auxyus commited on
Commit
634c0fc
·
verified ·
1 Parent(s): daed4d4

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 sha256:978fc3a36aa02ff4e4b8e582a8df18c0a8742fe4c260e8e3b70fede03d059ca4
3
  size 19552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc84fa4ccaafb5ca88bdde643e2920bd6307b40dacab0f938212e2665420db9
3
  size 19552
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6e0123ed99a9c8333b0e2ffadcbffd712caaeb4a962515e69f46ce18b91a479
3
  size 44354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83976741256f6949507ef62ec9a3b67750f6029f1a7bbe32d29d968690c31ff2
3
  size 44354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c45e8509362c8946d16db39b13d549197b82acbaa6f5959a7e441bdaff0afef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ffb1a9f905314256c3560fb26e0ee1cc6bd29505ea11d989f25455a0e7abb5c
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": 1.6071428571428572,
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": 44.129,
306
  "eval_steps_per_second": 5.574,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 185354158080.0,
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": 1.7678571428571428,
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": 44.129,
306
  "eval_steps_per_second": 5.574,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 1.6607142857142856,
311
+ "grad_norm": 0.04004579409956932,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 12.4285,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 1.7142857142857144,
318
+ "grad_norm": 0.04052690416574478,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 12.4281,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 1.7678571428571428,
325
+ "grad_norm": 0.043967243283987045,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 12.4284,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 1.7678571428571428,
332
+ "eval_loss": 12.429804801940918,
333
+ "eval_runtime": 2.1471,
334
+ "eval_samples_per_second": 44.246,
335
+ "eval_steps_per_second": 5.589,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 204467601408.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null