chauhoang commited on
Commit
9339066
·
verified ·
1 Parent(s): 088b8e4

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:dd547a88a26156fc10dce217a728a045f648f1d380d836efa6348aa996c54706
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce8ee556fce32850950d170c1ab554b4151f034af71b91070333ee7b5836113
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39b33a225feddad4c076acc936d56a0fb5f8c43b8de2d5281051163310f6aaed
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23431ff47b663a92ea1e0db610ee5d0444d764d82b5801579d99f642e22c8c2a
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7144b0dce529bd6ff66b9941983b581e0ea1f47f188e811ff4fa48d3921f957f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79860259ff731f0b1c006300fee3fbd1e0fb1cad375751b62eee5d8cabbc13f0
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": 0.055378061767838126,
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": 2.3689,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4855106151383040.0,
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": 0.08306709265175719,
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": 2.3689,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.06389776357827476,
72
+ "grad_norm": 2.8140757083892822,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.4515,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.06389776357827476,
79
+ "eval_loss": 2.134063482284546,
80
+ "eval_runtime": 14.1573,
81
+ "eval_samples_per_second": 13.986,
82
+ "eval_steps_per_second": 6.993,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.07454739084132056,
87
+ "grad_norm": 2.416900157928467,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.9785,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7259539673972736.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null