oldiday commited on
Commit
f7349a9
·
verified ·
1 Parent(s): d8ec4d1

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:edbc21c787945e38d2c438b2ecb5645373cf162e96885a338948d711adc3209a
3
  size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21bbebd7740c97702a254bec74443839e155afdbcaeb2c516ced3ed8dea2a8f0
3
  size 119801528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cc552429c21b7e5ae820c3a5827388b559772022c63004799a847b9a1edeed7
3
  size 61392180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:126e375a861516cabd2e963e0bf443ee3d41f0061558d9c4a326b43b0d0ddee1
3
  size 61392180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24f6965551efad167728b9169c302fa4cac2713a66fa6c20d26656298bffc5a9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53560af45fac022c4d2c5071405400a8b63d20569d0888a324347390aaf7a3c9
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": 0.07514088916718847,
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": 11.446,
306
  "eval_steps_per_second": 1.435,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 9.925702170181632e+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": 0.08265497808390733,
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": 11.446,
306
  "eval_steps_per_second": 1.435,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.07764558547276143,
311
+ "grad_norm": 0.3372178375720978,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 1.3194,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.08015028177833437,
318
+ "grad_norm": 0.35166051983833313,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 1.3366,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.08265497808390733,
325
+ "grad_norm": 0.33704036474227905,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 1.3919,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.08265497808390733,
332
+ "eval_loss": 1.3384730815887451,
333
+ "eval_runtime": 176.3253,
334
+ "eval_samples_per_second": 11.445,
335
+ "eval_steps_per_second": 1.435,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.0918272387199795e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null