phungkhaccuong commited on
Commit
2abfb06
·
verified ·
1 Parent(s): efc8f61

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 sha256:9e7e4efbbc0960b11215b19ee697d612d2a08e75c9fae0810852255be9118ef4
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285ef7d844df91bcbe3f44bf76ca306bed6dc48ab536abb11e669b0cf7f5ab6f
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b22b47c89c9b014aa551edb170adc69971e51254fee1ba4258c4a384a35ea66
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c12f844e83b270eca953a432b58a5975e7bf1e77981563496963bf60a80cb89
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55bb1e80ed6d0d4c2435a0b8bffcc98b3af6698f43dd2898b0736579515f3096
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba1e30e28aa45cf44ce5d51d23b6a01a5f4515c33ee5cd42abcbcc581e0b1cf
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": 0.09195402298850575,
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": 0.842,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4366730746920960.0,
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": 0.13793103448275862,
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": 0.842,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.10610079575596817,
72
+ "grad_norm": 4.434057712554932,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.0252,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.10610079575596817,
79
+ "eval_loss": 0.8172988891601562,
80
+ "eval_runtime": 14.1194,
81
+ "eval_samples_per_second": 8.499,
82
+ "eval_steps_per_second": 4.249,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.1237842617152962,
87
+ "grad_norm": 4.096339225769043,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.6784,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6550096120381440.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null