chauhoang commited on
Commit
3c610a6
·
verified ·
1 Parent(s): da34384

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:a3e20d7f0a36a24c594a3ce12cf066047bd260acc15a33bfb55ed773225a5e11
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb83edb4db37ae8fcf1897a79583502d24a84fb9170dd01a3da0dcc0a0eaf5e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89c404d66e9ab8e0bdf4e1592b9cf5ba00d849b7dd9978c3f2abd84cd4455d9b
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab52ec8eb1e1109ab9a9615408a7c91e3104306e6926209e3332f6b7f27d3d0
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b03e90faa1967f18f72061550dc7b793bd6230a686d92c6466c314f9d209bd4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4983d71e319f9e21c9711f39e1b30bc6171dbcb39df362b58f72f84be87098fd
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": 0.0007123921993054176,
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": 0.6941,
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": 0.0010685882989581264,
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": 0.6941,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0008219909991985587,
72
+ "grad_norm": 1.2582858800888062,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.6445,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0008219909991985587,
79
+ "eval_loss": 0.589572012424469,
80
+ "eval_runtime": 1036.876,
81
+ "eval_samples_per_second": 14.821,
82
+ "eval_steps_per_second": 7.411,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0009589894990649852,
87
+ "grad_norm": 1.1963167190551758,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.6821,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7352017886380032.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null