chauhoang commited on
Commit
23f8450
·
verified ·
1 Parent(s): 418e05b

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:eca81df7a64dcbef955defcdc893e7eaeabd36e26c8a2edfb854e067c04584a1
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13c203d4db1c2b0b1f28feb189626b182195af12e4fcdadbdf4f70f9a68ac56
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b88f026827207e77059bfe152a3c4a0fcf271e722da0c83418dae1406ef9a45f
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b67102e35457945c1fe28a47762ec97ae2540e8d2bbe0995d7241841cb04d89f
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": 0.01839731116221475,
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": 0.3967,
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": 0.02759596674332213,
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": 0.3967,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.021227666725632408,
72
+ "grad_norm": 7.217609405517578,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.2675,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.021227666725632408,
79
+ "eval_loss": 0.19041143357753754,
80
+ "eval_runtime": 47.9386,
81
+ "eval_samples_per_second": 12.412,
82
+ "eval_steps_per_second": 6.216,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.024765611179904477,
87
+ "grad_norm": 2.8961856365203857,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.2384,
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