kevinoli commited on
Commit
2642c5f
1 Parent(s): 5faa8bb

Training in progress, step 11500, checkpoint

Browse files
checkpoint-11500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84e1ee6b3c168b207fca02305df1519c614139dc265aa30e8f2be4ba697cfdcd
3
  size 1711848436
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7f294b2c0022fc60e5f79be2880b9040e4ddbddefe6df37e3a5bd55b190597
3
  size 1711848436
checkpoint-11500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ff6bd3bc2250bf3d9795e789b8676a822d32772918a505f5f0d75af5290dfdb
3
  size 3424043887
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfadb03e6f4ffeeb7e0e53bd6fadc2d3778ffb65b36404fdb60e5738d8d71d90
3
  size 3424043887
checkpoint-11500/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.5536245703697205,
3
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-11500",
4
  "epoch": 2.1186440677966103,
5
  "eval_steps": 500,
@@ -10,347 +10,347 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.09211495946941783,
13
- "grad_norm": 3.083087682723999,
14
  "learning_rate": 4.84647506755097e-07,
15
- "loss": 0.2708,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.09211495946941783,
20
- "eval_loss": 1.0631108283996582,
21
- "eval_runtime": 74.1964,
22
- "eval_samples_per_second": 16.268,
23
- "eval_steps_per_second": 2.035,
24
  "step": 500
25
  },
26
  {
27
  "epoch": 0.18422991893883567,
28
- "grad_norm": 7.726487159729004,
29
  "learning_rate": 4.69295013510194e-07,
30
- "loss": 0.251,
31
  "step": 1000
32
  },
33
  {
34
  "epoch": 0.18422991893883567,
35
- "eval_loss": 0.942773699760437,
36
- "eval_runtime": 74.6047,
37
- "eval_samples_per_second": 16.179,
38
- "eval_steps_per_second": 2.024,
39
  "step": 1000
40
  },
41
  {
42
  "epoch": 0.2763448784082535,
43
- "grad_norm": 0.02718021161854267,
44
  "learning_rate": 4.5394252026529107e-07,
45
- "loss": 0.235,
46
  "step": 1500
47
  },
48
  {
49
  "epoch": 0.2763448784082535,
50
- "eval_loss": 0.8716810345649719,
51
- "eval_runtime": 75.03,
52
- "eval_samples_per_second": 16.087,
53
- "eval_steps_per_second": 2.013,
54
  "step": 1500
55
  },
56
  {
57
  "epoch": 0.36845983787767134,
58
- "grad_norm": 0.0001215290030813776,
59
  "learning_rate": 4.385900270203881e-07,
60
- "loss": 0.1529,
61
  "step": 2000
62
  },
63
  {
64
  "epoch": 0.36845983787767134,
65
- "eval_loss": 0.8318113088607788,
66
- "eval_runtime": 76.6917,
67
- "eval_samples_per_second": 15.738,
68
- "eval_steps_per_second": 1.969,
69
  "step": 2000
70
  },
71
  {
72
  "epoch": 0.46057479734708917,
73
- "grad_norm": 419.545166015625,
74
  "learning_rate": 4.232375337754851e-07,
75
- "loss": 0.1781,
76
  "step": 2500
77
  },
78
  {
79
  "epoch": 0.46057479734708917,
80
- "eval_loss": 0.7549223303794861,
81
- "eval_runtime": 75.2036,
82
- "eval_samples_per_second": 16.05,
83
- "eval_steps_per_second": 2.008,
84
  "step": 2500
85
  },
86
  {
87
  "epoch": 0.552689756816507,
88
- "grad_norm": 368.7484436035156,
89
  "learning_rate": 4.0788504053058217e-07,
90
- "loss": 0.1681,
91
  "step": 3000
92
  },
93
  {
94
  "epoch": 0.552689756816507,
95
- "eval_loss": 0.7217888236045837,
96
- "eval_runtime": 76.0606,
97
- "eval_samples_per_second": 15.869,
98
- "eval_steps_per_second": 1.985,
99
  "step": 3000
100
  },
101
  {
102
  "epoch": 0.6448047162859248,
103
- "grad_norm": 20.03949737548828,
104
  "learning_rate": 3.925325472856792e-07,
105
- "loss": 0.1064,
106
  "step": 3500
107
  },
108
  {
109
  "epoch": 0.6448047162859248,
110
- "eval_loss": 0.7048410177230835,
111
- "eval_runtime": 76.0578,
112
- "eval_samples_per_second": 15.87,
113
- "eval_steps_per_second": 1.985,
114
  "step": 3500
115
  },
116
  {
117
  "epoch": 0.7369196757553427,
118
- "grad_norm": 363.6124267578125,
119
  "learning_rate": 3.771800540407762e-07,
120
- "loss": 0.1357,
121
  "step": 4000
122
  },
123
  {
124
  "epoch": 0.7369196757553427,
125
- "eval_loss": 0.6961681246757507,
126
- "eval_runtime": 76.3574,
127
- "eval_samples_per_second": 15.807,
128
- "eval_steps_per_second": 1.978,
129
  "step": 4000
130
  },
131
  {
132
  "epoch": 0.8290346352247605,
133
- "grad_norm": 494.03570556640625,
134
  "learning_rate": 3.618275607958732e-07,
135
- "loss": 0.1098,
136
  "step": 4500
137
  },
138
  {
139
  "epoch": 0.8290346352247605,
140
- "eval_loss": 0.6778352856636047,
141
- "eval_runtime": 76.4844,
142
- "eval_samples_per_second": 15.781,
143
- "eval_steps_per_second": 1.974,
144
  "step": 4500
145
  },
146
  {
147
  "epoch": 0.9211495946941783,
148
- "grad_norm": 4.2969353671651334e-05,
149
  "learning_rate": 3.464750675509703e-07,
150
- "loss": 0.1142,
151
  "step": 5000
152
  },
153
  {
154
  "epoch": 0.9211495946941783,
155
- "eval_loss": 0.6656659245491028,
156
- "eval_runtime": 76.6475,
157
- "eval_samples_per_second": 15.747,
158
- "eval_steps_per_second": 1.97,
159
  "step": 5000
160
  },
161
  {
162
  "epoch": 1.013264554163596,
163
- "grad_norm": 0.0010161151876673102,
164
  "learning_rate": 3.311225743060673e-07,
165
- "loss": 0.1113,
166
  "step": 5500
167
  },
168
  {
169
  "epoch": 1.013264554163596,
170
- "eval_loss": 0.6430702209472656,
171
- "eval_runtime": 76.4915,
172
- "eval_samples_per_second": 15.78,
173
- "eval_steps_per_second": 1.974,
174
  "step": 5500
175
  },
176
  {
177
  "epoch": 1.105379513633014,
178
- "grad_norm": 0.05515381693840027,
179
  "learning_rate": 3.157700810611643e-07,
180
- "loss": 0.0572,
181
  "step": 6000
182
  },
183
  {
184
  "epoch": 1.105379513633014,
185
- "eval_loss": 0.636746883392334,
186
- "eval_runtime": 76.0169,
187
- "eval_samples_per_second": 15.878,
188
- "eval_steps_per_second": 1.986,
189
  "step": 6000
190
  },
191
  {
192
  "epoch": 1.1974944731024317,
193
- "grad_norm": 0.0038496837951242924,
194
  "learning_rate": 3.0041758781626137e-07,
195
- "loss": 0.0746,
196
  "step": 6500
197
  },
198
  {
199
  "epoch": 1.1974944731024317,
200
- "eval_loss": 0.6261336207389832,
201
- "eval_runtime": 76.1916,
202
- "eval_samples_per_second": 15.842,
203
- "eval_steps_per_second": 1.982,
204
  "step": 6500
205
  },
206
  {
207
  "epoch": 1.2896094325718497,
208
- "grad_norm": 2.594869386030041e-07,
209
  "learning_rate": 2.8506509457135833e-07,
210
- "loss": 0.0494,
211
  "step": 7000
212
  },
213
  {
214
  "epoch": 1.2896094325718497,
215
- "eval_loss": 0.6245251893997192,
216
- "eval_runtime": 75.9712,
217
- "eval_samples_per_second": 15.888,
218
- "eval_steps_per_second": 1.988,
219
  "step": 7000
220
  },
221
  {
222
  "epoch": 1.3817243920412676,
223
- "grad_norm": 25.23366928100586,
224
  "learning_rate": 2.697126013264554e-07,
225
- "loss": 0.0788,
226
  "step": 7500
227
  },
228
  {
229
  "epoch": 1.3817243920412676,
230
- "eval_loss": 0.611993670463562,
231
- "eval_runtime": 75.1885,
232
- "eval_samples_per_second": 16.053,
233
- "eval_steps_per_second": 2.008,
234
  "step": 7500
235
  },
236
  {
237
  "epoch": 1.4738393515106853,
238
- "grad_norm": 0.0002172550739487633,
239
  "learning_rate": 2.5436010808155247e-07,
240
- "loss": 0.0808,
241
  "step": 8000
242
  },
243
  {
244
  "epoch": 1.4738393515106853,
245
- "eval_loss": 0.6011174917221069,
246
- "eval_runtime": 76.2572,
247
- "eval_samples_per_second": 15.828,
248
- "eval_steps_per_second": 1.98,
249
  "step": 8000
250
  },
251
  {
252
  "epoch": 1.565954310980103,
253
- "grad_norm": 0.032347481697797775,
254
  "learning_rate": 2.390076148366495e-07,
255
  "loss": 0.0536,
256
  "step": 8500
257
  },
258
  {
259
  "epoch": 1.565954310980103,
260
- "eval_loss": 0.5893377661705017,
261
- "eval_runtime": 75.429,
262
- "eval_samples_per_second": 16.002,
263
- "eval_steps_per_second": 2.002,
264
  "step": 8500
265
  },
266
  {
267
  "epoch": 1.658069270449521,
268
- "grad_norm": 2.7040863415095373e-07,
269
  "learning_rate": 2.236551215917465e-07,
270
- "loss": 0.0869,
271
  "step": 9000
272
  },
273
  {
274
  "epoch": 1.658069270449521,
275
- "eval_loss": 0.59163498878479,
276
- "eval_runtime": 75.4027,
277
- "eval_samples_per_second": 16.007,
278
- "eval_steps_per_second": 2.003,
279
  "step": 9000
280
  },
281
  {
282
  "epoch": 1.750184229918939,
283
- "grad_norm": 3.4501523166197146e-11,
284
  "learning_rate": 2.083026283468435e-07,
285
- "loss": 0.0752,
286
  "step": 9500
287
  },
288
  {
289
  "epoch": 1.750184229918939,
290
- "eval_loss": 0.5707471370697021,
291
- "eval_runtime": 76.0154,
292
- "eval_samples_per_second": 15.878,
293
- "eval_steps_per_second": 1.986,
294
  "step": 9500
295
  },
296
  {
297
  "epoch": 1.8422991893883567,
298
- "grad_norm": 0.00039183301851153374,
299
  "learning_rate": 1.9295013510194055e-07,
300
- "loss": 0.0577,
301
  "step": 10000
302
  },
303
  {
304
  "epoch": 1.8422991893883567,
305
- "eval_loss": 0.5678250789642334,
306
- "eval_runtime": 75.8084,
307
- "eval_samples_per_second": 15.922,
308
- "eval_steps_per_second": 1.992,
309
  "step": 10000
310
  },
311
  {
312
  "epoch": 1.9344141488577744,
313
- "grad_norm": 1.0438248487787405e-08,
314
  "learning_rate": 1.7759764185703757e-07,
315
- "loss": 0.0891,
316
  "step": 10500
317
  },
318
  {
319
  "epoch": 1.9344141488577744,
320
- "eval_loss": 0.563089907169342,
321
- "eval_runtime": 75.3868,
322
- "eval_samples_per_second": 16.011,
323
- "eval_steps_per_second": 2.003,
324
  "step": 10500
325
  },
326
  {
327
  "epoch": 2.026529108327192,
328
- "grad_norm": 1.162303306045942e-06,
329
  "learning_rate": 1.6224514861213458e-07,
330
- "loss": 0.0559,
331
  "step": 11000
332
  },
333
  {
334
  "epoch": 2.026529108327192,
335
- "eval_loss": 0.5547806620597839,
336
- "eval_runtime": 76.4427,
337
- "eval_samples_per_second": 15.79,
338
- "eval_steps_per_second": 1.975,
339
  "step": 11000
340
  },
341
  {
342
  "epoch": 2.1186440677966103,
343
- "grad_norm": 123.83905029296875,
344
  "learning_rate": 1.4689265536723165e-07,
345
- "loss": 0.0385,
346
  "step": 11500
347
  },
348
  {
349
  "epoch": 2.1186440677966103,
350
- "eval_loss": 0.5536245703697205,
351
- "eval_runtime": 75.6886,
352
- "eval_samples_per_second": 15.947,
353
- "eval_steps_per_second": 1.995,
354
  "step": 11500
355
  }
356
  ],
 
1
  {
2
+ "best_metric": 0.5532959699630737,
3
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-11500",
4
  "epoch": 2.1186440677966103,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.09211495946941783,
13
+ "grad_norm": 2.6780805587768555,
14
  "learning_rate": 4.84647506755097e-07,
15
+ "loss": 0.2705,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.09211495946941783,
20
+ "eval_loss": 1.0680681467056274,
21
+ "eval_runtime": 74.5723,
22
+ "eval_samples_per_second": 16.186,
23
+ "eval_steps_per_second": 2.025,
24
  "step": 500
25
  },
26
  {
27
  "epoch": 0.18422991893883567,
28
+ "grad_norm": 8.301130294799805,
29
  "learning_rate": 4.69295013510194e-07,
30
+ "loss": 0.2545,
31
  "step": 1000
32
  },
33
  {
34
  "epoch": 0.18422991893883567,
35
+ "eval_loss": 0.9443553686141968,
36
+ "eval_runtime": 74.9643,
37
+ "eval_samples_per_second": 16.101,
38
+ "eval_steps_per_second": 2.014,
39
  "step": 1000
40
  },
41
  {
42
  "epoch": 0.2763448784082535,
43
+ "grad_norm": 0.018898434937000275,
44
  "learning_rate": 4.5394252026529107e-07,
45
+ "loss": 0.234,
46
  "step": 1500
47
  },
48
  {
49
  "epoch": 0.2763448784082535,
50
+ "eval_loss": 0.876915693283081,
51
+ "eval_runtime": 75.6401,
52
+ "eval_samples_per_second": 15.957,
53
+ "eval_steps_per_second": 1.996,
54
  "step": 1500
55
  },
56
  {
57
  "epoch": 0.36845983787767134,
58
+ "grad_norm": 0.00010984255641233176,
59
  "learning_rate": 4.385900270203881e-07,
60
+ "loss": 0.1539,
61
  "step": 2000
62
  },
63
  {
64
  "epoch": 0.36845983787767134,
65
+ "eval_loss": 0.8415330648422241,
66
+ "eval_runtime": 76.9959,
67
+ "eval_samples_per_second": 15.676,
68
+ "eval_steps_per_second": 1.961,
69
  "step": 2000
70
  },
71
  {
72
  "epoch": 0.46057479734708917,
73
+ "grad_norm": 395.890625,
74
  "learning_rate": 4.232375337754851e-07,
75
+ "loss": 0.1766,
76
  "step": 2500
77
  },
78
  {
79
  "epoch": 0.46057479734708917,
80
+ "eval_loss": 0.7660450339317322,
81
+ "eval_runtime": 76.733,
82
+ "eval_samples_per_second": 15.73,
83
+ "eval_steps_per_second": 1.968,
84
  "step": 2500
85
  },
86
  {
87
  "epoch": 0.552689756816507,
88
+ "grad_norm": 363.6924743652344,
89
  "learning_rate": 4.0788504053058217e-07,
90
+ "loss": 0.1679,
91
  "step": 3000
92
  },
93
  {
94
  "epoch": 0.552689756816507,
95
+ "eval_loss": 0.7269155383110046,
96
+ "eval_runtime": 76.7928,
97
+ "eval_samples_per_second": 15.718,
98
+ "eval_steps_per_second": 1.966,
99
  "step": 3000
100
  },
101
  {
102
  "epoch": 0.6448047162859248,
103
+ "grad_norm": 28.914026260375977,
104
  "learning_rate": 3.925325472856792e-07,
105
+ "loss": 0.1104,
106
  "step": 3500
107
  },
108
  {
109
  "epoch": 0.6448047162859248,
110
+ "eval_loss": 0.7097663283348083,
111
+ "eval_runtime": 76.6897,
112
+ "eval_samples_per_second": 15.739,
113
+ "eval_steps_per_second": 1.969,
114
  "step": 3500
115
  },
116
  {
117
  "epoch": 0.7369196757553427,
118
+ "grad_norm": 116.85651397705078,
119
  "learning_rate": 3.771800540407762e-07,
120
+ "loss": 0.1367,
121
  "step": 4000
122
  },
123
  {
124
  "epoch": 0.7369196757553427,
125
+ "eval_loss": 0.6968969106674194,
126
+ "eval_runtime": 77.1872,
127
+ "eval_samples_per_second": 15.637,
128
+ "eval_steps_per_second": 1.956,
129
  "step": 4000
130
  },
131
  {
132
  "epoch": 0.8290346352247605,
133
+ "grad_norm": 391.0343322753906,
134
  "learning_rate": 3.618275607958732e-07,
135
+ "loss": 0.1129,
136
  "step": 4500
137
  },
138
  {
139
  "epoch": 0.8290346352247605,
140
+ "eval_loss": 0.6776800751686096,
141
+ "eval_runtime": 75.0351,
142
+ "eval_samples_per_second": 16.086,
143
+ "eval_steps_per_second": 2.012,
144
  "step": 4500
145
  },
146
  {
147
  "epoch": 0.9211495946941783,
148
+ "grad_norm": 2.0514346033451147e-05,
149
  "learning_rate": 3.464750675509703e-07,
150
+ "loss": 0.1125,
151
  "step": 5000
152
  },
153
  {
154
  "epoch": 0.9211495946941783,
155
+ "eval_loss": 0.6658498048782349,
156
+ "eval_runtime": 77.111,
157
+ "eval_samples_per_second": 15.653,
158
+ "eval_steps_per_second": 1.958,
159
  "step": 5000
160
  },
161
  {
162
  "epoch": 1.013264554163596,
163
+ "grad_norm": 0.000568103976547718,
164
  "learning_rate": 3.311225743060673e-07,
165
+ "loss": 0.1071,
166
  "step": 5500
167
  },
168
  {
169
  "epoch": 1.013264554163596,
170
+ "eval_loss": 0.6465296149253845,
171
+ "eval_runtime": 75.2951,
172
+ "eval_samples_per_second": 16.03,
173
+ "eval_steps_per_second": 2.005,
174
  "step": 5500
175
  },
176
  {
177
  "epoch": 1.105379513633014,
178
+ "grad_norm": 0.02698369137942791,
179
  "learning_rate": 3.157700810611643e-07,
180
+ "loss": 0.0553,
181
  "step": 6000
182
  },
183
  {
184
  "epoch": 1.105379513633014,
185
+ "eval_loss": 0.6357071995735168,
186
+ "eval_runtime": 76.6726,
187
+ "eval_samples_per_second": 15.742,
188
+ "eval_steps_per_second": 1.969,
189
  "step": 6000
190
  },
191
  {
192
  "epoch": 1.1974944731024317,
193
+ "grad_norm": 0.0005627564387395978,
194
  "learning_rate": 3.0041758781626137e-07,
195
+ "loss": 0.0729,
196
  "step": 6500
197
  },
198
  {
199
  "epoch": 1.1974944731024317,
200
+ "eval_loss": 0.628384530544281,
201
+ "eval_runtime": 75.6565,
202
+ "eval_samples_per_second": 15.954,
203
+ "eval_steps_per_second": 1.996,
204
  "step": 6500
205
  },
206
  {
207
  "epoch": 1.2896094325718497,
208
+ "grad_norm": 4.7338733111246256e-07,
209
  "learning_rate": 2.8506509457135833e-07,
210
+ "loss": 0.0476,
211
  "step": 7000
212
  },
213
  {
214
  "epoch": 1.2896094325718497,
215
+ "eval_loss": 0.6259528994560242,
216
+ "eval_runtime": 75.2674,
217
+ "eval_samples_per_second": 16.036,
218
+ "eval_steps_per_second": 2.006,
219
  "step": 7000
220
  },
221
  {
222
  "epoch": 1.3817243920412676,
223
+ "grad_norm": 28.43704605102539,
224
  "learning_rate": 2.697126013264554e-07,
225
+ "loss": 0.0756,
226
  "step": 7500
227
  },
228
  {
229
  "epoch": 1.3817243920412676,
230
+ "eval_loss": 0.6102285981178284,
231
+ "eval_runtime": 76.1062,
232
+ "eval_samples_per_second": 15.859,
233
+ "eval_steps_per_second": 1.984,
234
  "step": 7500
235
  },
236
  {
237
  "epoch": 1.4738393515106853,
238
+ "grad_norm": 0.0002958567056339234,
239
  "learning_rate": 2.5436010808155247e-07,
240
+ "loss": 0.0797,
241
  "step": 8000
242
  },
243
  {
244
  "epoch": 1.4738393515106853,
245
+ "eval_loss": 0.6023213267326355,
246
+ "eval_runtime": 75.1644,
247
+ "eval_samples_per_second": 16.058,
248
+ "eval_steps_per_second": 2.009,
249
  "step": 8000
250
  },
251
  {
252
  "epoch": 1.565954310980103,
253
+ "grad_norm": 0.0021068258211016655,
254
  "learning_rate": 2.390076148366495e-07,
255
  "loss": 0.0536,
256
  "step": 8500
257
  },
258
  {
259
  "epoch": 1.565954310980103,
260
+ "eval_loss": 0.5879408121109009,
261
+ "eval_runtime": 76.0196,
262
+ "eval_samples_per_second": 15.877,
263
+ "eval_steps_per_second": 1.986,
264
  "step": 8500
265
  },
266
  {
267
  "epoch": 1.658069270449521,
268
+ "grad_norm": 4.1152270569000393e-07,
269
  "learning_rate": 2.236551215917465e-07,
270
+ "loss": 0.0784,
271
  "step": 9000
272
  },
273
  {
274
  "epoch": 1.658069270449521,
275
+ "eval_loss": 0.5879626274108887,
276
+ "eval_runtime": 75.6453,
277
+ "eval_samples_per_second": 15.956,
278
+ "eval_steps_per_second": 1.996,
279
  "step": 9000
280
  },
281
  {
282
  "epoch": 1.750184229918939,
283
+ "grad_norm": 2.4213447913368213e-10,
284
  "learning_rate": 2.083026283468435e-07,
285
+ "loss": 0.0703,
286
  "step": 9500
287
  },
288
  {
289
  "epoch": 1.750184229918939,
290
+ "eval_loss": 0.5665237307548523,
291
+ "eval_runtime": 74.9732,
292
+ "eval_samples_per_second": 16.099,
293
+ "eval_steps_per_second": 2.014,
294
  "step": 9500
295
  },
296
  {
297
  "epoch": 1.8422991893883567,
298
+ "grad_norm": 5.074160799267702e-05,
299
  "learning_rate": 1.9295013510194055e-07,
300
+ "loss": 0.0551,
301
  "step": 10000
302
  },
303
  {
304
  "epoch": 1.8422991893883567,
305
+ "eval_loss": 0.5670996308326721,
306
+ "eval_runtime": 75.902,
307
+ "eval_samples_per_second": 15.902,
308
+ "eval_steps_per_second": 1.989,
309
  "step": 10000
310
  },
311
  {
312
  "epoch": 1.9344141488577744,
313
+ "grad_norm": 6.560769350016926e-08,
314
  "learning_rate": 1.7759764185703757e-07,
315
+ "loss": 0.0852,
316
  "step": 10500
317
  },
318
  {
319
  "epoch": 1.9344141488577744,
320
+ "eval_loss": 0.5694836974143982,
321
+ "eval_runtime": 76.048,
322
+ "eval_samples_per_second": 15.872,
323
+ "eval_steps_per_second": 1.986,
324
  "step": 10500
325
  },
326
  {
327
  "epoch": 2.026529108327192,
328
+ "grad_norm": 4.498223916016286e-06,
329
  "learning_rate": 1.6224514861213458e-07,
330
+ "loss": 0.0546,
331
  "step": 11000
332
  },
333
  {
334
  "epoch": 2.026529108327192,
335
+ "eval_loss": 0.555758535861969,
336
+ "eval_runtime": 74.9986,
337
+ "eval_samples_per_second": 16.094,
338
+ "eval_steps_per_second": 2.013,
339
  "step": 11000
340
  },
341
  {
342
  "epoch": 2.1186440677966103,
343
+ "grad_norm": 273.0765380859375,
344
  "learning_rate": 1.4689265536723165e-07,
345
+ "loss": 0.0369,
346
  "step": 11500
347
  },
348
  {
349
  "epoch": 2.1186440677966103,
350
+ "eval_loss": 0.5532959699630737,
351
+ "eval_runtime": 74.8225,
352
+ "eval_samples_per_second": 16.132,
353
+ "eval_steps_per_second": 2.018,
354
  "step": 11500
355
  }
356
  ],
checkpoint-11500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9589d95f7287a546fe28eed1162f0176f1b95b18274e91ad5fc36f7db12aeb
3
  size 4847
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea34fd4333686a44a60d290faa4ae8e00df783131842d9ae3ef1b9e874a39349
3
  size 4847