duyphu commited on
Commit
0caec8d
·
verified ·
1 Parent(s): 0ea783d

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:eae67c0e24fc390afa0ee2d8f1fc30af918a2f6ac3f4c9be5578a084f409dcb0
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133ad96631b12af0d3b197c91d748a70df94965e1d5b6a1f9f94c52e50938d1e
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21529a83ff0011aca45dd627414c70a1c80522adcb75c6b8b9f1313359055f2e
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e878f892b659bd3210388c110fc2f4d9c51547a43ff3b59d8ea6042ec67d258
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4789694b0dfbba236adc1e0423cccff54c291754e75185fa5ae6a3664fb3ce4a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6684d632e0ed9894b7d3581195993fbfd0a1de05dcd5960c38ed169d3e9d554
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": 0.01369141653501843,
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": 0.0001,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 625418340139008.0,
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": 0.020537124802527645,
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": 0.0001,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.01579778830963665,
72
+ "grad_norm": 0.00030174487619660795,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.0,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.01579778830963665,
79
+ "eval_loss": 3.3131864256574772e-06,
80
+ "eval_runtime": 21.4681,
81
+ "eval_samples_per_second": 37.265,
82
+ "eval_steps_per_second": 18.632,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.018430753027909426,
87
+ "grad_norm": 0.00019788318604696542,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.0,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 938127510208512.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null