ardaspear commited on
Commit
a43e22f
·
verified ·
1 Parent(s): 353dadc

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:bfdfd19792a9dbd2720aeaed1a4167bc1f2f00c5a2f87732af76a348929cc758
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e527d066bb71ea5091dca932e80523b89769cbcf347bc0608c33419b82fa9f
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3275035391a762bc48aec56071648a53c024855788cdf14fff0f522318886b02
3
  size 42608388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157986dd13cdee42acbe0789742e23a1e240f6f83df37fd87a3f6c79c60d7a95
3
  size 42608388
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fbf0174a92740940690c194188c669febbb8555816ce6230c570c8e14a577c0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52946e0252615f36cad448e4b44b69930b25ebc27175be7067636619699904c9
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": 0.0373948270489249,
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": 23.393,
306
  "eval_steps_per_second": 2.926,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 3.629126828792218e+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": 0.04113430975381739,
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": 23.393,
306
  "eval_steps_per_second": 2.926,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.038641321283889064,
311
+ "grad_norm": 0.6684338450431824,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 1.167,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.039887815518853224,
318
+ "grad_norm": 0.700363278388977,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 1.2644,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.04113430975381739,
325
+ "grad_norm": 0.7705054879188538,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 1.2685,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.04113430975381739,
332
+ "eval_loss": 1.2470118999481201,
333
+ "eval_runtime": 173.4404,
334
+ "eval_samples_per_second": 23.374,
335
+ "eval_steps_per_second": 2.923,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 4.001087196286157e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null