ardaspear commited on
Commit
c481535
·
verified ·
1 Parent(s): 66676a3

Training in progress, step 90, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cf1ff1bde4a9a6022ac8d39608228a985747eed18a9868fb97da59a1c2b97eb
3
  size 228140600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8c946b2fe94b05fb6d13996d3434b3af89d3dc407d59150d8a123a8af0cdf1
3
  size 228140600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f0bbd2c2a547b2578f9a6283ad7f48dec789a54d89e4acceebee8b4b2dffe05
3
  size 116472340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c0998d152b70a78eb16205fc52e7d8ddc5a96938cfefc0e1a43967fa559385
3
  size 116472340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3142ee6aaa193c1c9391b604988921bcafd1308f2f439db9ebf61ffce370b67f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac30eb90771ad572928492a9b294c2a00ae840bf4dd4ced4785e131650bb6d2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
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": 0.27835051546391754,
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,
@@ -276,6 +276,35 @@
276
  "eval_samples_per_second": 6.799,
277
  "eval_steps_per_second": 0.86,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 2.8648187904393216e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.30927835051546393,
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,
 
276
  "eval_samples_per_second": 6.799,
277
  "eval_steps_per_second": 0.86,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.28865979381443296,
282
+ "grad_norm": 1.9313831329345703,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 2.6863,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.29896907216494845,
289
+ "grad_norm": 1.7214744091033936,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 2.9589,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.30927835051546393,
296
+ "grad_norm": 1.789853811264038,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 3.0606,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.30927835051546393,
303
+ "eval_loss": 0.7060263752937317,
304
+ "eval_runtime": 72.1222,
305
+ "eval_samples_per_second": 6.794,
306
+ "eval_steps_per_second": 0.86,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 3.1964744587935744e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null