Nexspear commited on
Commit
389d1e8
·
verified ·
1 Parent(s): 42b22d3

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 sha256:3fc48538d8f76604a49c323644bef05b6f87121e14aecf505dfd0fec31140955
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec67bd30fe36de64c1ae07e3cf6201f3314b1ba97078908f12652f2fbc5c46e8
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c6b18ca8922f378b7b9a6f9b25767b0a9d34ac4791169748e6adea94218fb07
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe601159f2c46ceb5fee1032460bb441a984df80fb4a720c4b21d4c5febf6f6
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:883478422214c28f96eaa5d8ca0a7298b12cf7bbdd2ff81f66f224e8fd07520a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccbeeee722d0a1f47e36cf63eba1cd767f47fa281b199cb896ca45c5f2ddf7a1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
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": 0.9836065573770492,
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": 15.38,
306
  "eval_steps_per_second": 1.997,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.1958285094826803e+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": 1.0819672131147542,
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": 15.38,
306
  "eval_steps_per_second": 1.997,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 1.0163934426229508,
311
+ "grad_norm": 1.1719740629196167,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 7.2704,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 1.0491803278688525,
318
+ "grad_norm": 1.204927921295166,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 7.3601,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 1.0819672131147542,
325
+ "grad_norm": 1.423250675201416,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 7.4071,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 1.0819672131147542,
332
+ "eval_loss": 1.8196653127670288,
333
+ "eval_runtime": 10.0108,
334
+ "eval_samples_per_second": 15.383,
335
+ "eval_steps_per_second": 1.998,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.3150846313299968e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null