auxyus commited on
Commit
18a2238
·
verified ·
1 Parent(s): 8ed9431

Training in progress, step 72, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2138eddfa5145d3a15a5015d50c7cca0fab97d181e2c27f3d14767760c1f329d
3
  size 217931936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7639baad966f325fdb6e56ea97b0a5745e13ad6d8363e7e05515b5602adba26
3
  size 217931936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38f5466891e2168b51d64ee8be7100f0de55c502370289e697b521c924865a5b
3
  size 111412180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ceb09bab6d24aa586bf7e466dce666f3a2fb9d1ddda598069c5c930e2342759
3
  size 111412180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02385c92fa40b224b03902b652f2243adedbec7acf45d5bb02bb0f1f688514dd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a5264ff7e3618ea0ec2e45530eacee8e87dd5d31d530019ae23255a32db19f1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.8484848484848485,
5
  "eval_steps": 9,
6
- "global_step": 63,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -218,6 +218,35 @@
218
  "eval_samples_per_second": 11.086,
219
  "eval_steps_per_second": 1.419,
220
  "step": 63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
221
  }
222
  ],
223
  "logging_steps": 3,
@@ -237,7 +266,7 @@
237
  "attributes": {}
238
  }
239
  },
240
- "total_flos": 1.06791290108117e+17,
241
  "train_batch_size": 8,
242
  "trial_name": null,
243
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9696969696969697,
5
  "eval_steps": 9,
6
+ "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
218
  "eval_samples_per_second": 11.086,
219
  "eval_steps_per_second": 1.419,
220
  "step": 63
221
+ },
222
+ {
223
+ "epoch": 0.8888888888888888,
224
+ "grad_norm": 0.00031755914096720517,
225
+ "learning_rate": 3.12696703292044e-05,
226
+ "loss": 0.0,
227
+ "step": 66
228
+ },
229
+ {
230
+ "epoch": 0.9292929292929293,
231
+ "grad_norm": 0.00030167968361638486,
232
+ "learning_rate": 2.6526421860705473e-05,
233
+ "loss": 0.0,
234
+ "step": 69
235
+ },
236
+ {
237
+ "epoch": 0.9696969696969697,
238
+ "grad_norm": 0.0002713320136535913,
239
+ "learning_rate": 2.2040354826462668e-05,
240
+ "loss": 0.0,
241
+ "step": 72
242
+ },
243
+ {
244
+ "epoch": 0.9696969696969697,
245
+ "eval_loss": 7.80674508860102e-06,
246
+ "eval_runtime": 11.3027,
247
+ "eval_samples_per_second": 11.059,
248
+ "eval_steps_per_second": 1.416,
249
+ "step": 72
250
  }
251
  ],
252
  "logging_steps": 3,
 
266
  "attributes": {}
267
  }
268
  },
269
+ "total_flos": 1.2204718869499085e+17,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null