Femboyuwu2000 commited on
Commit
6b2df5e
1 Parent(s): 3c45183

Training in progress, step 2920, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53f013c8a2c8bef97abb794e6a06b77a2e4147632cf2273758eca6f336e2f82f
3
  size 13982248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6c16135c13b23b78a32406104d4f95e87d9791d1a272abfccfbd9fdb510426
3
  size 13982248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d5bf1a7d0bfb46b3a3dd1d3164d601e5d0acbf095447fb95f3aa1049e4f9c18
3
  size 7062522
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b05dba35ea8a717a04f46d499a1ccf269bb03de54656129a1c330a120df94f
3
  size 7062522
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35e1a4b7f4cf5b6d8da788548ce2d5664e1ef7d1e94833e7402606e114248110
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b286f648466e298147b9ac515ac28c993ffdd3dde88ab047cd5663dfb0283c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e6ba93e40726a23826255063f80deb5e022a089a3ff72f2cec37c66a0e303e9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd83110a1782b749193fd27672b7b7d37d3e0002a327d8a612fab168891e9de5
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": 0.232,
5
  "eval_steps": 500,
6
- "global_step": 2900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1022,6 +1022,13 @@
1022
  "learning_rate": 2.8971541407162637e-05,
1023
  "loss": 3.5707,
1024
  "step": 2900
 
 
 
 
 
 
 
1025
  }
1026
  ],
1027
  "logging_steps": 20,
@@ -1029,7 +1036,7 @@
1029
  "num_input_tokens_seen": 0,
1030
  "num_train_epochs": 2,
1031
  "save_steps": 20,
1032
- "total_flos": 6859880349204480.0,
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": 0.2336,
5
  "eval_steps": 500,
6
+ "global_step": 2920,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1022
  "learning_rate": 2.8971541407162637e-05,
1023
  "loss": 3.5707,
1024
  "step": 2900
1025
+ },
1026
+ {
1027
+ "epoch": 0.23,
1028
+ "grad_norm": 31.303403854370117,
1029
+ "learning_rate": 2.8953789174920795e-05,
1030
+ "loss": 3.5748,
1031
+ "step": 2920
1032
  }
1033
  ],
1034
  "logging_steps": 20,
 
1036
  "num_input_tokens_seen": 0,
1037
  "num_train_epochs": 2,
1038
  "save_steps": 20,
1039
+ "total_flos": 6907678563827712.0,
1040
  "train_batch_size": 8,
1041
  "trial_name": null,
1042
  "trial_params": null