phungkhaccuong commited on
Commit
0237686
·
verified ·
1 Parent(s): 482c9e0

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:a2e4a4da8afdcbdc0961caaccf0b13a4be9f030dd95181e1ac54c2c9905a5d72
3
  size 30026872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8ca26ac84f31eb3e10d7cb1a5a1172ff9ef0879255e66931100eac461270bb
3
  size 30026872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa29873b70976ba05383b4314b0440def161f3842c0a1f739edc5803a8f1b649
3
  size 15611412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab52c60e4970aee8e83795050e478a9b66afacece224eb202b42707cff1153b
3
  size 15611412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4899205b88a06715915110bb1166b71e0049d68043762a00a5883f00debe981e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10177ba4b0cfe4bef6f12698f94fbc66659931101eb6a166445976be8cd0bf0d
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": 0.00036061901641163275,
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": 0.042,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 830516546764800.0,
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": 0.0005409285246174491,
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": 0.042,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.00041609886509034544,
72
+ "grad_norm": 0.2505738139152527,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.0624,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.00041609886509034544,
79
+ "eval_loss": 0.03364470601081848,
80
+ "eval_runtime": 1002.5128,
81
+ "eval_samples_per_second": 30.282,
82
+ "eval_steps_per_second": 15.141,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0004854486759387364,
87
+ "grad_norm": 0.33506065607070923,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.0356,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1265549023641600.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null