qingy2024 commited on
Commit
1d3f3d4
·
verified ·
1 Parent(s): 62cb3b0

Upload checkpoint 8700

Browse files
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89b6ed8f166125c4e0ccb4438463feac8c4befdcfa3b5fc23df50b931dd37964
3
  size 4957560304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b11035d8bf31e165917a7dcfceb6ec5dc1f4f3c3ad78092bcaea45bfac2a86d
3
  size 4957560304
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfeea3b480b0ac3a7be7edb3e3d45b0b6eed0bc230ddbdd298ef3463ce89ffd9
3
  size 3989163248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e657eb4960ca2f126e63960bd32422b6ff61f48d25c083228c21ff92b84eb943
3
  size 3989163248
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc5cc673934837b111c47f04c42854cbbf4155db979be7dde3c8474b55635ed6
3
  size 17893865224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5b9e5e639d529391dd985fc3d312297ab0abb3033b2e8289b0cb7a465b27da
3
  size 17893865224
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb0516760d88d4baa388b6e998401e0078c7ad3407932309df513a21a23fcf7a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb9b203b48c284e5ca3d5f0f55dfbe5f8779d467d5680d977c3a7b3ba01095a7
3
  size 1064
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.9999425452456191,
5
  "eval_steps": 500,
6
- "global_step": 8702,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -20321,12 +20321,12 @@
20321
  "should_evaluate": false,
20322
  "should_log": false,
20323
  "should_save": true,
20324
- "should_training_stop": true
20325
  },
20326
  "attributes": {}
20327
  }
20328
  },
20329
- "total_flos": 3.1626194748539142e+19,
20330
  "train_batch_size": 4,
20331
  "trial_name": null,
20332
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9997127262280954,
5
  "eval_steps": 500,
6
+ "global_step": 8700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
20321
  "should_evaluate": false,
20322
  "should_log": false,
20323
  "should_save": true,
20324
+ "should_training_stop": false
20325
  },
20326
  "attributes": {}
20327
  }
20328
  },
20329
+ "total_flos": 3.161964823751688e+19,
20330
  "train_batch_size": 4,
20331
  "trial_name": null,
20332
  "trial_params": null