chauhoang commited on
Commit
1cc26ec
·
verified ·
1 Parent(s): 82b135c

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:b5f38e134dc206774ce1d9317ee743cbd60fe8866ff6cd49b5221202e0b03db6
3
  size 32856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75b70b76f1aec56b74984bf133b73dffe581c2de3ce1ef11ce02272bd0a8838
3
  size 32856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1293ab8adaf11431079c5f9602906657ec065906eeabd6fee72dcf40bedb9ccc
3
  size 71358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963d868253b73bdf6c931559833bbd00790142e541e54fe267f9933de898efdd
3
  size 71358
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
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": 0.04567413263065437,
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": 44.3135,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 23533977600.0,
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": 0.06851119894598155,
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": 44.3135,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.052700922266139656,
72
+ "grad_norm": 0.4921723008155823,
73
+ "learning_rate": 5e-05,
74
+ "loss": 44.2984,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.052700922266139656,
79
+ "eval_loss": 11.075677871704102,
80
+ "eval_runtime": 1.5009,
81
+ "eval_samples_per_second": 159.903,
82
+ "eval_steps_per_second": 79.951,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.061484409310496264,
87
+ "grad_norm": 0.43915820121765137,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 44.3019,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 34927411200.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null