leixa commited on
Commit
d7599d0
·
verified ·
1 Parent(s): e0d8eb2

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 sha256:9c936a8681c1d4f010fac3f3588d52c3bb9049a1f07020a30608ec0225d2d095
3
  size 10636096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54511147b00eed7fa2883908536799af5e2b7660b3e7af88b653be591acc5405
3
  size 10636096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a1de862a132f2f27e2871dd94756b01ca2071f886c76718e74c69cd6d54e3c2
3
  size 5561082
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac769c8c9689a85e32057fcf0bd4fb3a28a2c6cbf990122eea1591b138c8a22
3
  size 5561082
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1745f2c4475acc7af3be8dcfe8049bd3af84688905ec4a16b903840aac4c9890
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbe0d2d485c0770c1a2499b995372347e71eac4fe26fa36bcb43a33e867c38e
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": 0.44063647490820074,
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": 34.721,
306
  "eval_steps_per_second": 4.34,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 3103036696166400.0,
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": 0.4847001223990208,
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": 34.721,
306
  "eval_steps_per_second": 4.34,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.45532435740514077,
311
+ "grad_norm": 1.218754768371582,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 10.7893,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.4700122399020808,
318
+ "grad_norm": 1.0495154857635498,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 10.9183,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.4847001223990208,
325
+ "grad_norm": 0.9865614771842957,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 11.1974,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.4847001223990208,
332
+ "eval_loss": 2.7715492248535156,
333
+ "eval_runtime": 9.9162,
334
+ "eval_samples_per_second": 34.691,
335
+ "eval_steps_per_second": 4.336,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 3413340365783040.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null