duyphu commited on
Commit
378d29d
·
verified ·
1 Parent(s): 68f8309

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 sha256:5e32ea8fc338d99e4e0c13688e72a59216b557fc2acf70623158aa87abae95a0
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46927eb7f44466a1ba4fea38fee7cfd01e70fe7441140288a7d7427551f825b5
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f725303b41f6995c7b8ecf7a946e767717a1a6ae7815ce9b26dea67c1fce26b
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c188ce8aee542ede6f5a5529abea22bf64c05794fe771ca6aa6188696394964
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab1d35b7b08d2869ce54f82448af01693fcbfcf11fc2ad8a25dbf70409dac1df
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f40a4c065023b7c7e84169852874083c9c8aff5ea2268e61269a141fdbb1b4f
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": 0.056799563080284,
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": 0.95,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4968837682298880.0,
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": 0.085199344620426,
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": 0.95,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0655379574003277,
72
+ "grad_norm": 9.343716621398926,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.8587,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0655379574003277,
79
+ "eval_loss": 0.9797313213348389,
80
+ "eval_runtime": 14.9045,
81
+ "eval_samples_per_second": 12.949,
82
+ "eval_steps_per_second": 6.508,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0764609503003823,
87
+ "grad_norm": 5.940131664276123,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.8317,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7501033808855040.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null