chauhoang commited on
Commit
65a9b42
·
verified ·
1 Parent(s): 52b7a2a

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:d4397371949a0a11e6c9326f50376c519ee26fcc09698e9c507bb5dcb754345d
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42416108f97a3819b4bd2240a04742941a54982500e06041d6740b0f086f1b05
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:189c11d49dc4ec1b76a60a13824ce8f8cbdf82945637995ed559a5dd0a12b292
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764d30744a2d196fe5e3d3a693ba10ea4bc34dcfa41dc180226eee6119960791
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01898d7ee61fd42fd0e6cb22d62ed29c4e5b0a0f5b2fc626a3c984b595e158b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6777854a7d16d2ed048ffceaeb822cfc907d9b86c3ff3213c5abc2910706824f
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": 0.001130987983252678,
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": 0.6557,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1298144289619968.0,
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": 0.0016964819748790168,
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": 0.6557,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0013049861345223207,
72
+ "grad_norm": 0.431514710187912,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.6638,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0013049861345223207,
79
+ "eval_loss": 0.648958683013916,
80
+ "eval_runtime": 334.9897,
81
+ "eval_samples_per_second": 28.896,
82
+ "eval_steps_per_second": 14.448,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001522483823609374,
87
+ "grad_norm": 0.422538697719574,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.6469,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1963203433070592.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null