tuanna08go commited on
Commit
a370b76
·
verified ·
1 Parent(s): d2cbf76

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 sha256:4d166736af61f78ed9fd563d0cfdde33724df31f23800bc8f0b4c53f0650e5f6
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6ad556bd97da50e305b98c8a484073658e36cc49bb538e31e71541abe6e6e4
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a512a8847bbd1cf952f8428d9c45ebcbb129891f8d21fd5f78248f1917f096c
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6126a4c3dfc2e6bc13772ba8501d4b23f13634afef8cc8c57a97816cc4b69be2
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96e4daddc9d7c5cbeb54d01c4668ac702b17a95c44af4f4fdf33d4b01cc31cb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9dbdd915e523edf9fbadf618141dbc0ab0a7ef9e84774dcab8a9237c5a21f51
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": 0.018277680140597538,
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": 1.6509,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9061707439669248.0,
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": 0.02741652021089631,
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": 1.6509,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0210896309314587,
72
+ "grad_norm": 0.2966659367084503,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.6662,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0210896309314587,
79
+ "eval_loss": 1.7381675243377686,
80
+ "eval_runtime": 114.3973,
81
+ "eval_samples_per_second": 5.236,
82
+ "eval_steps_per_second": 2.622,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.02460456942003515,
87
+ "grad_norm": 0.266242653131485,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.6692,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3592561159503872e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null