mgh6 commited on
Commit
0eb648d
·
verified ·
1 Parent(s): fa08afe

Training in progress, step 10600, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07cd80e643eb2a26b379e7fa735978101f48a40e12d6f3481f32426f56decfd3
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcccd26783f1e34eae156e2da0b5fef41c1e65d587cfb0f831432d18f096f763
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:815b4aad044494428efe65ad0dd7d96090c7bb0cdd3e7891ab0bd30980a00de0
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301eec8eda217373e240c25d9c969e10d53e0d4b20644d67d9fd64dacf53376c
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92bc953fd68dd79c772e0c4700bc289fc99028c313b2f470c74ebf85287cb40e
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b7be0f4cd02dd7e17ebc6e8c0b49743ef05f4decb5389592f997e0d71fc7362
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51c6e60b9620f85b02af88312b38e0a19eeb53d066787459ff7296998b69c686
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0864d7691cefdaea2817fc3cef666767c8663ff5575730845b1f369e52abde04
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": 20.996719262615215,
5
  "eval_steps": 500,
6
- "global_step": 10500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -910,6 +910,13 @@
910
  "eval_samples_per_second": 19.859,
911
  "eval_steps_per_second": 2.483,
912
  "step": 10500
 
 
 
 
 
 
 
913
  }
914
  ],
915
  "logging_steps": 100,
@@ -929,7 +936,7 @@
929
  "attributes": {}
930
  }
931
  },
932
- "total_flos": 1.6387688837351997e+19,
933
  "train_batch_size": 8,
934
  "trial_name": null,
935
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 21.196688017497266,
5
  "eval_steps": 500,
6
+ "global_step": 10600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
910
  "eval_samples_per_second": 19.859,
911
  "eval_steps_per_second": 2.483,
912
  "step": 10500
913
+ },
914
+ {
915
+ "epoch": 21.196688017497266,
916
+ "grad_norm": 0.2408709079027176,
917
+ "learning_rate": 2.9333333333333336e-05,
918
+ "loss": 1.2215,
919
+ "step": 10600
920
  }
921
  ],
922
  "logging_steps": 100,
 
936
  "attributes": {}
937
  }
938
  },
939
+ "total_flos": 1.654375465166989e+19,
940
  "train_batch_size": 8,
941
  "trial_name": null,
942
  "trial_params": null