leixa commited on
Commit
3923a7f
·
verified ·
1 Parent(s): 8f28aaa

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 sha256:15a1b4c886f4276cc230facd5fc439b32bb30afe2344e3f061a4a6ae7f2cd3fc
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec25839b2d9cfe5250eddaabd13fbdbf86de708e8156e4d94f0f2cb62a66052e
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01b46df13c075aef9c26ff6d87c3cb73ee59f2e63ddf4577653e799db3d24429
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7678d792f746175b19ce9f6ec8c8d882fead6d574fc03531b38c59c069127280
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f65d33f8dbb303a0d5f68445f3c91506d6bca32bb2475114b5510685edbdcace
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a002c35283ee15865b652908226f5a02d99c68599148fb6605a660ea5c853706
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": 0.11980033277870217,
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": 13.415,
306
  "eval_steps_per_second": 1.686,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.2111908438016e+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": 0.13178036605657237,
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": 13.415,
306
  "eval_steps_per_second": 1.686,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.1237936772046589,
311
+ "grad_norm": 0.7145574688911438,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 0.0618,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.12778702163061564,
318
+ "grad_norm": 0.8748223185539246,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 0.0521,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.13178036605657237,
325
+ "grad_norm": 1.464680790901184,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 0.0948,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.13178036605657237,
332
+ "eval_loss": 0.07193463295698166,
333
+ "eval_runtime": 94.3059,
334
+ "eval_samples_per_second": 13.414,
335
+ "eval_steps_per_second": 1.686,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.33230992818176e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null