chauhoang commited on
Commit
e7e4799
·
verified ·
1 Parent(s): 6373850

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 sha256:68913d84892d3858fb9abf74c31181a3333dc7ca38a5b31684cfc99e99414c31
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2d927879e78c01b3d9c98eadc02a1f3c184ca2aa7a3b2d11d46c32ccfe4c5b
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a435c4428c0ef485f02b81658cd570d7a494bf33d09783f1076f98242fd1ac1
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9362519b342a46efb766dc3221299ad2e9eab812acfde9fa15de722c81a3a40
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b20b810bbff08c53880fe8d9f68c3b26b73045caeb0ce540722b11f3250e5fc6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22601140bc0a5947d3bbd230e18458f69ce95eeff744ca680f4ea6f1cc378d76
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": 0.0025619549687145885,
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": 2.9028,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 139742550687744.0,
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": 0.0038429324530718824,
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": 2.9028,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.002956101886978371,
72
+ "grad_norm": 5.219675540924072,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.5896,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.002956101886978371,
79
+ "eval_loss": 2.277921199798584,
80
+ "eval_runtime": 81.8017,
81
+ "eval_samples_per_second": 52.236,
82
+ "eval_steps_per_second": 26.124,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0034487855348081,
87
+ "grad_norm": 4.284224987030029,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.2228,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 209185167900672.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null