chauhoang commited on
Commit
8bfd5af
·
verified ·
1 Parent(s): 25a0e39

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:fa209710d25f02d073c6e33d715ef603159e1541b3b288d7116272513424e2b2
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bdd4db947580c240730d40ba05463553c77208ed1bbc98dbeb6af05a13d4539
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbc0bb2e06fb07887025cc073c02153a4eac2e336eb95b5d29d7603801e77f79
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d57cd9ca359f609ab2f12d9e9ef4c697228cdf41921e8e425d34398d5ab7b7f
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": 0.02293274531422271,
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": 2.4782,
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": 0.03439911797133407,
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": 2.4782,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.026460859977949284,
72
+ "grad_norm": 5.2271623611450195,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.5298,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.026460859977949284,
79
+ "eval_loss": 2.3998324871063232,
80
+ "eval_runtime": 38.7979,
81
+ "eval_samples_per_second": 12.32,
82
+ "eval_steps_per_second": 6.16,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.030871003307607496,
87
+ "grad_norm": 4.6522016525268555,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.3057,
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