flytech commited on
Commit
580112a
·
1 Parent(s): c512445

Training in progress, step 600, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8641639f36d2017cd3be1c77d3de39c47ab3545ed6cdf0ef30eafe1db1dca62e
3
  size 67143296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157d7e277c1c8219b9d93cf7040850a7ac5a80fc6b886b36435d94f77c8d1c92
3
  size 67143296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44e354b2b9a397b20dbba46c4d4bd8056e9c164df5588f0377d09afe9a838825
3
  size 33920095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ce837df695dd71c1cbdb21655cb5bb90c0317c9aa59a2fd2ba6110cfffdde7b
3
  size 33920095
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ec45735acf0d21a6a13a33353b33cadb4eb3f9c802c936af55a3f5542ea95b3
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816f7fa111049288948681980d7f6da0ed6b67a312e2df8d010618bfb7bb84eb
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1352cee7a141eadc0dec5a54fb0352c24d3de0192e8f627a38660bb21a3c14e2
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d35059d85341a60a5de1f3d03e1d2de2567877022fe78e41439726275de277
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.048780487804878,
5
  "eval_steps": 100,
6
- "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -72,13 +72,26 @@
72
  "eval_samples_per_second": 2.037,
73
  "eval_steps_per_second": 0.266,
74
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  }
76
  ],
77
  "logging_steps": 100,
78
  "max_steps": 1312,
79
  "num_train_epochs": 8,
80
  "save_steps": 100,
81
- "total_flos": 4.151500035902669e+16,
82
  "trial_name": null,
83
  "trial_params": null
84
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.658536585365854,
5
  "eval_steps": 100,
6
+ "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
72
  "eval_samples_per_second": 2.037,
73
  "eval_steps_per_second": 0.266,
74
  "step": 500
75
+ },
76
+ {
77
+ "epoch": 3.66,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.0576,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 3.66,
84
+ "eval_runtime": 33.8607,
85
+ "eval_samples_per_second": 2.038,
86
+ "eval_steps_per_second": 0.266,
87
+ "step": 600
88
  }
89
  ],
90
  "logging_steps": 100,
91
  "max_steps": 1312,
92
  "num_train_epochs": 8,
93
  "save_steps": 100,
94
+ "total_flos": 4.983672430972109e+16,
95
  "trial_name": null,
96
  "trial_params": null
97
  }