chauhoang commited on
Commit
7a013d9
·
verified ·
1 Parent(s): 9183b82

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 sha256:831eb6ff7c7ec07a949a88e1b1f9e6543e8e00f453ee5afdd7004975f252ff77
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32264a2a885aa27a0aa96ce9f09b78b305bd715aee8d9c92de828bc0caac8ff
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37ffaf58eee7e49d66e40334a90197f3b16b3ad935288baf459cbc6ded3d09e3
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104f14af17cda8d0007171226780c1d4ab0668d8b2b9fe4fdf33bc489866df5a
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bacace43e547c94b41abff4056126eb4e9b430747001acf89e0e67ee0e4b31ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee089b8eda3d2f03579660229909140f9bb3bc7af0a9129bb3775da6328a203
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": 0.001960821282452535,
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": 0.6764,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9247821240729600.0,
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": 0.0029412319236788026,
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": 0.6764,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0022624860951375404,
72
+ "grad_norm": 1.5029770135879517,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.5842,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0022624860951375404,
79
+ "eval_loss": 0.5466399192810059,
80
+ "eval_runtime": 657.5066,
81
+ "eval_samples_per_second": 8.493,
82
+ "eval_steps_per_second": 4.246,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002639567110993797,
87
+ "grad_norm": 1.5323377847671509,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.5669,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3964210073501696e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null