DeepDream2045 commited on
Commit
a6d9588
1 Parent(s): 9dde83a

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "o_proj",
24
  "down_proj",
25
- "gate_proj",
26
- "k_proj",
27
- "up_proj",
28
  "v_proj",
29
- "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "up_proj",
24
+ "q_proj",
25
+ "gate_proj",
26
  "o_proj",
27
  "down_proj",
 
 
 
28
  "v_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:641eb0d184ee62ddb72b2621ad6e78f932ea4c29eca641c702063c63c6f10f77
3
  size 859909312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a098e4073b8a0fba6a26374975a056a3b02d4cf25c917449c64558f8aafcf8fa
3
  size 859909312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52bf5ee5bd5dbb1359f2d2bd6532253f49d51d51c343323744f90193aa9e28d9
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e6a48dba0f4f00bf14d009b9a04064d26d6a7f7fa75bd50fca733463a100786
3
  size 671466706
last-checkpoint/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 1.7394925355911255,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
  "epoch": 0.05378874470517044,
5
  "eval_steps": 25,
@@ -10,376 +10,376 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.0010757748941034088,
13
- "grad_norm": 1.6709057092666626,
14
  "learning_rate": 5e-05,
15
- "loss": 1.707,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.0010757748941034088,
20
- "eval_loss": 2.019153356552124,
21
- "eval_runtime": 186.2275,
22
- "eval_samples_per_second": 33.631,
23
- "eval_steps_per_second": 4.205,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.0021515497882068175,
28
- "grad_norm": 1.8899304866790771,
29
  "learning_rate": 0.0001,
30
- "loss": 1.8408,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.0032273246823102267,
35
- "grad_norm": 1.4666272401809692,
36
  "learning_rate": 9.989294616193017e-05,
37
- "loss": 1.7696,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.004303099576413635,
42
- "grad_norm": 0.9372745752334595,
43
  "learning_rate": 9.957224306869053e-05,
44
- "loss": 1.7414,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.005378874470517044,
49
- "grad_norm": 0.8082295656204224,
50
  "learning_rate": 9.903926402016153e-05,
51
- "loss": 1.7415,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.006454649364620453,
56
- "grad_norm": 0.9279489517211914,
57
  "learning_rate": 9.829629131445342e-05,
58
- "loss": 1.7757,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.007530424258723862,
63
- "grad_norm": 0.701418936252594,
64
  "learning_rate": 9.73465064747553e-05,
65
- "loss": 1.8196,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.00860619915282727,
70
- "grad_norm": 0.688548743724823,
71
  "learning_rate": 9.619397662556435e-05,
72
- "loss": 1.7341,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.00968197404693068,
77
- "grad_norm": 0.6612863540649414,
78
  "learning_rate": 9.484363707663442e-05,
79
- "loss": 1.7848,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 0.010757748941034088,
84
- "grad_norm": 0.6995035409927368,
85
  "learning_rate": 9.330127018922194e-05,
86
- "loss": 1.8447,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.011833523835137498,
91
- "grad_norm": 0.7706447243690491,
92
  "learning_rate": 9.157348061512727e-05,
93
- "loss": 1.8312,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.012909298729240907,
98
- "grad_norm": 0.9608161449432373,
99
  "learning_rate": 8.966766701456177e-05,
100
- "loss": 2.0029,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.013985073623344316,
105
- "grad_norm": 1.8199213743209839,
106
  "learning_rate": 8.759199037394887e-05,
107
- "loss": 1.6517,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.015060848517447724,
112
- "grad_norm": 1.3464016914367676,
113
  "learning_rate": 8.535533905932738e-05,
114
- "loss": 1.6332,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.016136623411551133,
119
- "grad_norm": 0.96041339635849,
120
  "learning_rate": 8.296729075500344e-05,
121
- "loss": 1.6261,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.01721239830565454,
126
- "grad_norm": 0.7431668043136597,
127
  "learning_rate": 8.043807145043604e-05,
128
- "loss": 1.6273,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.01828817319975795,
133
- "grad_norm": 0.560585618019104,
134
  "learning_rate": 7.777851165098012e-05,
135
- "loss": 1.6822,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.01936394809386136,
140
- "grad_norm": 0.5964136123657227,
141
  "learning_rate": 7.500000000000001e-05,
142
- "loss": 1.7219,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.02043972298796477,
147
- "grad_norm": 0.6002236604690552,
148
  "learning_rate": 7.211443451095007e-05,
149
- "loss": 1.7398,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.021515497882068177,
154
- "grad_norm": 0.6054794788360596,
155
  "learning_rate": 6.91341716182545e-05,
156
- "loss": 1.778,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.022591272776171584,
161
- "grad_norm": 0.6320491433143616,
162
  "learning_rate": 6.607197326515808e-05,
163
- "loss": 1.7474,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 0.023667047670274995,
168
- "grad_norm": 0.6241698265075684,
169
  "learning_rate": 6.294095225512603e-05,
170
- "loss": 1.8189,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 0.024742822564378403,
175
- "grad_norm": 0.7055386304855347,
176
  "learning_rate": 5.9754516100806423e-05,
177
- "loss": 1.7957,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 0.025818597458481814,
182
- "grad_norm": 0.8027210235595703,
183
  "learning_rate": 5.6526309611002594e-05,
184
- "loss": 1.9507,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 0.02689437235258522,
189
- "grad_norm": 1.0420467853546143,
190
  "learning_rate": 5.327015646150716e-05,
191
- "loss": 2.1519,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 0.02689437235258522,
196
- "eval_loss": 1.7508697509765625,
197
- "eval_runtime": 186.2853,
198
- "eval_samples_per_second": 33.62,
199
- "eval_steps_per_second": 4.203,
200
  "step": 25
201
  },
202
  {
203
  "epoch": 0.027970147246688632,
204
- "grad_norm": 0.6345541477203369,
205
  "learning_rate": 5e-05,
206
- "loss": 1.5864,
207
  "step": 26
208
  },
209
  {
210
  "epoch": 0.02904592214079204,
211
- "grad_norm": 0.5340394377708435,
212
  "learning_rate": 4.6729843538492847e-05,
213
- "loss": 1.555,
214
  "step": 27
215
  },
216
  {
217
  "epoch": 0.030121697034895447,
218
- "grad_norm": 0.49378207325935364,
219
  "learning_rate": 4.347369038899744e-05,
220
- "loss": 1.6126,
221
  "step": 28
222
  },
223
  {
224
  "epoch": 0.031197471928998858,
225
- "grad_norm": 0.4962691068649292,
226
  "learning_rate": 4.0245483899193595e-05,
227
- "loss": 1.6681,
228
  "step": 29
229
  },
230
  {
231
  "epoch": 0.032273246823102265,
232
- "grad_norm": 0.490527480840683,
233
  "learning_rate": 3.705904774487396e-05,
234
- "loss": 1.7026,
235
  "step": 30
236
  },
237
  {
238
  "epoch": 0.033349021717205676,
239
- "grad_norm": 0.49440085887908936,
240
  "learning_rate": 3.392802673484193e-05,
241
- "loss": 1.6943,
242
  "step": 31
243
  },
244
  {
245
  "epoch": 0.03442479661130908,
246
- "grad_norm": 0.5249375700950623,
247
  "learning_rate": 3.086582838174551e-05,
248
- "loss": 1.7494,
249
  "step": 32
250
  },
251
  {
252
  "epoch": 0.03550057150541249,
253
- "grad_norm": 0.5410753488540649,
254
  "learning_rate": 2.7885565489049946e-05,
255
- "loss": 1.7389,
256
  "step": 33
257
  },
258
  {
259
  "epoch": 0.0365763463995159,
260
- "grad_norm": 0.5691052675247192,
261
  "learning_rate": 2.500000000000001e-05,
262
- "loss": 1.7568,
263
  "step": 34
264
  },
265
  {
266
  "epoch": 0.03765212129361931,
267
- "grad_norm": 0.628642201423645,
268
  "learning_rate": 2.2221488349019903e-05,
269
- "loss": 1.8005,
270
  "step": 35
271
  },
272
  {
273
  "epoch": 0.03872789618772272,
274
- "grad_norm": 0.6629976034164429,
275
  "learning_rate": 1.9561928549563968e-05,
276
- "loss": 1.8407,
277
  "step": 36
278
  },
279
  {
280
  "epoch": 0.03980367108182613,
281
- "grad_norm": 0.8179542422294617,
282
  "learning_rate": 1.703270924499656e-05,
283
- "loss": 1.9433,
284
  "step": 37
285
  },
286
  {
287
  "epoch": 0.04087944597592954,
288
- "grad_norm": 0.6521536707878113,
289
  "learning_rate": 1.4644660940672627e-05,
290
- "loss": 1.6141,
291
  "step": 38
292
  },
293
  {
294
  "epoch": 0.04195522087003294,
295
- "grad_norm": 0.5380288362503052,
296
  "learning_rate": 1.2408009626051137e-05,
297
- "loss": 1.6136,
298
  "step": 39
299
  },
300
  {
301
  "epoch": 0.043030995764136354,
302
- "grad_norm": 0.505171000957489,
303
  "learning_rate": 1.0332332985438248e-05,
304
- "loss": 1.5648,
305
  "step": 40
306
  },
307
  {
308
  "epoch": 0.044106770658239765,
309
- "grad_norm": 0.509820818901062,
310
  "learning_rate": 8.426519384872733e-06,
311
- "loss": 1.6574,
312
  "step": 41
313
  },
314
  {
315
  "epoch": 0.04518254555234317,
316
- "grad_norm": 0.5152492523193359,
317
  "learning_rate": 6.698729810778065e-06,
318
- "loss": 1.7135,
319
  "step": 42
320
  },
321
  {
322
  "epoch": 0.04625832044644658,
323
- "grad_norm": 0.4926588535308838,
324
  "learning_rate": 5.156362923365588e-06,
325
- "loss": 1.6862,
326
  "step": 43
327
  },
328
  {
329
  "epoch": 0.04733409534054999,
330
- "grad_norm": 0.5057544708251953,
331
  "learning_rate": 3.8060233744356633e-06,
332
- "loss": 1.7803,
333
  "step": 44
334
  },
335
  {
336
  "epoch": 0.0484098702346534,
337
- "grad_norm": 0.5117193460464478,
338
  "learning_rate": 2.653493525244721e-06,
339
- "loss": 1.6953,
340
  "step": 45
341
  },
342
  {
343
  "epoch": 0.049485645128756806,
344
- "grad_norm": 0.5249567627906799,
345
  "learning_rate": 1.70370868554659e-06,
346
- "loss": 1.7361,
347
  "step": 46
348
  },
349
  {
350
  "epoch": 0.050561420022860216,
351
- "grad_norm": 0.5613279342651367,
352
  "learning_rate": 9.607359798384785e-07,
353
- "loss": 1.7436,
354
  "step": 47
355
  },
356
  {
357
  "epoch": 0.05163719491696363,
358
- "grad_norm": 0.6121152639389038,
359
  "learning_rate": 4.277569313094809e-07,
360
- "loss": 1.8016,
361
  "step": 48
362
  },
363
  {
364
  "epoch": 0.05271296981106703,
365
- "grad_norm": 0.6896836757659912,
366
  "learning_rate": 1.0705383806982606e-07,
367
- "loss": 1.9185,
368
  "step": 49
369
  },
370
  {
371
  "epoch": 0.05378874470517044,
372
- "grad_norm": 0.9745162725448608,
373
  "learning_rate": 0.0,
374
- "loss": 2.1614,
375
  "step": 50
376
  },
377
  {
378
  "epoch": 0.05378874470517044,
379
- "eval_loss": 1.7394925355911255,
380
- "eval_runtime": 186.2842,
381
- "eval_samples_per_second": 33.621,
382
- "eval_steps_per_second": 4.203,
383
  "step": 50
384
  }
385
  ],
 
1
  {
2
+ "best_metric": 1.7409106492996216,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
  "epoch": 0.05378874470517044,
5
  "eval_steps": 25,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.0010757748941034088,
13
+ "grad_norm": 2.889035224914551,
14
  "learning_rate": 5e-05,
15
+ "loss": 1.7307,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.0010757748941034088,
20
+ "eval_loss": 2.065730094909668,
21
+ "eval_runtime": 186.3032,
22
+ "eval_samples_per_second": 33.617,
23
+ "eval_steps_per_second": 4.203,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.0021515497882068175,
28
+ "grad_norm": 2.8928565979003906,
29
  "learning_rate": 0.0001,
30
+ "loss": 1.8653,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.0032273246823102267,
35
+ "grad_norm": 1.6839524507522583,
36
  "learning_rate": 9.989294616193017e-05,
37
+ "loss": 1.756,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.004303099576413635,
42
+ "grad_norm": 0.8242851495742798,
43
  "learning_rate": 9.957224306869053e-05,
44
+ "loss": 1.7457,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.005378874470517044,
49
+ "grad_norm": 1.0334848165512085,
50
  "learning_rate": 9.903926402016153e-05,
51
+ "loss": 1.7532,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.006454649364620453,
56
+ "grad_norm": 0.7117134928703308,
57
  "learning_rate": 9.829629131445342e-05,
58
+ "loss": 1.7827,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.007530424258723862,
63
+ "grad_norm": 0.7202480435371399,
64
  "learning_rate": 9.73465064747553e-05,
65
+ "loss": 1.8289,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.00860619915282727,
70
+ "grad_norm": 0.6732454299926758,
71
  "learning_rate": 9.619397662556435e-05,
72
+ "loss": 1.7357,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.00968197404693068,
77
+ "grad_norm": 0.6462610960006714,
78
  "learning_rate": 9.484363707663442e-05,
79
+ "loss": 1.7847,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 0.010757748941034088,
84
+ "grad_norm": 0.7184572815895081,
85
  "learning_rate": 9.330127018922194e-05,
86
+ "loss": 1.8445,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.011833523835137498,
91
+ "grad_norm": 0.7928162813186646,
92
  "learning_rate": 9.157348061512727e-05,
93
+ "loss": 1.8327,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.012909298729240907,
98
+ "grad_norm": 0.9331445693969727,
99
  "learning_rate": 8.966766701456177e-05,
100
+ "loss": 2.0023,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.013985073623344316,
105
+ "grad_norm": 1.8583245277404785,
106
  "learning_rate": 8.759199037394887e-05,
107
+ "loss": 1.6557,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.015060848517447724,
112
+ "grad_norm": 1.4030020236968994,
113
  "learning_rate": 8.535533905932738e-05,
114
+ "loss": 1.6399,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.016136623411551133,
119
+ "grad_norm": 1.2228798866271973,
120
  "learning_rate": 8.296729075500344e-05,
121
+ "loss": 1.637,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.01721239830565454,
126
+ "grad_norm": 0.8515083193778992,
127
  "learning_rate": 8.043807145043604e-05,
128
+ "loss": 1.6325,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.01828817319975795,
133
+ "grad_norm": 0.6020737290382385,
134
  "learning_rate": 7.777851165098012e-05,
135
+ "loss": 1.6861,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.01936394809386136,
140
+ "grad_norm": 0.658804714679718,
141
  "learning_rate": 7.500000000000001e-05,
142
+ "loss": 1.7261,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.02043972298796477,
147
+ "grad_norm": 0.6308284997940063,
148
  "learning_rate": 7.211443451095007e-05,
149
+ "loss": 1.7423,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.021515497882068177,
154
+ "grad_norm": 0.6279967427253723,
155
  "learning_rate": 6.91341716182545e-05,
156
+ "loss": 1.7781,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.022591272776171584,
161
+ "grad_norm": 0.6446429491043091,
162
  "learning_rate": 6.607197326515808e-05,
163
+ "loss": 1.747,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 0.023667047670274995,
168
+ "grad_norm": 0.6265982985496521,
169
  "learning_rate": 6.294095225512603e-05,
170
+ "loss": 1.8178,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 0.024742822564378403,
175
+ "grad_norm": 0.695231556892395,
176
  "learning_rate": 5.9754516100806423e-05,
177
+ "loss": 1.7954,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 0.025818597458481814,
182
+ "grad_norm": 0.7961277365684509,
183
  "learning_rate": 5.6526309611002594e-05,
184
+ "loss": 1.9499,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 0.02689437235258522,
189
+ "grad_norm": 1.026402235031128,
190
  "learning_rate": 5.327015646150716e-05,
191
+ "loss": 2.1511,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 0.02689437235258522,
196
+ "eval_loss": 1.753453016281128,
197
+ "eval_runtime": 186.4029,
198
+ "eval_samples_per_second": 33.599,
199
+ "eval_steps_per_second": 4.201,
200
  "step": 25
201
  },
202
  {
203
  "epoch": 0.027970147246688632,
204
+ "grad_norm": 0.6362124681472778,
205
  "learning_rate": 5e-05,
206
+ "loss": 1.5936,
207
  "step": 26
208
  },
209
  {
210
  "epoch": 0.02904592214079204,
211
+ "grad_norm": 0.5519288182258606,
212
  "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 1.5623,
214
  "step": 27
215
  },
216
  {
217
  "epoch": 0.030121697034895447,
218
+ "grad_norm": 0.4948122501373291,
219
  "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.6165,
221
  "step": 28
222
  },
223
  {
224
  "epoch": 0.031197471928998858,
225
+ "grad_norm": 0.5037927627563477,
226
  "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 1.6709,
228
  "step": 29
229
  },
230
  {
231
  "epoch": 0.032273246823102265,
232
+ "grad_norm": 0.5008567571640015,
233
  "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.7043,
235
  "step": 30
236
  },
237
  {
238
  "epoch": 0.033349021717205676,
239
+ "grad_norm": 0.5066686272621155,
240
  "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.6957,
242
  "step": 31
243
  },
244
  {
245
  "epoch": 0.03442479661130908,
246
+ "grad_norm": 0.5251875519752502,
247
  "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.7502,
249
  "step": 32
250
  },
251
  {
252
  "epoch": 0.03550057150541249,
253
+ "grad_norm": 0.5396082401275635,
254
  "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.7408,
256
  "step": 33
257
  },
258
  {
259
  "epoch": 0.0365763463995159,
260
+ "grad_norm": 0.5625227689743042,
261
  "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.7587,
263
  "step": 34
264
  },
265
  {
266
  "epoch": 0.03765212129361931,
267
+ "grad_norm": 0.5840663909912109,
268
  "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.8015,
270
  "step": 35
271
  },
272
  {
273
  "epoch": 0.03872789618772272,
274
+ "grad_norm": 0.6661264300346375,
275
  "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 1.8426,
277
  "step": 36
278
  },
279
  {
280
  "epoch": 0.03980367108182613,
281
+ "grad_norm": 0.8346494436264038,
282
  "learning_rate": 1.703270924499656e-05,
283
+ "loss": 1.9472,
284
  "step": 37
285
  },
286
  {
287
  "epoch": 0.04087944597592954,
288
+ "grad_norm": 0.6206389665603638,
289
  "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 1.6175,
291
  "step": 38
292
  },
293
  {
294
  "epoch": 0.04195522087003294,
295
+ "grad_norm": 0.5432288646697998,
296
  "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 1.6168,
298
  "step": 39
299
  },
300
  {
301
  "epoch": 0.043030995764136354,
302
+ "grad_norm": 0.501873254776001,
303
  "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 1.5663,
305
  "step": 40
306
  },
307
  {
308
  "epoch": 0.044106770658239765,
309
+ "grad_norm": 0.4983377158641815,
310
  "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.6572,
312
  "step": 41
313
  },
314
  {
315
  "epoch": 0.04518254555234317,
316
+ "grad_norm": 0.4926607608795166,
317
  "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.7136,
319
  "step": 42
320
  },
321
  {
322
  "epoch": 0.04625832044644658,
323
+ "grad_norm": 0.4842887222766876,
324
  "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.6859,
326
  "step": 43
327
  },
328
  {
329
  "epoch": 0.04733409534054999,
330
+ "grad_norm": 0.4948004484176636,
331
  "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.7795,
333
  "step": 44
334
  },
335
  {
336
  "epoch": 0.0484098702346534,
337
+ "grad_norm": 0.5172557830810547,
338
  "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.6963,
340
  "step": 45
341
  },
342
  {
343
  "epoch": 0.049485645128756806,
344
+ "grad_norm": 0.5146644711494446,
345
  "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.7358,
347
  "step": 46
348
  },
349
  {
350
  "epoch": 0.050561420022860216,
351
+ "grad_norm": 0.5665210485458374,
352
  "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.7453,
354
  "step": 47
355
  },
356
  {
357
  "epoch": 0.05163719491696363,
358
+ "grad_norm": 0.6140392422676086,
359
  "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.8031,
361
  "step": 48
362
  },
363
  {
364
  "epoch": 0.05271296981106703,
365
+ "grad_norm": 0.7129289507865906,
366
  "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 1.9231,
368
  "step": 49
369
  },
370
  {
371
  "epoch": 0.05378874470517044,
372
+ "grad_norm": 1.0026451349258423,
373
  "learning_rate": 0.0,
374
+ "loss": 2.1672,
375
  "step": 50
376
  },
377
  {
378
  "epoch": 0.05378874470517044,
379
+ "eval_loss": 1.7409106492996216,
380
+ "eval_runtime": 186.33,
381
+ "eval_samples_per_second": 33.612,
382
+ "eval_steps_per_second": 4.202,
383
  "step": 50
384
  }
385
  ],
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:987fd07a10c7dc3d0202f3fd844ca5c32e5eda76cf15397ae30934c49a3acd1e
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde298347aefb5569ecda1d0ffbfc1f74fe5a8aad71a508769958efdcaf21bdf
3
  size 6776