duyphu commited on
Commit
80f39cb
·
verified ·
1 Parent(s): c5ed6b9

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 sha256:24eb9a4923629aebd979d29c8e4411fd96a4d2d8632a25c06ac35d88b5cea3aa
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b799d4a8b1513acb5d49ab8640608c56263bfe37a23048a51282bc314823504e
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29aa99a06017a373a2c95d2f7d1454f98fe6195143d04ce74705dee58dd52384
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc65514a6a016348da951c4f066047cadcb4187e8380dc5728db6c17c0d96c1
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70aad4b3ac51dddc7d9c6e648201db746c0cc853235d6c6dbd5ee81055a6b8f9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f75c5d1de79fa8d130bf453a0e1b1047ff784c6b921ee1d2efd0d34aa6b721f
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": 0.01386481802426343,
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": 0.0351,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8250556258713600.0,
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": 0.02079722703639515,
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": 0.0351,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.015997866951073192,
72
+ "grad_norm": 0.33927980065345764,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.0159,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.015997866951073192,
79
+ "eval_loss": 0.011334585957229137,
80
+ "eval_runtime": 83.5481,
81
+ "eval_samples_per_second": 9.456,
82
+ "eval_steps_per_second": 4.728,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.01866417810958539,
87
+ "grad_norm": 0.2027255892753601,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.0098,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.23758343880704e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null