Hugging Face's logo

Azrail
/
smallm_70

Text Generation
Transformers
Safetensors
English
smallm
transformer
language-model
experimental
conversational
custom_code
Model card Files
xet
 Community
Azrail commited on
Commit
097b117
·
verified ·
1 Parent(s): 8003691

Training in progress, step 30000, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +182 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fed58b9377855fe80a778b09bc2f72a0dc4e91c0242adc79b95ac4868b0921df
3
  size 301235464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f51ff64449431cc6b860fc6a206e20886e5f1d192ef9f5c4665dcd4473c0b48
3
  size 301235464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd09749daae0bf1f567d4c6a6fbe152fdcd1c8cc6de8109ecaa45912c30be9b2
3
  size 602335994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b7cea09d7e221121f61088c25620a75a4e14dc5da50c48e0e34b3039ac72bd
3
  size 602335994
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9846b22739edf9c19756d28d9b1bb6ad70ad314d431493efdbec089d6aa54593
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6b0657fb61feb4f28f22e2ad479d4cf998ca9bc56886ce112bfea918a730a8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6038c3966e5acd5e329cd1d75f036dea625d34bb913a8f0d05452e8d1784e0ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0c8a94ae7b3402d9f6c538decfc8292fd64108bb86fd10da3f27734428bf0b
3
  size 1064
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": 0.13833072969459914,
6
  "eval_steps": 500,
7
- "global_step": 29000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -5170,11 +5170,189 @@
5170
  "eval_steps_per_second": 24.551,
5171
  "num_input_tokens_seen": 7602176000,
5172
  "step": 29000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5173
  }
5174
  ],
5175
  "logging_steps": 50,
5176
  "max_steps": 70000,
5177
- "num_input_tokens_seen": 7602176000,
5178
  "num_train_epochs": 1,
5179
  "save_steps": 1000,
5180
  "stateful_callbacks": {
@@ -5189,7 +5367,7 @@
5189
  "attributes": {}
5190
  }
5191
  },
5192
- "total_flos": 2.03365627723776e+18,
5193
  "train_batch_size": 64,
5194
  "trial_name": null,
5195
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.14310075485648185,
6
  "eval_steps": 500,
7
+ "global_step": 30000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
5170
  "eval_steps_per_second": 24.551,
5171
  "num_input_tokens_seen": 7602176000,
5172
  "step": 29000
5173
+ },
5174
+ {
5175
+ "epoch": 0.13856923095269327,
5176
+ "grad_norm": 0.18520566821098328,
5177
+ "learning_rate": 0.001,
5178
+ "loss": 2.6644,
5179
+ "num_input_tokens_seen": 7615283200,
5180
+ "step": 29050
5181
+ },
5182
+ {
5183
+ "epoch": 0.1388077322107874,
5184
+ "grad_norm": 0.22739861905574799,
5185
+ "learning_rate": 0.001,
5186
+ "loss": 2.6597,
5187
+ "num_input_tokens_seen": 7628390400,
5188
+ "step": 29100
5189
+ },
5190
+ {
5191
+ "epoch": 0.13904623346888154,
5192
+ "grad_norm": 0.18451730906963348,
5193
+ "learning_rate": 0.001,
5194
+ "loss": 2.6432,
5195
+ "num_input_tokens_seen": 7641497600,
5196
+ "step": 29150
5197
+ },
5198
+ {
5199
+ "epoch": 0.1392847347269757,
5200
+ "grad_norm": 0.1865098923444748,
5201
+ "learning_rate": 0.001,
5202
+ "loss": 2.6651,
5203
+ "num_input_tokens_seen": 7654604800,
5204
+ "step": 29200
5205
+ },
5206
+ {
5207
+ "epoch": 0.13952323598506983,
5208
+ "grad_norm": 0.18676789104938507,
5209
+ "learning_rate": 0.001,
5210
+ "loss": 2.6597,
5211
+ "num_input_tokens_seen": 7667712000,
5212
+ "step": 29250
5213
+ },
5214
+ {
5215
+ "epoch": 0.13976173724316396,
5216
+ "grad_norm": 0.17463742196559906,
5217
+ "learning_rate": 0.001,
5218
+ "loss": 2.6571,
5219
+ "num_input_tokens_seen": 7680819200,
5220
+ "step": 29300
5221
+ },
5222
+ {
5223
+ "epoch": 0.1400002385012581,
5224
+ "grad_norm": 0.21621429920196533,
5225
+ "learning_rate": 0.001,
5226
+ "loss": 2.6342,
5227
+ "num_input_tokens_seen": 7693926400,
5228
+ "step": 29350
5229
+ },
5230
+ {
5231
+ "epoch": 0.14023873975935222,
5232
+ "grad_norm": 0.17493990063667297,
5233
+ "learning_rate": 0.001,
5234
+ "loss": 2.6536,
5235
+ "num_input_tokens_seen": 7707033600,
5236
+ "step": 29400
5237
+ },
5238
+ {
5239
+ "epoch": 0.14047724101744638,
5240
+ "grad_norm": 0.17649762332439423,
5241
+ "learning_rate": 0.001,
5242
+ "loss": 2.6526,
5243
+ "num_input_tokens_seen": 7720140800,
5244
+ "step": 29450
5245
+ },
5246
+ {
5247
+ "epoch": 0.1407157422755405,
5248
+ "grad_norm": 0.18224874138832092,
5249
+ "learning_rate": 0.001,
5250
+ "loss": 2.6635,
5251
+ "num_input_tokens_seen": 7733248000,
5252
+ "step": 29500
5253
+ },
5254
+ {
5255
+ "epoch": 0.1407157422755405,
5256
+ "eval_loss": 2.5433554649353027,
5257
+ "eval_runtime": 51.2973,
5258
+ "eval_samples_per_second": 97.471,
5259
+ "eval_steps_per_second": 24.368,
5260
+ "num_input_tokens_seen": 7733248000,
5261
+ "step": 29500
5262
+ },
5263
+ {
5264
+ "epoch": 0.14095424353363464,
5265
+ "grad_norm": 0.21109874546527863,
5266
+ "learning_rate": 0.001,
5267
+ "loss": 2.6788,
5268
+ "num_input_tokens_seen": 7746355200,
5269
+ "step": 29550
5270
+ },
5271
+ {
5272
+ "epoch": 0.14119274479172877,
5273
+ "grad_norm": 0.17663723230361938,
5274
+ "learning_rate": 0.001,
5275
+ "loss": 2.6578,
5276
+ "num_input_tokens_seen": 7759462400,
5277
+ "step": 29600
5278
+ },
5279
+ {
5280
+ "epoch": 0.1414312460498229,
5281
+ "grad_norm": 0.18385198712348938,
5282
+ "learning_rate": 0.001,
5283
+ "loss": 2.676,
5284
+ "num_input_tokens_seen": 7772569600,
5285
+ "step": 29650
5286
+ },
5287
+ {
5288
+ "epoch": 0.14166974730791704,
5289
+ "grad_norm": 0.1829567402601242,
5290
+ "learning_rate": 0.001,
5291
+ "loss": 2.6586,
5292
+ "num_input_tokens_seen": 7785676800,
5293
+ "step": 29700
5294
+ },
5295
+ {
5296
+ "epoch": 0.1419082485660112,
5297
+ "grad_norm": 0.1907297968864441,
5298
+ "learning_rate": 0.001,
5299
+ "loss": 2.6508,
5300
+ "num_input_tokens_seen": 7798784000,
5301
+ "step": 29750
5302
+ },
5303
+ {
5304
+ "epoch": 0.14214674982410533,
5305
+ "grad_norm": 0.2106500118970871,
5306
+ "learning_rate": 0.001,
5307
+ "loss": 2.6578,
5308
+ "num_input_tokens_seen": 7811891200,
5309
+ "step": 29800
5310
+ },
5311
+ {
5312
+ "epoch": 0.14238525108219946,
5313
+ "grad_norm": 0.18974357843399048,
5314
+ "learning_rate": 0.001,
5315
+ "loss": 2.6506,
5316
+ "num_input_tokens_seen": 7824998400,
5317
+ "step": 29850
5318
+ },
5319
+ {
5320
+ "epoch": 0.1426237523402936,
5321
+ "grad_norm": 0.18876343965530396,
5322
+ "learning_rate": 0.001,
5323
+ "loss": 2.6663,
5324
+ "num_input_tokens_seen": 7838105600,
5325
+ "step": 29900
5326
+ },
5327
+ {
5328
+ "epoch": 0.14286225359838772,
5329
+ "grad_norm": 0.17305608093738556,
5330
+ "learning_rate": 0.001,
5331
+ "loss": 2.657,
5332
+ "num_input_tokens_seen": 7851212800,
5333
+ "step": 29950
5334
+ },
5335
+ {
5336
+ "epoch": 0.14310075485648185,
5337
+ "grad_norm": 0.18900860846042633,
5338
+ "learning_rate": 0.001,
5339
+ "loss": 2.6502,
5340
+ "num_input_tokens_seen": 7864320000,
5341
+ "step": 30000
5342
+ },
5343
+ {
5344
+ "epoch": 0.14310075485648185,
5345
+ "eval_loss": 2.540076971054077,
5346
+ "eval_runtime": 50.1464,
5347
+ "eval_samples_per_second": 99.708,
5348
+ "eval_steps_per_second": 24.927,
5349
+ "num_input_tokens_seen": 7864320000,
5350
+ "step": 30000
5351
  }
5352
  ],
5353
  "logging_steps": 50,
5354
  "max_steps": 70000,
5355
+ "num_input_tokens_seen": 7864320000,
5356
  "num_train_epochs": 1,
5357
  "save_steps": 1000,
5358
  "stateful_callbacks": {
 
5367
  "attributes": {}
5368
  }
5369
  },
5370
+ "total_flos": 2.1037823557632e+18,
5371
  "train_batch_size": 64,
5372
  "trial_name": null,
5373
  "trial_params": null