ardaspear commited on
Commit
c6ac523
1 Parent(s): 4559bba

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:ee9f7eea2dd575295592ba917b24d7a282381a526cf5ec960273ae9d5f7d1300
3
  size 338298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9e8fd7c8a12791cc506371f45bfae65abf676668c63fa633a2c452534c6a12
3
  size 338298
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:699c1a1b1e54c1590e45fffc670055a3d8522c0ae0ae5d30acf382f14654ceeb
3
  size 418030
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f96cfcf2a4a955e6ac84e6be957b924bc505a87d5a884175cd88db7225dd1f
3
  size 418030
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11b709a6bf0fa0f36688b3f138d920bc6ad6f587da0edf35784ddb4f658162ee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b5c4946255fb1e60837fcc05354e2a4c3f41256e6e0a49b069a9b109e53ea0b
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": 0.45918367346938777,
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": 614.27,
306
  "eval_steps_per_second": 156.36,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 865015234560.0,
328
  "train_batch_size": 4,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5051020408163265,
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": 614.27,
306
  "eval_steps_per_second": 156.36,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.4744897959183674,
311
+ "grad_norm": 0.20826943218708038,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 6.8322,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.4897959183673469,
318
+ "grad_norm": 0.20993828773498535,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 6.8318,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.5051020408163265,
325
+ "grad_norm": 0.21039879322052002,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 6.8296,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.5051020408163265,
332
+ "eval_loss": 6.827375411987305,
333
+ "eval_runtime": 0.2813,
334
+ "eval_samples_per_second": 586.647,
335
+ "eval_steps_per_second": 149.328,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 951516758016.0,
357
  "train_batch_size": 4,
358
  "trial_name": null,
359
  "trial_params": null