phungkhaccuong commited on
Commit
eee8277
·
verified ·
1 Parent(s): 8ec24c6

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:accc1d39d426e757618983ac9121c0083a5375257be7b9f22c2cf69f0f144f24
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4200c4461060a522df9d4b285543c59d6ad0ad62115b506d9eb517eedf1b70b
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3126f1b97ee2c2e2f26e720510f2cee0092ace840d159584189a7b4878a05ea
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1511b37df79bd00f1324c15f9d45123e0982fd6758b2deeea6dac424ed87924
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
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": 0.0005070672497940039,
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": 8.0305,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4556941443465216.0,
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": 0.0007606008746910059,
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": 8.0305,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005850775959161584,
72
+ "grad_norm": 22.63473892211914,
73
+ "learning_rate": 5e-05,
74
+ "loss": 7.9584,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005850775959161584,
79
+ "eval_loss": 1.8975735902786255,
80
+ "eval_runtime": 1354.7033,
81
+ "eval_samples_per_second": 15.937,
82
+ "eval_steps_per_second": 7.969,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0006825905285688514,
87
+ "grad_norm": 19.12643814086914,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 7.1474,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6835412165197824.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null