oldiday commited on
Commit
366a146
·
verified ·
1 Parent(s): 6fee177

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 sha256:37f137cabd55bb78d9483291e1a1df07524d4721c29e5d94cb4469c46e8c7172
3
  size 15156512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3566d37ca1b990a59eac09fc214f8ceb198a249ef11caf0177268403d0869fa
3
  size 15156512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad1e4b0221c13bf71cb9439ed9839762d0e68539c486d15c7710fb4e1b8a6af1
3
  size 7825914
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8d2d87c254213b594fa4d4db52f856d090d4355b9adf109bd997154a894b965
3
  size 7825914
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e99209c41da0980c9208e58dbfe7c7019b4fbd930a44a38b4e9bae1f6563a0d6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189135c442502e7dffa763dde1dec0944237776c36851e246a627de318e5012c
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": 0.008544371395343317,
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": 156.393,
306
  "eval_steps_per_second": 19.554,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 7714123315937280.0,
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": 0.009398808534877649,
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": 156.393,
306
  "eval_steps_per_second": 19.554,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.008829183775188095,
311
+ "grad_norm": 1.6321587562561035,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 8.9392,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.009113996155032873,
318
+ "grad_norm": 1.5234466791152954,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 8.8882,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.009398808534877649,
325
+ "grad_norm": 1.6211401224136353,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 8.8878,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.009398808534877649,
332
+ "eval_loss": 8.878786087036133,
333
+ "eval_runtime": 114.8285,
334
+ "eval_samples_per_second": 154.491,
335
+ "eval_steps_per_second": 19.316,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 8485535647531008.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null