duyphu commited on
Commit
5089ec7
·
verified ·
1 Parent(s): 844088f

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 sha256:801ee0a5f782916528a28a521d16b749724342af9f6ff4c11c65687196946758
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be6cfe8739e42f10532a9fb1000e79850c23cf8328bca1ef035214eba9d359a
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0044b10a62b25903d949fb17fa46f2116c061ca9ed16c1e9d543ecd89fc06c67
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30642f462ce258be1e8deb06c2bad7eb1333b2715398c12c27bfbf8cff7be7f6
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 sha256:89125b381bd706e47d0969ca57bde232385b184bb6fee985c4b095b282bae7af
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": 0.023674026860915093,
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": 2.2521,
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": 0.035511040291372635,
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": 2.2521,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.027316184839517414,
72
+ "grad_norm": 11.48447036743164,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.416,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.027316184839517414,
79
+ "eval_loss": 1.9078246355056763,
80
+ "eval_runtime": 37.4007,
81
+ "eval_samples_per_second": 12.379,
82
+ "eval_steps_per_second": 6.203,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03186888231277032,
87
+ "grad_norm": 8.533246040344238,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.6025,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7453256523448320.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null