tuanna08go commited on
Commit
664d874
·
verified ·
1 Parent(s): cbcfac2

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:ddaa10b9c13cbeafbcfcc7d6229d4c829e01ce078f6f444164a984db91625998
3
  size 1134088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92547d07e97061169823acf095a4339feef4b9dbee81aa2d6c3d611b22ecd0be
3
  size 1134088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5c4e5eda47d679d6cdbc060262ce802ac0bffa029421002bc9aac5ba451b62e
3
  size 608186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85bd2e222b826bbda801bcb676e9473d5d426d83902035b3ffd3aed041a38d1
3
  size 608186
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:970692caa867a85ad5143a11673c0a1eafd0aaa61e02122a9a1ea48f567151af
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7233f71eef067dfb5212372f77526d42bc1aa4c08c35396591f7298fbe303574
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": 0.01030417120776776,
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": 6.8991,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 27946785964032.0,
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": 0.01545625681165164,
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": 6.8991,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.011889428316655107,
72
+ "grad_norm": 14.197517395019531,
73
+ "learning_rate": 5e-05,
74
+ "loss": 5.9194,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.011889428316655107,
79
+ "eval_loss": 5.657083988189697,
80
+ "eval_runtime": 4.8044,
81
+ "eval_samples_per_second": 221.256,
82
+ "eval_steps_per_second": 110.732,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.013870999702764291,
87
+ "grad_norm": 13.543628692626953,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 5.2658,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 41920178946048.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null