duyphu commited on
Commit
3ff8cc0
·
verified ·
1 Parent(s): 6512a01

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:ceba5856dd087ecefc1a2431c822e33c924e7c48b64bc1fca8d0a7045a633b6e
3
  size 32856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a3837cf0e557fd316ab61ff8e04d3f59b8c9858c0fce92029776f07e461f7a
3
  size 32856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84afc5c9a55c976b81a988367e184d8f398de1c26ac086e8030465277b4d2d9b
3
  size 71358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43decc6191ed79417ec300331f6c775e4187e257a39b3bdd592bcf4373630276
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": 0.0004369050319696855,
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": 44.2714,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 38849740800.0,
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": 0.0006553575479545283,
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": 44.2714,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005041211907342526,
72
+ "grad_norm": 0.9127441048622131,
73
+ "learning_rate": 5e-05,
74
+ "loss": 44.2555,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005041211907342526,
79
+ "eval_loss": 11.063674926757812,
80
+ "eval_runtime": 180.8119,
81
+ "eval_samples_per_second": 138.58,
82
+ "eval_steps_per_second": 69.293,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0005881413891899612,
87
+ "grad_norm": 0.9231416583061218,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 44.2482,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 58274611200.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null