mgh6 commited on
Commit
0c60814
·
verified ·
1 Parent(s): c1e2838

Training in progress, step 13400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4103a2add7fb89c1b79882e7fb8c6de8cc76be806c788d6de2a3740a555b7c9c
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1386e828b3ba479196522024102112e210e952e5254c67fc939f220aff955ac6
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07856b3f020773c2b2571cf5b26bd9050afcac89d3a152df7e3fd595b927d69c
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff9ebb9fca0c17ff991f1cef7618725b58455f772919586e80516856dad8806
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:f50e513ed146397e0157d8860ccde6d3ee73cd5ca826ca991c743b54369d411f
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd8409f64af20a99c74e394e705eb79e774a42d36c1eb3e8c1583d929923352
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac652e298728dd54f7655367206bd90df753b21de87616802de685012895f259
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee4f684a730e891fd1e26e72f5546f480a0c3d9d36c0f17b64dcdf05ef17e02
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": 26.595844399312607,
5
  "eval_steps": 500,
6
- "global_step": 13300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1146,6 +1146,13 @@
1146
  "learning_rate": 1.1333333333333334e-05,
1147
  "loss": 1.2237,
1148
  "step": 13300
 
 
 
 
 
 
 
1149
  }
1150
  ],
1151
  "logging_steps": 100,
@@ -1165,7 +1172,7 @@
1165
  "attributes": {}
1166
  }
1167
  },
1168
- "total_flos": 2.0757733089399013e+19,
1169
  "train_batch_size": 8,
1170
  "trial_name": null,
1171
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 26.795813154194658,
5
  "eval_steps": 500,
6
+ "global_step": 13400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1146
  "learning_rate": 1.1333333333333334e-05,
1147
  "loss": 1.2237,
1148
  "step": 13300
1149
+ },
1150
+ {
1151
+ "epoch": 26.795813154194658,
1152
+ "grad_norm": 0.24814079701900482,
1153
+ "learning_rate": 1.0666666666666667e-05,
1154
+ "loss": 1.2186,
1155
+ "step": 13400
1156
  }
1157
  ],
1158
  "logging_steps": 100,
 
1172
  "attributes": {}
1173
  }
1174
  },
1175
+ "total_flos": 2.091380806058718e+19,
1176
  "train_batch_size": 8,
1177
  "trial_name": null,
1178
  "trial_params": null