khyat commited on
Commit
494e02d
·
verified ·
1 Parent(s): 68daea4

Training in progress, step 15500, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:533e935409b4170d162fed8d1c119a219ea4f62de432fe3747abe3ea89cf4341
3
  size 5544932128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4a371729967bce8d31eac7beba1522a6dabd9b8c5b5dc74c71ee0c23ecff4b
3
  size 5544932128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45d7d6dc909c5ed63e989fad2d139f2dd3e54db1a7a058011a8dad4f5522f3fd
3
  size 2778379356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68108d6fc3024d0784d2df3e6ec9b3d03553fdbb99b26671786af518accffee
3
  size 2778379356
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0625e950d9560e69388b40a91a9ea0cb749f2db07fe9f8a1ba977525f540fb44
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66a17452b4372f999c6063a7de49c04b5e9251b9e7cf0d0071dc845ddf0c4a1a
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": 0.9579538106604293,
5
  "eval_steps": 500,
6
- "global_step": 15000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -217,6 +217,13 @@
217
  "learning_rate": 2.3346579619642353e-06,
218
  "loss": 0.1127,
219
  "step": 15000
 
 
 
 
 
 
 
220
  }
221
  ],
222
  "logging_steps": 500,
@@ -236,7 +243,7 @@
236
  "attributes": {}
237
  }
238
  },
239
- "total_flos": 1.6005421733888655e+19,
240
  "train_batch_size": 2,
241
  "trial_name": null,
242
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9898856043491103,
5
  "eval_steps": 500,
6
+ "global_step": 15500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
217
  "learning_rate": 2.3346579619642353e-06,
218
  "loss": 0.1127,
219
  "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.9898856043491103,
223
+ "grad_norm": 0.3714085519313812,
224
+ "learning_rate": 5.606017598637525e-07,
225
+ "loss": 0.1099,
226
+ "step": 15500
227
  }
228
  ],
229
  "logging_steps": 500,
 
243
  "attributes": {}
244
  }
245
  },
246
+ "total_flos": 1.653612317438976e+19,
247
  "train_batch_size": 2,
248
  "trial_name": null,
249
  "trial_params": null