chauhoang commited on
Commit
8234675
·
verified ·
1 Parent(s): d05d657

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:b64327a169e6d662f85098062e4b9d09820e130c4285536dd57334267390201f
3
  size 32856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4115b9c8be12d47d473dda16e0f38890e54cf251362c88c4c98cec087d4308
3
  size 32856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6261f830fdf9b4e24440e1563df6021768499f58e4303728cc6270c08a19794b
3
  size 71358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6dedff1cecf76773f8e3c26adc19594e9f77d6866ac07a2ae1c96d6969c04e
3
  size 71358
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
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": 0.0006052846001629612,
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": 62.8437,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 20171980800.0,
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": 0.0009079269002444419,
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": 62.8437,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0006984053078803399,
72
+ "grad_norm": 1.821262001991272,
73
+ "learning_rate": 5e-05,
74
+ "loss": 84.6001,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0006984053078803399,
79
+ "eval_loss": NaN,
80
+ "eval_runtime": 79.1527,
81
+ "eval_samples_per_second": 228.508,
82
+ "eval_steps_per_second": 114.26,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0008148061925270633,
87
+ "grad_norm": 1.472610592842102,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 52.4185,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 30257971200.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null