dixedus commited on
Commit
edbfae2
·
verified ·
1 Parent(s): b72bba6

Training in progress, step 99, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5524909abef78e795502572e2024aa152f285bcd7a80ffc89c7e3bc02b078043
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2401932aa8a61f3c33205ddf479d0c5a6e95614afa76c40d77bc7ec1a35602b0
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e69e5637343508e9d45ad5a7d23abd78f38308580ecdf5b584a9e2d9f0c75766
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d6279d58a89f9c471fb98486bf64ee0ac2fdbe56dfc18673447f1e5af0c954
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfaf8be53ae247332dd24016fe33ba54f82eb66ab59a691e62d323776545d891
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1599650ced2ecf60940df790d4fe337551b47bec67ef42caf69e43782b47758
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 0.42908224076281287,
5
  "eval_steps": 9,
6
- "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 14.912,
306
  "eval_steps_per_second": 1.896,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.2492420589132186e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.4719904648390942,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 14.912,
306
  "eval_steps_per_second": 1.896,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.4433849821215733,
311
+ "grad_norm": 0.8038536906242371,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 2.2257,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.4576877234803337,
318
+ "grad_norm": 0.6432086229324341,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 2.1321,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.4719904648390942,
325
+ "grad_norm": 0.6721349358558655,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 2.1555,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.4719904648390942,
332
+ "eval_loss": 2.206080198287964,
333
+ "eval_runtime": 23.7434,
334
+ "eval_samples_per_second": 14.909,
335
+ "eval_steps_per_second": 1.895,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.3711997269337702e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null