Nexspear commited on
Commit
8ad69f9
·
verified ·
1 Parent(s): 390d498

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 sha256:58f2ce4ae7af57b60f7578d767277d756cd4a2659717dfeae882c0417ebe7919
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7345791d4a517543e41d32929260e235bf187624dcc2fb731f247a56b35d709
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6136fccae05899c5770ba60d4ac50df69804114f951aa1f1c8d286c9262aa4c3
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019370692d0f42d58ad414f4b5b2a8e0e71e5c543a2fc3f4dfd8748c28115f81
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38d98de3804c2db040b85e337427c43f61d74444b1ae81f8d1f76948acd21257
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0822341b37d6b966f9522273003e3c7b865a882b22bd8905d2a264c6840d0dd
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": 1.5652173913043477,
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": 36.22,
306
  "eval_steps_per_second": 4.854,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 2.363530176626688e+16,
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": 1.7217391304347827,
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": 36.22,
306
  "eval_steps_per_second": 4.854,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 1.617391304347826,
311
+ "grad_norm": 0.4980301558971405,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 1.164,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 1.6695652173913045,
318
+ "grad_norm": 0.4769861102104187,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 0.7116,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 1.7217391304347827,
325
+ "grad_norm": 0.4263245463371277,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 1.272,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 1.7217391304347827,
332
+ "eval_loss": 0.9631911516189575,
333
+ "eval_runtime": 2.7065,
334
+ "eval_samples_per_second": 35.84,
335
+ "eval_steps_per_second": 4.803,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 2.6117212556230656e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null