phungkhaccuong commited on
Commit
e9f48df
·
verified ·
1 Parent(s): 9f9eaff

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 sha256:05eb79e8c49c0567e57f6bf06c673e4075e3e7f71bb712baef67f68bf88c57b3
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72bbb0d4e294d2404e5324dd03e1f633dd15199c420e18727429c93447b934c5
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7935ef4822e8c2d6d428ec49be1138202a7b90ce57e0698a437dc258ee59deab
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfe31a3638c384ffbbc23ae26a0c4b4f68c0b2e0d7e15ad0aebad2c251bb1641
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a997aa8bfab00a35d7cfa486126e3d295d226a899068a295415cfc8e8058a7c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551c6190aa7460da0f5f87f766f1e262863111d15319ee98d5b09ac189feeb2f
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": 0.05442176870748299,
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": 0.3618,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 665059143450624.0,
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": 0.08163265306122448,
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": 0.3618,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.06279434850863422,
72
+ "grad_norm": 1.4411214590072632,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.3125,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.06279434850863422,
79
+ "eval_loss": 0.3016051948070526,
80
+ "eval_runtime": 6.2362,
81
+ "eval_samples_per_second": 32.392,
82
+ "eval_steps_per_second": 16.196,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.07326007326007326,
87
+ "grad_norm": 0.9302160143852234,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.2499,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 997588715175936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null