duyphu commited on
Commit
1dd535f
·
verified ·
1 Parent(s): 7549c10

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:d30d26407626d20c85e45e0d07e586b8d7bd417756db4f6f64ac6dd47b687963
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52efa5693197c6bddb7732fca8a6fab9b915bb3cb5f98a86059492498037a65c
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:407c65b743768aa1f1c133e87c9da8e69c27559f32277ff756bad0868db09767
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dce1791a001dea4fbaddd5262eb11d319910e00bad6a4c157e4090d4b0b3d09
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd29364c179bbae80a4e5f5a5c20d5c32ab12b18ea0b2becd6f8e4dd05b25d8d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad126059eda90deccd7392c4c88acf9f2b706ce7fbf93830d8a6d7c95e06c329
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": 0.028618602091359385,
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": 0.05,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 760981135294464.0,
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": 0.04292790313703908,
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": 0.05,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.03302146395156852,
72
+ "grad_norm": 0.31124940514564514,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.026,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.03302146395156852,
79
+ "eval_loss": 0.02826586551964283,
80
+ "eval_runtime": 12.3902,
81
+ "eval_samples_per_second": 30.912,
82
+ "eval_steps_per_second": 15.496,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03852504127682994,
87
+ "grad_norm": 0.21600860357284546,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.0187,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1138274303213568.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null