chauhoang commited on
Commit
576211c
·
verified ·
1 Parent(s): e486c33

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 sha256:896ce4bd36c19e9db1888e0f8765a2fd98edb11784b4ea83ddb0995efbe6aece
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d14bcce38aede51387cf640be849365192e77b53302ae61a760936a8b3513a
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7680d30a7b7ec0b4bfbdc577e921c2737b441378f65b56ad5f73df19051d28e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84f91fc46d9b8d4c7c61d241568651136786a38a7e0557b99d4a5c1f6d432d1
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1745effe6c36a594072b7b0bb75cfc3c020c1509f0abfe1f2db48370590cfc9b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a14c9deb8ff4708c2ea491fb60635316be958194c4fe145c894226a400011fc
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": 0.009855951478392721,
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": 2.8186,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5363736319623168.0,
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": 0.014783927217589083,
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": 2.8186,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.011372251705837756,
72
+ "grad_norm": 0.9212977290153503,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.7789,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.011372251705837756,
79
+ "eval_loss": 2.736600160598755,
80
+ "eval_runtime": 84.609,
81
+ "eval_samples_per_second": 13.131,
82
+ "eval_steps_per_second": 6.571,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.013267626990144048,
87
+ "grad_norm": 0.6569848656654358,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.731,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7999365373231104.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null