TensorBoard
Safetensors
English
llama
appvoid commited on
Commit
2a55cbf
·
verified ·
1 Parent(s): 898bc9f

Deep35 continual checkpoint step 76000

Browse files
last-checkpoint/continual_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "global_step": 74000,
3
- "sequence_tokens_emitted": 12452085760,
4
  "mix": [
5
  0.8,
6
  0.09,
@@ -56,5 +56,5 @@
56
  "current_batch_size": 240,
57
  "current_gradient_accumulation": 1,
58
  "current_tokens_per_update": 245760,
59
- "cumulative_tokens_at_save": 12451840000
60
  }
 
1
  {
2
+ "global_step": 76000,
3
+ "sequence_tokens_emitted": 12943605760,
4
  "mix": [
5
  0.8,
6
  0.09,
 
56
  "current_batch_size": 240,
57
  "current_gradient_accumulation": 1,
58
  "current_tokens_per_update": 245760,
59
+ "cumulative_tokens_at_save": 12943360000
60
  }
last-checkpoint/data_state.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:193b8481b71b1e462deba4e1d2588971efc2907c27434cf80029c855d9776d7c
3
- size 23167
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db0a7528b879de1dd934b14c71e1ac12e62298372db610dedec8f1bb6401bd5
3
+ size 9215
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b238f149de3df051122be2427756f6faaf2af03650f9b9d011212e7590a1afd0
3
  size 70326256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45da2581647cc8a686f27829602eb15c2bd790db8d3cf80c62d457a94ff9c77f
3
  size 70326256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa89a2f6d6f0cd57b2adea3fa0e8883e58d6926ed5f359ad97b230faf57e3636
3
  size 140740171
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa306709fe81f84ce797b20706082cc13adac4e3596cc0f66a027286af1e5f16
3
  size 140740171
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5b477bccf313d86ce4e238573f0377f2745a039e51df225133c25739f80f36b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95b12ec6f4fbca97257760646da87d062e7d41f499a559a59dcf7f57b03a6a8
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f75d234766fdf1d24ea2b12cb42d7f86a6198458ea79abb952eaaaeb050c7388
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c204a89545d4c45919c954c242782ce01d755f1aee403d4c206ed5abd551c5ab
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 1.2e-05,
6
  "eval_steps": 500,
7
- "global_step": 74000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -53090,6 +53090,1438 @@
53090
  "eval_samples_per_second": 462.734,
53091
  "eval_steps_per_second": 14.46,
53092
  "step": 74000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53093
  }
53094
  ],
53095
  "logging_steps": 10,
@@ -53109,7 +54541,7 @@
53109
  "attributes": {}
53110
  }
53111
  },
53112
- "total_flos": 1.70846098292736e+18,
53113
  "train_batch_size": 240,
53114
  "trial_name": null,
53115
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.3e-05,
6
  "eval_steps": 500,
7
+ "global_step": 76000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
53090
  "eval_samples_per_second": 462.734,
53091
  "eval_steps_per_second": 14.46,
53092
  "step": 74000
53093
+ },
53094
+ {
53095
+ "epoch": 1.2005e-05,
53096
+ "grad_norm": 0.470703125,
53097
+ "learning_rate": 2.9999999999999997e-05,
53098
+ "loss": 3.0497,
53099
+ "step": 74010
53100
+ },
53101
+ {
53102
+ "epoch": 1.201e-05,
53103
+ "grad_norm": 0.453125,
53104
+ "learning_rate": 2.9999999999999997e-05,
53105
+ "loss": 3.0465,
53106
+ "step": 74020
53107
+ },
53108
+ {
53109
+ "epoch": 1.2015e-05,
53110
+ "grad_norm": 0.44921875,
53111
+ "learning_rate": 2.9999999999999997e-05,
53112
+ "loss": 3.0514,
53113
+ "step": 74030
53114
+ },
53115
+ {
53116
+ "epoch": 1.202e-05,
53117
+ "grad_norm": 0.443359375,
53118
+ "learning_rate": 2.9999999999999997e-05,
53119
+ "loss": 3.0168,
53120
+ "step": 74040
53121
+ },
53122
+ {
53123
+ "epoch": 1.2025e-05,
53124
+ "grad_norm": 0.46484375,
53125
+ "learning_rate": 2.9999999999999997e-05,
53126
+ "loss": 3.0312,
53127
+ "step": 74050
53128
+ },
53129
+ {
53130
+ "epoch": 1.203e-05,
53131
+ "grad_norm": 0.462890625,
53132
+ "learning_rate": 2.9999999999999997e-05,
53133
+ "loss": 3.0419,
53134
+ "step": 74060
53135
+ },
53136
+ {
53137
+ "epoch": 1.2035e-05,
53138
+ "grad_norm": 0.4765625,
53139
+ "learning_rate": 2.9999999999999997e-05,
53140
+ "loss": 3.0464,
53141
+ "step": 74070
53142
+ },
53143
+ {
53144
+ "epoch": 1.204e-05,
53145
+ "grad_norm": 0.45703125,
53146
+ "learning_rate": 2.9999999999999997e-05,
53147
+ "loss": 3.0235,
53148
+ "step": 74080
53149
+ },
53150
+ {
53151
+ "epoch": 1.2045e-05,
53152
+ "grad_norm": 0.50390625,
53153
+ "learning_rate": 2.9999999999999997e-05,
53154
+ "loss": 3.043,
53155
+ "step": 74090
53156
+ },
53157
+ {
53158
+ "epoch": 1.205e-05,
53159
+ "grad_norm": 0.455078125,
53160
+ "learning_rate": 2.9999999999999997e-05,
53161
+ "loss": 3.0619,
53162
+ "step": 74100
53163
+ },
53164
+ {
53165
+ "epoch": 1.2055e-05,
53166
+ "grad_norm": 0.474609375,
53167
+ "learning_rate": 2.9999999999999997e-05,
53168
+ "loss": 3.0388,
53169
+ "step": 74110
53170
+ },
53171
+ {
53172
+ "epoch": 1.206e-05,
53173
+ "grad_norm": 0.45703125,
53174
+ "learning_rate": 2.9999999999999997e-05,
53175
+ "loss": 3.0505,
53176
+ "step": 74120
53177
+ },
53178
+ {
53179
+ "epoch": 1.2065e-05,
53180
+ "grad_norm": 0.453125,
53181
+ "learning_rate": 2.9999999999999997e-05,
53182
+ "loss": 3.0437,
53183
+ "step": 74130
53184
+ },
53185
+ {
53186
+ "epoch": 1.207e-05,
53187
+ "grad_norm": 0.498046875,
53188
+ "learning_rate": 2.9999999999999997e-05,
53189
+ "loss": 3.0447,
53190
+ "step": 74140
53191
+ },
53192
+ {
53193
+ "epoch": 1.2075e-05,
53194
+ "grad_norm": 0.451171875,
53195
+ "learning_rate": 2.9999999999999997e-05,
53196
+ "loss": 3.0418,
53197
+ "step": 74150
53198
+ },
53199
+ {
53200
+ "epoch": 1.208e-05,
53201
+ "grad_norm": 0.498046875,
53202
+ "learning_rate": 2.9999999999999997e-05,
53203
+ "loss": 3.0496,
53204
+ "step": 74160
53205
+ },
53206
+ {
53207
+ "epoch": 1.2085e-05,
53208
+ "grad_norm": 0.46875,
53209
+ "learning_rate": 2.9999999999999997e-05,
53210
+ "loss": 3.0437,
53211
+ "step": 74170
53212
+ },
53213
+ {
53214
+ "epoch": 1.209e-05,
53215
+ "grad_norm": 0.498046875,
53216
+ "learning_rate": 2.9999999999999997e-05,
53217
+ "loss": 3.04,
53218
+ "step": 74180
53219
+ },
53220
+ {
53221
+ "epoch": 1.2095e-05,
53222
+ "grad_norm": 0.451171875,
53223
+ "learning_rate": 2.9999999999999997e-05,
53224
+ "loss": 3.0498,
53225
+ "step": 74190
53226
+ },
53227
+ {
53228
+ "epoch": 1.21e-05,
53229
+ "grad_norm": 0.44921875,
53230
+ "learning_rate": 2.9999999999999997e-05,
53231
+ "loss": 3.0493,
53232
+ "step": 74200
53233
+ },
53234
+ {
53235
+ "epoch": 1.2105e-05,
53236
+ "grad_norm": 0.45703125,
53237
+ "learning_rate": 2.9999999999999997e-05,
53238
+ "loss": 3.0361,
53239
+ "step": 74210
53240
+ },
53241
+ {
53242
+ "epoch": 1.211e-05,
53243
+ "grad_norm": 0.46484375,
53244
+ "learning_rate": 2.9999999999999997e-05,
53245
+ "loss": 3.0513,
53246
+ "step": 74220
53247
+ },
53248
+ {
53249
+ "epoch": 1.2115e-05,
53250
+ "grad_norm": 0.5078125,
53251
+ "learning_rate": 2.9999999999999997e-05,
53252
+ "loss": 3.0745,
53253
+ "step": 74230
53254
+ },
53255
+ {
53256
+ "epoch": 1.212e-05,
53257
+ "grad_norm": 0.51953125,
53258
+ "learning_rate": 2.9999999999999997e-05,
53259
+ "loss": 3.0383,
53260
+ "step": 74240
53261
+ },
53262
+ {
53263
+ "epoch": 1.2125e-05,
53264
+ "grad_norm": 0.515625,
53265
+ "learning_rate": 2.9999999999999997e-05,
53266
+ "loss": 3.0239,
53267
+ "step": 74250
53268
+ },
53269
+ {
53270
+ "epoch": 1.213e-05,
53271
+ "grad_norm": 0.54296875,
53272
+ "learning_rate": 2.9999999999999997e-05,
53273
+ "loss": 3.0402,
53274
+ "step": 74260
53275
+ },
53276
+ {
53277
+ "epoch": 1.2135e-05,
53278
+ "grad_norm": 0.45703125,
53279
+ "learning_rate": 2.9999999999999997e-05,
53280
+ "loss": 3.04,
53281
+ "step": 74270
53282
+ },
53283
+ {
53284
+ "epoch": 1.214e-05,
53285
+ "grad_norm": 0.46484375,
53286
+ "learning_rate": 2.9999999999999997e-05,
53287
+ "loss": 3.0298,
53288
+ "step": 74280
53289
+ },
53290
+ {
53291
+ "epoch": 1.2145e-05,
53292
+ "grad_norm": 0.494140625,
53293
+ "learning_rate": 2.9999999999999997e-05,
53294
+ "loss": 3.0419,
53295
+ "step": 74290
53296
+ },
53297
+ {
53298
+ "epoch": 1.215e-05,
53299
+ "grad_norm": 0.44140625,
53300
+ "learning_rate": 2.9999999999999997e-05,
53301
+ "loss": 3.0287,
53302
+ "step": 74300
53303
+ },
53304
+ {
53305
+ "epoch": 1.2155e-05,
53306
+ "grad_norm": 0.515625,
53307
+ "learning_rate": 2.9999999999999997e-05,
53308
+ "loss": 3.0545,
53309
+ "step": 74310
53310
+ },
53311
+ {
53312
+ "epoch": 1.216e-05,
53313
+ "grad_norm": 0.455078125,
53314
+ "learning_rate": 2.9999999999999997e-05,
53315
+ "loss": 3.0401,
53316
+ "step": 74320
53317
+ },
53318
+ {
53319
+ "epoch": 1.2165e-05,
53320
+ "grad_norm": 0.447265625,
53321
+ "learning_rate": 2.9999999999999997e-05,
53322
+ "loss": 3.0475,
53323
+ "step": 74330
53324
+ },
53325
+ {
53326
+ "epoch": 1.217e-05,
53327
+ "grad_norm": 0.453125,
53328
+ "learning_rate": 2.9999999999999997e-05,
53329
+ "loss": 3.0167,
53330
+ "step": 74340
53331
+ },
53332
+ {
53333
+ "epoch": 1.2175e-05,
53334
+ "grad_norm": 0.443359375,
53335
+ "learning_rate": 2.9999999999999997e-05,
53336
+ "loss": 3.0337,
53337
+ "step": 74350
53338
+ },
53339
+ {
53340
+ "epoch": 1.218e-05,
53341
+ "grad_norm": 0.56640625,
53342
+ "learning_rate": 2.9999999999999997e-05,
53343
+ "loss": 3.0626,
53344
+ "step": 74360
53345
+ },
53346
+ {
53347
+ "epoch": 1.2185e-05,
53348
+ "grad_norm": 0.447265625,
53349
+ "learning_rate": 2.9999999999999997e-05,
53350
+ "loss": 3.0372,
53351
+ "step": 74370
53352
+ },
53353
+ {
53354
+ "epoch": 1.219e-05,
53355
+ "grad_norm": 0.4296875,
53356
+ "learning_rate": 2.9999999999999997e-05,
53357
+ "loss": 3.0063,
53358
+ "step": 74380
53359
+ },
53360
+ {
53361
+ "epoch": 1.2195e-05,
53362
+ "grad_norm": 0.98046875,
53363
+ "learning_rate": 2.9999999999999997e-05,
53364
+ "loss": 3.024,
53365
+ "step": 74390
53366
+ },
53367
+ {
53368
+ "epoch": 1.22e-05,
53369
+ "grad_norm": 0.49609375,
53370
+ "learning_rate": 2.9999999999999997e-05,
53371
+ "loss": 3.0563,
53372
+ "step": 74400
53373
+ },
53374
+ {
53375
+ "epoch": 1.2205e-05,
53376
+ "grad_norm": 0.478515625,
53377
+ "learning_rate": 2.9999999999999997e-05,
53378
+ "loss": 3.075,
53379
+ "step": 74410
53380
+ },
53381
+ {
53382
+ "epoch": 1.221e-05,
53383
+ "grad_norm": 0.4296875,
53384
+ "learning_rate": 2.9999999999999997e-05,
53385
+ "loss": 2.9934,
53386
+ "step": 74420
53387
+ },
53388
+ {
53389
+ "epoch": 1.2215e-05,
53390
+ "grad_norm": 0.48046875,
53391
+ "learning_rate": 2.9999999999999997e-05,
53392
+ "loss": 3.0843,
53393
+ "step": 74430
53394
+ },
53395
+ {
53396
+ "epoch": 1.222e-05,
53397
+ "grad_norm": 0.46484375,
53398
+ "learning_rate": 2.9999999999999997e-05,
53399
+ "loss": 3.0439,
53400
+ "step": 74440
53401
+ },
53402
+ {
53403
+ "epoch": 1.2225e-05,
53404
+ "grad_norm": 0.466796875,
53405
+ "learning_rate": 2.9999999999999997e-05,
53406
+ "loss": 3.0453,
53407
+ "step": 74450
53408
+ },
53409
+ {
53410
+ "epoch": 1.223e-05,
53411
+ "grad_norm": 0.451171875,
53412
+ "learning_rate": 2.9999999999999997e-05,
53413
+ "loss": 3.0585,
53414
+ "step": 74460
53415
+ },
53416
+ {
53417
+ "epoch": 1.2235e-05,
53418
+ "grad_norm": 0.45703125,
53419
+ "learning_rate": 2.9999999999999997e-05,
53420
+ "loss": 3.0325,
53421
+ "step": 74470
53422
+ },
53423
+ {
53424
+ "epoch": 1.224e-05,
53425
+ "grad_norm": 0.45703125,
53426
+ "learning_rate": 2.9999999999999997e-05,
53427
+ "loss": 3.0441,
53428
+ "step": 74480
53429
+ },
53430
+ {
53431
+ "epoch": 1.2245e-05,
53432
+ "grad_norm": 0.45703125,
53433
+ "learning_rate": 2.9999999999999997e-05,
53434
+ "loss": 3.0291,
53435
+ "step": 74490
53436
+ },
53437
+ {
53438
+ "epoch": 1.225e-05,
53439
+ "grad_norm": 0.478515625,
53440
+ "learning_rate": 2.9999999999999997e-05,
53441
+ "loss": 3.0217,
53442
+ "step": 74500
53443
+ },
53444
+ {
53445
+ "epoch": 1.225e-05,
53446
+ "eval_loss": 3.0819525718688965,
53447
+ "eval_runtime": 0.0614,
53448
+ "eval_samples_per_second": 521.163,
53449
+ "eval_steps_per_second": 16.286,
53450
+ "step": 74500
53451
+ },
53452
+ {
53453
+ "epoch": 1.2255e-05,
53454
+ "grad_norm": 0.443359375,
53455
+ "learning_rate": 2.9999999999999997e-05,
53456
+ "loss": 3.0251,
53457
+ "step": 74510
53458
+ },
53459
+ {
53460
+ "epoch": 1.226e-05,
53461
+ "grad_norm": 0.4765625,
53462
+ "learning_rate": 2.9999999999999997e-05,
53463
+ "loss": 3.0458,
53464
+ "step": 74520
53465
+ },
53466
+ {
53467
+ "epoch": 1.2265e-05,
53468
+ "grad_norm": 0.47265625,
53469
+ "learning_rate": 2.9999999999999997e-05,
53470
+ "loss": 3.0466,
53471
+ "step": 74530
53472
+ },
53473
+ {
53474
+ "epoch": 1.227e-05,
53475
+ "grad_norm": 0.484375,
53476
+ "learning_rate": 2.9999999999999997e-05,
53477
+ "loss": 3.0494,
53478
+ "step": 74540
53479
+ },
53480
+ {
53481
+ "epoch": 1.2275e-05,
53482
+ "grad_norm": 0.453125,
53483
+ "learning_rate": 2.9999999999999997e-05,
53484
+ "loss": 3.0463,
53485
+ "step": 74550
53486
+ },
53487
+ {
53488
+ "epoch": 1.228e-05,
53489
+ "grad_norm": 0.48046875,
53490
+ "learning_rate": 2.9999999999999997e-05,
53491
+ "loss": 3.0409,
53492
+ "step": 74560
53493
+ },
53494
+ {
53495
+ "epoch": 1.2285e-05,
53496
+ "grad_norm": 0.44921875,
53497
+ "learning_rate": 2.9999999999999997e-05,
53498
+ "loss": 3.0571,
53499
+ "step": 74570
53500
+ },
53501
+ {
53502
+ "epoch": 1.229e-05,
53503
+ "grad_norm": 0.439453125,
53504
+ "learning_rate": 2.9999999999999997e-05,
53505
+ "loss": 3.0276,
53506
+ "step": 74580
53507
+ },
53508
+ {
53509
+ "epoch": 1.2295e-05,
53510
+ "grad_norm": 0.515625,
53511
+ "learning_rate": 2.9999999999999997e-05,
53512
+ "loss": 3.0626,
53513
+ "step": 74590
53514
+ },
53515
+ {
53516
+ "epoch": 1.23e-05,
53517
+ "grad_norm": 0.431640625,
53518
+ "learning_rate": 2.9999999999999997e-05,
53519
+ "loss": 3.0557,
53520
+ "step": 74600
53521
+ },
53522
+ {
53523
+ "epoch": 1.2305e-05,
53524
+ "grad_norm": 0.46875,
53525
+ "learning_rate": 2.9999999999999997e-05,
53526
+ "loss": 3.0612,
53527
+ "step": 74610
53528
+ },
53529
+ {
53530
+ "epoch": 1.231e-05,
53531
+ "grad_norm": 0.44921875,
53532
+ "learning_rate": 2.9999999999999997e-05,
53533
+ "loss": 3.0593,
53534
+ "step": 74620
53535
+ },
53536
+ {
53537
+ "epoch": 1.2315e-05,
53538
+ "grad_norm": 0.48046875,
53539
+ "learning_rate": 2.9999999999999997e-05,
53540
+ "loss": 3.0449,
53541
+ "step": 74630
53542
+ },
53543
+ {
53544
+ "epoch": 1.232e-05,
53545
+ "grad_norm": 0.466796875,
53546
+ "learning_rate": 2.9999999999999997e-05,
53547
+ "loss": 3.0297,
53548
+ "step": 74640
53549
+ },
53550
+ {
53551
+ "epoch": 1.2325e-05,
53552
+ "grad_norm": 0.458984375,
53553
+ "learning_rate": 2.9999999999999997e-05,
53554
+ "loss": 3.0521,
53555
+ "step": 74650
53556
+ },
53557
+ {
53558
+ "epoch": 1.233e-05,
53559
+ "grad_norm": 0.49609375,
53560
+ "learning_rate": 2.9999999999999997e-05,
53561
+ "loss": 3.0364,
53562
+ "step": 74660
53563
+ },
53564
+ {
53565
+ "epoch": 1.2335e-05,
53566
+ "grad_norm": 0.44140625,
53567
+ "learning_rate": 2.9999999999999997e-05,
53568
+ "loss": 3.054,
53569
+ "step": 74670
53570
+ },
53571
+ {
53572
+ "epoch": 1.234e-05,
53573
+ "grad_norm": 0.466796875,
53574
+ "learning_rate": 2.9999999999999997e-05,
53575
+ "loss": 3.0478,
53576
+ "step": 74680
53577
+ },
53578
+ {
53579
+ "epoch": 1.2345e-05,
53580
+ "grad_norm": 0.447265625,
53581
+ "learning_rate": 2.9999999999999997e-05,
53582
+ "loss": 3.0608,
53583
+ "step": 74690
53584
+ },
53585
+ {
53586
+ "epoch": 1.235e-05,
53587
+ "grad_norm": 0.447265625,
53588
+ "learning_rate": 2.9999999999999997e-05,
53589
+ "loss": 3.0593,
53590
+ "step": 74700
53591
+ },
53592
+ {
53593
+ "epoch": 1.2355e-05,
53594
+ "grad_norm": 0.47265625,
53595
+ "learning_rate": 2.9999999999999997e-05,
53596
+ "loss": 3.0608,
53597
+ "step": 74710
53598
+ },
53599
+ {
53600
+ "epoch": 1.236e-05,
53601
+ "grad_norm": 0.4609375,
53602
+ "learning_rate": 2.9999999999999997e-05,
53603
+ "loss": 3.0474,
53604
+ "step": 74720
53605
+ },
53606
+ {
53607
+ "epoch": 1.2365e-05,
53608
+ "grad_norm": 0.474609375,
53609
+ "learning_rate": 2.9999999999999997e-05,
53610
+ "loss": 3.0582,
53611
+ "step": 74730
53612
+ },
53613
+ {
53614
+ "epoch": 1.237e-05,
53615
+ "grad_norm": 0.455078125,
53616
+ "learning_rate": 2.9999999999999997e-05,
53617
+ "loss": 3.0403,
53618
+ "step": 74740
53619
+ },
53620
+ {
53621
+ "epoch": 1.2375e-05,
53622
+ "grad_norm": 0.447265625,
53623
+ "learning_rate": 2.9999999999999997e-05,
53624
+ "loss": 3.0219,
53625
+ "step": 74750
53626
+ },
53627
+ {
53628
+ "epoch": 1.238e-05,
53629
+ "grad_norm": 0.4921875,
53630
+ "learning_rate": 2.9999999999999997e-05,
53631
+ "loss": 3.0684,
53632
+ "step": 74760
53633
+ },
53634
+ {
53635
+ "epoch": 1.2385e-05,
53636
+ "grad_norm": 0.458984375,
53637
+ "learning_rate": 2.9999999999999997e-05,
53638
+ "loss": 3.0235,
53639
+ "step": 74770
53640
+ },
53641
+ {
53642
+ "epoch": 1.239e-05,
53643
+ "grad_norm": 0.435546875,
53644
+ "learning_rate": 2.9999999999999997e-05,
53645
+ "loss": 3.0559,
53646
+ "step": 74780
53647
+ },
53648
+ {
53649
+ "epoch": 1.2395e-05,
53650
+ "grad_norm": 0.4609375,
53651
+ "learning_rate": 2.9999999999999997e-05,
53652
+ "loss": 3.0515,
53653
+ "step": 74790
53654
+ },
53655
+ {
53656
+ "epoch": 1.24e-05,
53657
+ "grad_norm": 0.47265625,
53658
+ "learning_rate": 2.9999999999999997e-05,
53659
+ "loss": 3.0697,
53660
+ "step": 74800
53661
+ },
53662
+ {
53663
+ "epoch": 1.2405e-05,
53664
+ "grad_norm": 0.45703125,
53665
+ "learning_rate": 2.9999999999999997e-05,
53666
+ "loss": 3.0379,
53667
+ "step": 74810
53668
+ },
53669
+ {
53670
+ "epoch": 1.241e-05,
53671
+ "grad_norm": 0.447265625,
53672
+ "learning_rate": 2.9999999999999997e-05,
53673
+ "loss": 3.0036,
53674
+ "step": 74820
53675
+ },
53676
+ {
53677
+ "epoch": 1.2415e-05,
53678
+ "grad_norm": 0.48046875,
53679
+ "learning_rate": 2.9999999999999997e-05,
53680
+ "loss": 3.0423,
53681
+ "step": 74830
53682
+ },
53683
+ {
53684
+ "epoch": 1.242e-05,
53685
+ "grad_norm": 0.4765625,
53686
+ "learning_rate": 2.9999999999999997e-05,
53687
+ "loss": 3.0475,
53688
+ "step": 74840
53689
+ },
53690
+ {
53691
+ "epoch": 1.2425e-05,
53692
+ "grad_norm": 0.4609375,
53693
+ "learning_rate": 2.9999999999999997e-05,
53694
+ "loss": 3.0398,
53695
+ "step": 74850
53696
+ },
53697
+ {
53698
+ "epoch": 1.243e-05,
53699
+ "grad_norm": 0.474609375,
53700
+ "learning_rate": 2.9999999999999997e-05,
53701
+ "loss": 3.0573,
53702
+ "step": 74860
53703
+ },
53704
+ {
53705
+ "epoch": 1.2435e-05,
53706
+ "grad_norm": 0.474609375,
53707
+ "learning_rate": 2.9999999999999997e-05,
53708
+ "loss": 3.0451,
53709
+ "step": 74870
53710
+ },
53711
+ {
53712
+ "epoch": 1.244e-05,
53713
+ "grad_norm": 0.45703125,
53714
+ "learning_rate": 2.9999999999999997e-05,
53715
+ "loss": 3.0426,
53716
+ "step": 74880
53717
+ },
53718
+ {
53719
+ "epoch": 1.2445e-05,
53720
+ "grad_norm": 0.470703125,
53721
+ "learning_rate": 2.9999999999999997e-05,
53722
+ "loss": 3.0514,
53723
+ "step": 74890
53724
+ },
53725
+ {
53726
+ "epoch": 1.245e-05,
53727
+ "grad_norm": 0.4609375,
53728
+ "learning_rate": 2.9999999999999997e-05,
53729
+ "loss": 3.0477,
53730
+ "step": 74900
53731
+ },
53732
+ {
53733
+ "epoch": 1.2455e-05,
53734
+ "grad_norm": 0.47265625,
53735
+ "learning_rate": 2.9999999999999997e-05,
53736
+ "loss": 3.04,
53737
+ "step": 74910
53738
+ },
53739
+ {
53740
+ "epoch": 1.246e-05,
53741
+ "grad_norm": 0.478515625,
53742
+ "learning_rate": 2.9999999999999997e-05,
53743
+ "loss": 3.073,
53744
+ "step": 74920
53745
+ },
53746
+ {
53747
+ "epoch": 1.2465e-05,
53748
+ "grad_norm": 0.470703125,
53749
+ "learning_rate": 2.9999999999999997e-05,
53750
+ "loss": 3.0252,
53751
+ "step": 74930
53752
+ },
53753
+ {
53754
+ "epoch": 1.247e-05,
53755
+ "grad_norm": 0.44921875,
53756
+ "learning_rate": 2.9999999999999997e-05,
53757
+ "loss": 3.0285,
53758
+ "step": 74940
53759
+ },
53760
+ {
53761
+ "epoch": 1.2475e-05,
53762
+ "grad_norm": 0.455078125,
53763
+ "learning_rate": 2.9999999999999997e-05,
53764
+ "loss": 3.0629,
53765
+ "step": 74950
53766
+ },
53767
+ {
53768
+ "epoch": 1.248e-05,
53769
+ "grad_norm": 0.484375,
53770
+ "learning_rate": 2.9999999999999997e-05,
53771
+ "loss": 3.0646,
53772
+ "step": 74960
53773
+ },
53774
+ {
53775
+ "epoch": 1.2485e-05,
53776
+ "grad_norm": 0.4609375,
53777
+ "learning_rate": 2.9999999999999997e-05,
53778
+ "loss": 3.0587,
53779
+ "step": 74970
53780
+ },
53781
+ {
53782
+ "epoch": 1.249e-05,
53783
+ "grad_norm": 0.625,
53784
+ "learning_rate": 2.9999999999999997e-05,
53785
+ "loss": 3.0603,
53786
+ "step": 74980
53787
+ },
53788
+ {
53789
+ "epoch": 1.2495e-05,
53790
+ "grad_norm": 0.4765625,
53791
+ "learning_rate": 2.9999999999999997e-05,
53792
+ "loss": 3.052,
53793
+ "step": 74990
53794
+ },
53795
+ {
53796
+ "epoch": 1.25e-05,
53797
+ "grad_norm": 0.494140625,
53798
+ "learning_rate": 2.9999999999999997e-05,
53799
+ "loss": 3.0577,
53800
+ "step": 75000
53801
+ },
53802
+ {
53803
+ "epoch": 1.25e-05,
53804
+ "eval_loss": 3.082608222961426,
53805
+ "eval_runtime": 0.0642,
53806
+ "eval_samples_per_second": 498.567,
53807
+ "eval_steps_per_second": 15.58,
53808
+ "step": 75000
53809
+ },
53810
+ {
53811
+ "epoch": 1.2505e-05,
53812
+ "grad_norm": 0.45703125,
53813
+ "learning_rate": 2.9999999999999997e-05,
53814
+ "loss": 3.0583,
53815
+ "step": 75010
53816
+ },
53817
+ {
53818
+ "epoch": 1.251e-05,
53819
+ "grad_norm": 0.462890625,
53820
+ "learning_rate": 2.9999999999999997e-05,
53821
+ "loss": 3.0302,
53822
+ "step": 75020
53823
+ },
53824
+ {
53825
+ "epoch": 1.2515e-05,
53826
+ "grad_norm": 0.458984375,
53827
+ "learning_rate": 2.9999999999999997e-05,
53828
+ "loss": 3.0585,
53829
+ "step": 75030
53830
+ },
53831
+ {
53832
+ "epoch": 1.252e-05,
53833
+ "grad_norm": 0.494140625,
53834
+ "learning_rate": 2.9999999999999997e-05,
53835
+ "loss": 3.0556,
53836
+ "step": 75040
53837
+ },
53838
+ {
53839
+ "epoch": 1.2525e-05,
53840
+ "grad_norm": 0.470703125,
53841
+ "learning_rate": 2.9999999999999997e-05,
53842
+ "loss": 3.0414,
53843
+ "step": 75050
53844
+ },
53845
+ {
53846
+ "epoch": 1.253e-05,
53847
+ "grad_norm": 0.484375,
53848
+ "learning_rate": 2.9999999999999997e-05,
53849
+ "loss": 3.0358,
53850
+ "step": 75060
53851
+ },
53852
+ {
53853
+ "epoch": 1.2535e-05,
53854
+ "grad_norm": 0.5,
53855
+ "learning_rate": 2.9999999999999997e-05,
53856
+ "loss": 3.0353,
53857
+ "step": 75070
53858
+ },
53859
+ {
53860
+ "epoch": 1.254e-05,
53861
+ "grad_norm": 0.447265625,
53862
+ "learning_rate": 2.9999999999999997e-05,
53863
+ "loss": 3.0306,
53864
+ "step": 75080
53865
+ },
53866
+ {
53867
+ "epoch": 1.2545e-05,
53868
+ "grad_norm": 0.458984375,
53869
+ "learning_rate": 2.9999999999999997e-05,
53870
+ "loss": 3.0702,
53871
+ "step": 75090
53872
+ },
53873
+ {
53874
+ "epoch": 1.255e-05,
53875
+ "grad_norm": 0.5234375,
53876
+ "learning_rate": 2.9999999999999997e-05,
53877
+ "loss": 3.0643,
53878
+ "step": 75100
53879
+ },
53880
+ {
53881
+ "epoch": 1.2555e-05,
53882
+ "grad_norm": 0.474609375,
53883
+ "learning_rate": 2.9999999999999997e-05,
53884
+ "loss": 3.0678,
53885
+ "step": 75110
53886
+ },
53887
+ {
53888
+ "epoch": 1.256e-05,
53889
+ "grad_norm": 0.60546875,
53890
+ "learning_rate": 2.9999999999999997e-05,
53891
+ "loss": 3.0662,
53892
+ "step": 75120
53893
+ },
53894
+ {
53895
+ "epoch": 1.2565e-05,
53896
+ "grad_norm": 0.47265625,
53897
+ "learning_rate": 2.9999999999999997e-05,
53898
+ "loss": 3.0483,
53899
+ "step": 75130
53900
+ },
53901
+ {
53902
+ "epoch": 1.257e-05,
53903
+ "grad_norm": 0.462890625,
53904
+ "learning_rate": 2.9999999999999997e-05,
53905
+ "loss": 3.0476,
53906
+ "step": 75140
53907
+ },
53908
+ {
53909
+ "epoch": 1.2575e-05,
53910
+ "grad_norm": 0.453125,
53911
+ "learning_rate": 2.9999999999999997e-05,
53912
+ "loss": 3.0236,
53913
+ "step": 75150
53914
+ },
53915
+ {
53916
+ "epoch": 1.258e-05,
53917
+ "grad_norm": 0.447265625,
53918
+ "learning_rate": 2.9999999999999997e-05,
53919
+ "loss": 3.0354,
53920
+ "step": 75160
53921
+ },
53922
+ {
53923
+ "epoch": 1.2585e-05,
53924
+ "grad_norm": 0.435546875,
53925
+ "learning_rate": 2.9999999999999997e-05,
53926
+ "loss": 3.0504,
53927
+ "step": 75170
53928
+ },
53929
+ {
53930
+ "epoch": 1.259e-05,
53931
+ "grad_norm": 0.48828125,
53932
+ "learning_rate": 2.9999999999999997e-05,
53933
+ "loss": 3.0415,
53934
+ "step": 75180
53935
+ },
53936
+ {
53937
+ "epoch": 1.2595e-05,
53938
+ "grad_norm": 0.6171875,
53939
+ "learning_rate": 2.9999999999999997e-05,
53940
+ "loss": 3.0309,
53941
+ "step": 75190
53942
+ },
53943
+ {
53944
+ "epoch": 1.26e-05,
53945
+ "grad_norm": 0.4453125,
53946
+ "learning_rate": 2.9999999999999997e-05,
53947
+ "loss": 3.0471,
53948
+ "step": 75200
53949
+ },
53950
+ {
53951
+ "epoch": 1.2605e-05,
53952
+ "grad_norm": 0.47265625,
53953
+ "learning_rate": 2.9999999999999997e-05,
53954
+ "loss": 3.0306,
53955
+ "step": 75210
53956
+ },
53957
+ {
53958
+ "epoch": 1.261e-05,
53959
+ "grad_norm": 0.482421875,
53960
+ "learning_rate": 2.9999999999999997e-05,
53961
+ "loss": 3.0586,
53962
+ "step": 75220
53963
+ },
53964
+ {
53965
+ "epoch": 1.2615e-05,
53966
+ "grad_norm": 0.490234375,
53967
+ "learning_rate": 2.9999999999999997e-05,
53968
+ "loss": 3.0433,
53969
+ "step": 75230
53970
+ },
53971
+ {
53972
+ "epoch": 1.262e-05,
53973
+ "grad_norm": 0.46484375,
53974
+ "learning_rate": 2.9999999999999997e-05,
53975
+ "loss": 3.0321,
53976
+ "step": 75240
53977
+ },
53978
+ {
53979
+ "epoch": 1.2625e-05,
53980
+ "grad_norm": 0.474609375,
53981
+ "learning_rate": 2.9999999999999997e-05,
53982
+ "loss": 3.073,
53983
+ "step": 75250
53984
+ },
53985
+ {
53986
+ "epoch": 1.263e-05,
53987
+ "grad_norm": 0.484375,
53988
+ "learning_rate": 2.9999999999999997e-05,
53989
+ "loss": 3.0405,
53990
+ "step": 75260
53991
+ },
53992
+ {
53993
+ "epoch": 1.2635e-05,
53994
+ "grad_norm": 0.458984375,
53995
+ "learning_rate": 2.9999999999999997e-05,
53996
+ "loss": 3.0529,
53997
+ "step": 75270
53998
+ },
53999
+ {
54000
+ "epoch": 1.264e-05,
54001
+ "grad_norm": 0.44921875,
54002
+ "learning_rate": 2.9999999999999997e-05,
54003
+ "loss": 3.0505,
54004
+ "step": 75280
54005
+ },
54006
+ {
54007
+ "epoch": 1.2645e-05,
54008
+ "grad_norm": 0.50390625,
54009
+ "learning_rate": 2.9999999999999997e-05,
54010
+ "loss": 3.0441,
54011
+ "step": 75290
54012
+ },
54013
+ {
54014
+ "epoch": 1.265e-05,
54015
+ "grad_norm": 0.478515625,
54016
+ "learning_rate": 2.9999999999999997e-05,
54017
+ "loss": 3.0404,
54018
+ "step": 75300
54019
+ },
54020
+ {
54021
+ "epoch": 1.2655e-05,
54022
+ "grad_norm": 0.47265625,
54023
+ "learning_rate": 2.9999999999999997e-05,
54024
+ "loss": 3.0343,
54025
+ "step": 75310
54026
+ },
54027
+ {
54028
+ "epoch": 1.266e-05,
54029
+ "grad_norm": 0.47265625,
54030
+ "learning_rate": 2.9999999999999997e-05,
54031
+ "loss": 3.0255,
54032
+ "step": 75320
54033
+ },
54034
+ {
54035
+ "epoch": 1.2665e-05,
54036
+ "grad_norm": 0.48046875,
54037
+ "learning_rate": 2.9999999999999997e-05,
54038
+ "loss": 3.0401,
54039
+ "step": 75330
54040
+ },
54041
+ {
54042
+ "epoch": 1.267e-05,
54043
+ "grad_norm": 0.462890625,
54044
+ "learning_rate": 2.9999999999999997e-05,
54045
+ "loss": 3.0551,
54046
+ "step": 75340
54047
+ },
54048
+ {
54049
+ "epoch": 1.2675e-05,
54050
+ "grad_norm": 0.498046875,
54051
+ "learning_rate": 2.9999999999999997e-05,
54052
+ "loss": 3.0378,
54053
+ "step": 75350
54054
+ },
54055
+ {
54056
+ "epoch": 1.268e-05,
54057
+ "grad_norm": 0.462890625,
54058
+ "learning_rate": 2.9999999999999997e-05,
54059
+ "loss": 3.0603,
54060
+ "step": 75360
54061
+ },
54062
+ {
54063
+ "epoch": 1.2685e-05,
54064
+ "grad_norm": 0.451171875,
54065
+ "learning_rate": 2.9999999999999997e-05,
54066
+ "loss": 3.0587,
54067
+ "step": 75370
54068
+ },
54069
+ {
54070
+ "epoch": 1.269e-05,
54071
+ "grad_norm": 0.52734375,
54072
+ "learning_rate": 2.9999999999999997e-05,
54073
+ "loss": 3.0257,
54074
+ "step": 75380
54075
+ },
54076
+ {
54077
+ "epoch": 1.2695e-05,
54078
+ "grad_norm": 0.45703125,
54079
+ "learning_rate": 2.9999999999999997e-05,
54080
+ "loss": 3.033,
54081
+ "step": 75390
54082
+ },
54083
+ {
54084
+ "epoch": 1.27e-05,
54085
+ "grad_norm": 0.46484375,
54086
+ "learning_rate": 2.9999999999999997e-05,
54087
+ "loss": 3.0261,
54088
+ "step": 75400
54089
+ },
54090
+ {
54091
+ "epoch": 1.2705e-05,
54092
+ "grad_norm": 0.447265625,
54093
+ "learning_rate": 2.9999999999999997e-05,
54094
+ "loss": 3.053,
54095
+ "step": 75410
54096
+ },
54097
+ {
54098
+ "epoch": 1.271e-05,
54099
+ "grad_norm": 0.458984375,
54100
+ "learning_rate": 2.9999999999999997e-05,
54101
+ "loss": 3.0217,
54102
+ "step": 75420
54103
+ },
54104
+ {
54105
+ "epoch": 1.2715e-05,
54106
+ "grad_norm": 0.46484375,
54107
+ "learning_rate": 2.9999999999999997e-05,
54108
+ "loss": 3.0352,
54109
+ "step": 75430
54110
+ },
54111
+ {
54112
+ "epoch": 1.272e-05,
54113
+ "grad_norm": 0.5,
54114
+ "learning_rate": 2.9999999999999997e-05,
54115
+ "loss": 3.0482,
54116
+ "step": 75440
54117
+ },
54118
+ {
54119
+ "epoch": 1.2725e-05,
54120
+ "grad_norm": 0.451171875,
54121
+ "learning_rate": 2.9999999999999997e-05,
54122
+ "loss": 3.0461,
54123
+ "step": 75450
54124
+ },
54125
+ {
54126
+ "epoch": 1.273e-05,
54127
+ "grad_norm": 0.451171875,
54128
+ "learning_rate": 2.9999999999999997e-05,
54129
+ "loss": 3.0401,
54130
+ "step": 75460
54131
+ },
54132
+ {
54133
+ "epoch": 1.2735e-05,
54134
+ "grad_norm": 0.4609375,
54135
+ "learning_rate": 2.9999999999999997e-05,
54136
+ "loss": 3.0332,
54137
+ "step": 75470
54138
+ },
54139
+ {
54140
+ "epoch": 1.274e-05,
54141
+ "grad_norm": 0.451171875,
54142
+ "learning_rate": 2.9999999999999997e-05,
54143
+ "loss": 3.0431,
54144
+ "step": 75480
54145
+ },
54146
+ {
54147
+ "epoch": 1.2745e-05,
54148
+ "grad_norm": 0.46875,
54149
+ "learning_rate": 2.9999999999999997e-05,
54150
+ "loss": 3.0656,
54151
+ "step": 75490
54152
+ },
54153
+ {
54154
+ "epoch": 1.275e-05,
54155
+ "grad_norm": 0.4765625,
54156
+ "learning_rate": 2.9999999999999997e-05,
54157
+ "loss": 3.0316,
54158
+ "step": 75500
54159
+ },
54160
+ {
54161
+ "epoch": 1.275e-05,
54162
+ "eval_loss": 3.0825040340423584,
54163
+ "eval_runtime": 0.0636,
54164
+ "eval_samples_per_second": 503.282,
54165
+ "eval_steps_per_second": 15.728,
54166
+ "step": 75500
54167
+ },
54168
+ {
54169
+ "epoch": 1.2755e-05,
54170
+ "grad_norm": 0.443359375,
54171
+ "learning_rate": 2.9999999999999997e-05,
54172
+ "loss": 3.0493,
54173
+ "step": 75510
54174
+ },
54175
+ {
54176
+ "epoch": 1.276e-05,
54177
+ "grad_norm": 0.51171875,
54178
+ "learning_rate": 2.9999999999999997e-05,
54179
+ "loss": 3.0349,
54180
+ "step": 75520
54181
+ },
54182
+ {
54183
+ "epoch": 1.2765e-05,
54184
+ "grad_norm": 0.478515625,
54185
+ "learning_rate": 2.9999999999999997e-05,
54186
+ "loss": 3.0385,
54187
+ "step": 75530
54188
+ },
54189
+ {
54190
+ "epoch": 1.277e-05,
54191
+ "grad_norm": 0.443359375,
54192
+ "learning_rate": 2.9999999999999997e-05,
54193
+ "loss": 3.0388,
54194
+ "step": 75540
54195
+ },
54196
+ {
54197
+ "epoch": 1.2775e-05,
54198
+ "grad_norm": 0.494140625,
54199
+ "learning_rate": 2.9999999999999997e-05,
54200
+ "loss": 3.0524,
54201
+ "step": 75550
54202
+ },
54203
+ {
54204
+ "epoch": 1.278e-05,
54205
+ "grad_norm": 0.462890625,
54206
+ "learning_rate": 2.9999999999999997e-05,
54207
+ "loss": 3.0119,
54208
+ "step": 75560
54209
+ },
54210
+ {
54211
+ "epoch": 1.2785e-05,
54212
+ "grad_norm": 0.55859375,
54213
+ "learning_rate": 2.9999999999999997e-05,
54214
+ "loss": 3.0448,
54215
+ "step": 75570
54216
+ },
54217
+ {
54218
+ "epoch": 1.279e-05,
54219
+ "grad_norm": 0.50390625,
54220
+ "learning_rate": 2.9999999999999997e-05,
54221
+ "loss": 3.0425,
54222
+ "step": 75580
54223
+ },
54224
+ {
54225
+ "epoch": 1.2795e-05,
54226
+ "grad_norm": 0.48046875,
54227
+ "learning_rate": 2.9999999999999997e-05,
54228
+ "loss": 3.0612,
54229
+ "step": 75590
54230
+ },
54231
+ {
54232
+ "epoch": 1.28e-05,
54233
+ "grad_norm": 0.474609375,
54234
+ "learning_rate": 2.9999999999999997e-05,
54235
+ "loss": 3.0554,
54236
+ "step": 75600
54237
+ },
54238
+ {
54239
+ "epoch": 1.2805e-05,
54240
+ "grad_norm": 0.455078125,
54241
+ "learning_rate": 2.9999999999999997e-05,
54242
+ "loss": 3.0226,
54243
+ "step": 75610
54244
+ },
54245
+ {
54246
+ "epoch": 1.281e-05,
54247
+ "grad_norm": 0.4453125,
54248
+ "learning_rate": 2.9999999999999997e-05,
54249
+ "loss": 3.0568,
54250
+ "step": 75620
54251
+ },
54252
+ {
54253
+ "epoch": 1.2815e-05,
54254
+ "grad_norm": 0.447265625,
54255
+ "learning_rate": 2.9999999999999997e-05,
54256
+ "loss": 3.0626,
54257
+ "step": 75630
54258
+ },
54259
+ {
54260
+ "epoch": 1.282e-05,
54261
+ "grad_norm": 0.447265625,
54262
+ "learning_rate": 2.9999999999999997e-05,
54263
+ "loss": 3.0451,
54264
+ "step": 75640
54265
+ },
54266
+ {
54267
+ "epoch": 1.2825e-05,
54268
+ "grad_norm": 0.46875,
54269
+ "learning_rate": 2.9999999999999997e-05,
54270
+ "loss": 3.0423,
54271
+ "step": 75650
54272
+ },
54273
+ {
54274
+ "epoch": 1.283e-05,
54275
+ "grad_norm": 0.46484375,
54276
+ "learning_rate": 2.9999999999999997e-05,
54277
+ "loss": 3.0454,
54278
+ "step": 75660
54279
+ },
54280
+ {
54281
+ "epoch": 1.2835e-05,
54282
+ "grad_norm": 0.4453125,
54283
+ "learning_rate": 2.9999999999999997e-05,
54284
+ "loss": 3.0549,
54285
+ "step": 75670
54286
+ },
54287
+ {
54288
+ "epoch": 1.284e-05,
54289
+ "grad_norm": 0.50390625,
54290
+ "learning_rate": 2.9999999999999997e-05,
54291
+ "loss": 3.0614,
54292
+ "step": 75680
54293
+ },
54294
+ {
54295
+ "epoch": 1.2845e-05,
54296
+ "grad_norm": 0.484375,
54297
+ "learning_rate": 2.9999999999999997e-05,
54298
+ "loss": 3.0609,
54299
+ "step": 75690
54300
+ },
54301
+ {
54302
+ "epoch": 1.285e-05,
54303
+ "grad_norm": 0.5,
54304
+ "learning_rate": 2.9999999999999997e-05,
54305
+ "loss": 3.0362,
54306
+ "step": 75700
54307
+ },
54308
+ {
54309
+ "epoch": 1.2855e-05,
54310
+ "grad_norm": 0.451171875,
54311
+ "learning_rate": 2.9999999999999997e-05,
54312
+ "loss": 3.0342,
54313
+ "step": 75710
54314
+ },
54315
+ {
54316
+ "epoch": 1.286e-05,
54317
+ "grad_norm": 0.4375,
54318
+ "learning_rate": 2.9999999999999997e-05,
54319
+ "loss": 3.0526,
54320
+ "step": 75720
54321
+ },
54322
+ {
54323
+ "epoch": 1.2865e-05,
54324
+ "grad_norm": 0.435546875,
54325
+ "learning_rate": 2.9999999999999997e-05,
54326
+ "loss": 3.0123,
54327
+ "step": 75730
54328
+ },
54329
+ {
54330
+ "epoch": 1.287e-05,
54331
+ "grad_norm": 0.4453125,
54332
+ "learning_rate": 2.9999999999999997e-05,
54333
+ "loss": 3.0193,
54334
+ "step": 75740
54335
+ },
54336
+ {
54337
+ "epoch": 1.2875e-05,
54338
+ "grad_norm": 0.5078125,
54339
+ "learning_rate": 2.9999999999999997e-05,
54340
+ "loss": 3.0564,
54341
+ "step": 75750
54342
+ },
54343
+ {
54344
+ "epoch": 1.288e-05,
54345
+ "grad_norm": 0.5234375,
54346
+ "learning_rate": 2.9999999999999997e-05,
54347
+ "loss": 3.0246,
54348
+ "step": 75760
54349
+ },
54350
+ {
54351
+ "epoch": 1.2885e-05,
54352
+ "grad_norm": 0.458984375,
54353
+ "learning_rate": 2.9999999999999997e-05,
54354
+ "loss": 3.021,
54355
+ "step": 75770
54356
+ },
54357
+ {
54358
+ "epoch": 1.289e-05,
54359
+ "grad_norm": 0.45703125,
54360
+ "learning_rate": 2.9999999999999997e-05,
54361
+ "loss": 3.04,
54362
+ "step": 75780
54363
+ },
54364
+ {
54365
+ "epoch": 1.2895e-05,
54366
+ "grad_norm": 0.447265625,
54367
+ "learning_rate": 2.9999999999999997e-05,
54368
+ "loss": 3.0652,
54369
+ "step": 75790
54370
+ },
54371
+ {
54372
+ "epoch": 1.29e-05,
54373
+ "grad_norm": 0.455078125,
54374
+ "learning_rate": 2.9999999999999997e-05,
54375
+ "loss": 3.0214,
54376
+ "step": 75800
54377
+ },
54378
+ {
54379
+ "epoch": 1.2905e-05,
54380
+ "grad_norm": 0.51953125,
54381
+ "learning_rate": 2.9999999999999997e-05,
54382
+ "loss": 3.0484,
54383
+ "step": 75810
54384
+ },
54385
+ {
54386
+ "epoch": 1.291e-05,
54387
+ "grad_norm": 0.50390625,
54388
+ "learning_rate": 2.9999999999999997e-05,
54389
+ "loss": 3.0645,
54390
+ "step": 75820
54391
+ },
54392
+ {
54393
+ "epoch": 1.2915e-05,
54394
+ "grad_norm": 0.47265625,
54395
+ "learning_rate": 2.9999999999999997e-05,
54396
+ "loss": 3.0726,
54397
+ "step": 75830
54398
+ },
54399
+ {
54400
+ "epoch": 1.292e-05,
54401
+ "grad_norm": 0.498046875,
54402
+ "learning_rate": 2.9999999999999997e-05,
54403
+ "loss": 3.0457,
54404
+ "step": 75840
54405
+ },
54406
+ {
54407
+ "epoch": 1.2925e-05,
54408
+ "grad_norm": 0.490234375,
54409
+ "learning_rate": 2.9999999999999997e-05,
54410
+ "loss": 3.03,
54411
+ "step": 75850
54412
+ },
54413
+ {
54414
+ "epoch": 1.293e-05,
54415
+ "grad_norm": 0.4609375,
54416
+ "learning_rate": 2.9999999999999997e-05,
54417
+ "loss": 3.0607,
54418
+ "step": 75860
54419
+ },
54420
+ {
54421
+ "epoch": 1.2935e-05,
54422
+ "grad_norm": 0.4765625,
54423
+ "learning_rate": 2.9999999999999997e-05,
54424
+ "loss": 3.0342,
54425
+ "step": 75870
54426
+ },
54427
+ {
54428
+ "epoch": 1.294e-05,
54429
+ "grad_norm": 0.4453125,
54430
+ "learning_rate": 2.9999999999999997e-05,
54431
+ "loss": 3.0324,
54432
+ "step": 75880
54433
+ },
54434
+ {
54435
+ "epoch": 1.2945e-05,
54436
+ "grad_norm": 0.490234375,
54437
+ "learning_rate": 2.9999999999999997e-05,
54438
+ "loss": 3.0501,
54439
+ "step": 75890
54440
+ },
54441
+ {
54442
+ "epoch": 1.295e-05,
54443
+ "grad_norm": 0.439453125,
54444
+ "learning_rate": 2.9999999999999997e-05,
54445
+ "loss": 3.0216,
54446
+ "step": 75900
54447
+ },
54448
+ {
54449
+ "epoch": 1.2955e-05,
54450
+ "grad_norm": 0.455078125,
54451
+ "learning_rate": 2.9999999999999997e-05,
54452
+ "loss": 3.0644,
54453
+ "step": 75910
54454
+ },
54455
+ {
54456
+ "epoch": 1.296e-05,
54457
+ "grad_norm": 0.455078125,
54458
+ "learning_rate": 2.9999999999999997e-05,
54459
+ "loss": 3.0316,
54460
+ "step": 75920
54461
+ },
54462
+ {
54463
+ "epoch": 1.2965e-05,
54464
+ "grad_norm": 0.4609375,
54465
+ "learning_rate": 2.9999999999999997e-05,
54466
+ "loss": 3.0139,
54467
+ "step": 75930
54468
+ },
54469
+ {
54470
+ "epoch": 1.297e-05,
54471
+ "grad_norm": 0.443359375,
54472
+ "learning_rate": 2.9999999999999997e-05,
54473
+ "loss": 3.0269,
54474
+ "step": 75940
54475
+ },
54476
+ {
54477
+ "epoch": 1.2975e-05,
54478
+ "grad_norm": 0.453125,
54479
+ "learning_rate": 2.9999999999999997e-05,
54480
+ "loss": 3.0691,
54481
+ "step": 75950
54482
+ },
54483
+ {
54484
+ "epoch": 1.298e-05,
54485
+ "grad_norm": 0.478515625,
54486
+ "learning_rate": 2.9999999999999997e-05,
54487
+ "loss": 3.0304,
54488
+ "step": 75960
54489
+ },
54490
+ {
54491
+ "epoch": 1.2985e-05,
54492
+ "grad_norm": 0.498046875,
54493
+ "learning_rate": 2.9999999999999997e-05,
54494
+ "loss": 3.0494,
54495
+ "step": 75970
54496
+ },
54497
+ {
54498
+ "epoch": 1.299e-05,
54499
+ "grad_norm": 0.4453125,
54500
+ "learning_rate": 2.9999999999999997e-05,
54501
+ "loss": 3.0435,
54502
+ "step": 75980
54503
+ },
54504
+ {
54505
+ "epoch": 1.2995e-05,
54506
+ "grad_norm": 0.53515625,
54507
+ "learning_rate": 2.9999999999999997e-05,
54508
+ "loss": 3.068,
54509
+ "step": 75990
54510
+ },
54511
+ {
54512
+ "epoch": 1.3e-05,
54513
+ "grad_norm": 0.5,
54514
+ "learning_rate": 2.9999999999999997e-05,
54515
+ "loss": 3.0276,
54516
+ "step": 76000
54517
+ },
54518
+ {
54519
+ "epoch": 1.3e-05,
54520
+ "eval_loss": 3.08209228515625,
54521
+ "eval_runtime": 0.0672,
54522
+ "eval_samples_per_second": 476.536,
54523
+ "eval_steps_per_second": 14.892,
54524
+ "step": 76000
54525
  }
54526
  ],
54527
  "logging_steps": 10,
 
54541
  "attributes": {}
54542
  }
54543
  },
54544
+ "total_flos": 1.77590023225344e+18,
54545
  "train_batch_size": 240,
54546
  "trial_name": null,
54547
  "trial_params": null