mgh6 commited on
Commit
9b9a730
·
verified ·
1 Parent(s): b2a50f5

Training in progress, step 11800, 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:f4f9f022bd865f30e57f5db3f26032b54e5d0a3288e6a73ab297bdb678b13eaf
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62633b7dcaf8c61837361414d3b9085bce6a5e56f706cb82c07b9df6610d8e6b
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c57aa65c84a15777a1928efbeeb57520ae429b9f06503f7659cf22eb55588906
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7e06a365031b596ef70b53e34c40180945117e4d2cfd280c9df5380f0aee53
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40ef4a11b96067b992cf8afde7441d5bb4e1e029d276e66e4a189b2de033ce43
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea185db77febfbf42af1db49540af4d7f667c73c6e73736f39f279a136fad8a
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:037287bc729b2fa86d80a430fb4fe83cf5198d8ba517f10314c41efc8f3e614d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8182ee7bfd4cb11176b578a92d88b169573a199f40bbd7eb74ee316355558489
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": 23.396344321199813,
5
  "eval_steps": 500,
6
- "global_step": 11700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1010,6 +1010,13 @@
1010
  "learning_rate": 2.2000000000000003e-05,
1011
  "loss": 1.2218,
1012
  "step": 11700
 
 
 
 
 
 
 
1013
  }
1014
  ],
1015
  "logging_steps": 100,
@@ -1029,7 +1036,7 @@
1029
  "attributes": {}
1030
  }
1031
  },
1032
- "total_flos": 1.8260561020999172e+19,
1033
  "train_batch_size": 8,
1034
  "trial_name": null,
1035
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 23.596313076081863,
5
  "eval_steps": 500,
6
+ "global_step": 11800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1010
  "learning_rate": 2.2000000000000003e-05,
1011
  "loss": 1.2218,
1012
  "step": 11700
1013
+ },
1014
+ {
1015
+ "epoch": 23.596313076081863,
1016
+ "grad_norm": 0.2434803992509842,
1017
+ "learning_rate": 2.1333333333333335e-05,
1018
+ "loss": 1.224,
1019
+ "step": 11800
1020
  }
1021
  ],
1022
  "logging_steps": 100,
 
1036
  "attributes": {}
1037
  }
1038
  },
1039
+ "total_flos": 1.8416635992187339e+19,
1040
  "train_batch_size": 8,
1041
  "trial_name": null,
1042
  "trial_params": null