phungkhaccuong commited on
Commit
009f1eb
·
verified ·
1 Parent(s): 2f42f23

Training in progress, step 39, 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:e04538e0b69c4bf3b8544768736855d47844ff2eaf6c5851c5aebb3324e999d6
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9058c24b9d8d1f986400e4556450eb103cc68da04b1bdde58420cc279656ad52
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7870fd102501046c50f74597756060bbfd618c76c9f091217818de6247bfe523
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d508e13decc03060dafd2e0947ba33ab5e7652518bf66f2b6ab89ba74ffdb2cd
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39cc63099a8df0e8db25d6448d4aea7c7ade01b93a08b37545050aab75ed73ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23394f11c585caee6f023d3d27fbf169d72b7ba93e512d965e8d71c36f05c33
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.054223149113660066,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.0479,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1425277392519168.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.08133472367049009,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.0479,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.06256517205422316,
72
+ "grad_norm": 0.9831803441047668,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.8,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.06256517205422316,
79
+ "eval_loss": 1.8727952241897583,
80
+ "eval_runtime": 11.3697,
81
+ "eval_samples_per_second": 17.766,
82
+ "eval_steps_per_second": 8.883,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.072992700729927,
87
+ "grad_norm": 0.890938937664032,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.9681,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2162920955314176.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null