ardaspear commited on
Commit
8d4dcd2
·
verified ·
1 Parent(s): ca80665

Training in progress, step 81, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d8782bc461e8b015fe740a65535aa25fa75d17415539d401610c2b1d9d0a7d6
3
  size 228140600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf1ff1bde4a9a6022ac8d39608228a985747eed18a9868fb97da59a1c2b97eb
3
  size 228140600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:235a0f308146e6cf8a010693b5fab3580941eaf94971f2b643d8c142d33ce1e0
3
  size 116472340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f0bbd2c2a547b2578f9a6283ad7f48dec789a54d89e4acceebee8b4b2dffe05
3
  size 116472340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5266bdd4b52a1b86fdc9530ab1dabc1ae80542c8a6e21489d8e104bd2d986b44
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3142ee6aaa193c1c9391b604988921bcafd1308f2f439db9ebf61ffce370b67f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
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": 0.24742268041237114,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 6.794,
248
  "eval_steps_per_second": 0.86,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 2.516008518549504e+17,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.27835051546391754,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 6.794,
248
  "eval_steps_per_second": 0.86,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.25773195876288657,
253
+ "grad_norm": 1.9435456991195679,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 3.1961,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.26804123711340205,
260
+ "grad_norm": 3.1002867221832275,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 3.0302,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.27835051546391754,
267
+ "grad_norm": 1.6273797750473022,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 2.8564,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.27835051546391754,
274
+ "eval_loss": 0.7072886228561401,
275
+ "eval_runtime": 72.0658,
276
+ "eval_samples_per_second": 6.799,
277
+ "eval_steps_per_second": 0.86,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 2.8648187904393216e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null