 0.9671,
1173
+ "step": 780
1174
+ },
1175
+ {
1176
+ "epoch": 0.9559569717881063,
1177
+ "grad_norm": 1.5561960733621902,
1178
+ "learning_rate": 3.024497606276943e-07,
1179
+ "loss": 1.1151,
1180
+ "step": 785
1181
+ },
1182
+ {
1183
+ "epoch": 0.9620458696975848,
1184
+ "grad_norm": 1.84094988169291,
1185
+ "learning_rate": 3.016856664111943e-07,
1186
+ "loss": 0.9727,
1187
+ "step": 790
1188
+ },
1189
+ {
1190
+ "epoch": 0.9681347676070631,
1191
+ "grad_norm": 1.8600686188407434,
1192
+ "learning_rate": 3.0108592734273526e-07,
1193
+ "loss": 1.1713,
1194
+ "step": 795
1195
+ },
1196
+ {
1197
+ "epoch": 0.9742236655165415,
1198
+ "grad_norm": 1.9971464440071154,
1199
+ "learning_rate": 3.006366718310598e-07,
1200
+ "loss": 1.1649,
1201
+ "step": 800
1202
+ },
1203
+ {
1204
+ "epoch": 0.9742236655165415,
1205
+ "eval_loss": 0.9046012759208679,
1206
+ "eval_runtime": 10.0656,
1207
+ "eval_samples_per_second": 19.87,
1208
+ "eval_steps_per_second": 4.967,
1209
+ "step": 800
1210
+ },
1211
+ {
1212
+ "epoch": 0.9803125634260199,
1213
+ "grad_norm": 1.801943230059916,
1214
+ "learning_rate": 3.00322602222577e-07,
1215
+ "loss": 1.0695,
1216
+ "step": 805
1217
+ },
1218
+ {
1219
+ "epoch": 0.9864014613354982,
1220
+ "grad_norm": 1.839016967735732,
1221
+ "learning_rate": 3.001264297011597e-07,
1222
+ "loss": 0.9731,
1223
+ "step": 810
1224
+ },
1225
+ {
1226
+ "epoch": 0.9924903592449766,
1227
+ "grad_norm": 1.9692055921355986,
1228
+ "learning_rate": 3.00027780849675e-07,
1229
+ "loss": 0.9058,
1230
+ "step": 815
1231
+ },
1232
+ {
1233
+ "epoch": 0.9985792571544551,
1234
+ "grad_norm": 2.8720134735995413,
1235
+ "learning_rate": 3.0000031504123295e-07,
1236
+ "loss": 1.2194,
1237
+ "step": 820
1238
+ },
1239
+ {
1240
+ "epoch": 0.9997970367363507,
1241
+ "step": 821,
1242
+ "total_flos": 1.4841304991137792e+17,
1243
+ "train_loss": 1.0157385155576737,
1244
+ "train_runtime": 6062.254,
1245
+ "train_samples_per_second": 4.876,
1246
+ "train_steps_per_second": 0.135
1247
+ }
1248
+ ],
1249
+ "logging_steps": 5,
1250
+ "max_steps": 821,
1251
+ "num_input_tokens_seen": 0,
1252
+ "num_train_epochs": 1,
1253
+ "save_steps": 821,
1254
+ "stateful_callbacks": {
1255
+ "TrainerControl": {
1256
+ "args": {
1257
+ "should_epoch_stop": false,
1258
+ "should_evaluate": false,
1259
+ "should_log": false,
1260
+ "should_save": true,
1261
+ "should_training_stop": true
1262
+ },
1263
+ "attributes": {}
1264
+ }
1265
+ },
1266
+ "total_flos": 1.4841304991137792e+17,
1267
+ "train_batch_size": 3,
1268
+ "trial_name": null,
1269
+ "trial_params": null
1270
+ }