chauhoang commited on
Commit
d28f5b7
·
verified ·
1 Parent(s): a9d373e

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:ef6be86c707c2a119e2ddfa73526b75cc1a9690df6abe1acd1c4a8105888165b
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b33f0f228f24044e43e630a6f94634dad2c81ecb1db5a633f82fba0f0f52168f
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9786ab22013ce6f9f79a23ff8d5e45898152d73677fc87bacd57cfb44941bc29
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80625ad023d9a13dd77741126dc71e2dcb4053ea1c0920af84394cfabd8ca388
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:201527dc5436b602bc077fa95c944d5e44b446fb1b94eaa7be329ca1d114a83e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf1e54b729d67edae87b3d70f2e3e9f9a68fdbea26ad403a1d59aac4c85ed34
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": 0.02234156820622986,
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": 1.8,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 3341698309816320.0,
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": 0.03351235230934479,
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": 1.8,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.02577873254564984,
72
+ "grad_norm": 0.2129242718219757,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.6974,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.02577873254564984,
79
+ "eval_loss": 1.6400848627090454,
80
+ "eval_runtime": 27.5053,
81
+ "eval_samples_per_second": 17.815,
82
+ "eval_steps_per_second": 8.907,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03007518796992481,
87
+ "grad_norm": 0.22697673738002777,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.6973,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 5166306589409280.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null