oldiday commited on
Commit
f039994
·
verified ·
1 Parent(s): df312d0

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:f4433ad6cf019679e62efbe788522b91c37458129c1067a4580ae9b02ccd4112
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f07eee1ab12dd96d325c73c8146e730fe5d08f5411157ba03022053a279a91
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:766883cf96619f8dd359b441512cec68417e427045a983edad62fced6cbc90b0
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d240df8bfcde5fb3b54d54e577a335c4f1dadf63ca8cd57576bf5efd09af14d1
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7ea8262840a122cf727761fa8ac9dd15f3d9b85715f03be8d5dc6ff7641222c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be703232f77e7c534e421dcf5501e3b617cdcdf3bd14e61f4c5b6ba11022334
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": 0.0364167696976509,
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": 10.132,
277
  "eval_steps_per_second": 1.268,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 1.69102741270954e+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": 0.040463077441834326,
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": 10.132,
277
  "eval_steps_per_second": 1.268,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.03776553894571204,
282
+ "grad_norm": 3.1315290927886963,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 7.1733,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.039114308193773185,
289
+ "grad_norm": 3.2087924480438232,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 7.1793,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.040463077441834326,
296
+ "grad_norm": 3.4287378787994385,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 6.9864,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.040463077441834326,
303
+ "eval_loss": 1.7765320539474487,
304
+ "eval_runtime": 369.8484,
305
+ "eval_samples_per_second": 10.131,
306
+ "eval_steps_per_second": 1.268,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 1.866809888043172e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null