chauhoang commited on
Commit
3046de2
·
verified ·
1 Parent(s): 0740bc5

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 sha256:98ef3e1109c96e3acdea8addd0db21102ed5f5a100979721707e353056717eba
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0989175c75d0d3bdbed9d424fae37c1d537025130c008e7b1705772fb8f3784d
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26d589b43b55ad096a93f76be3f1a4c12aa7babc9440ad05294bbcaa227a8c60
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f759d44808e8c5480f15a281b1b9cbab047f854e422104a5d187c4732b4abbb
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a997aa8bfab00a35d7cfa486126e3d295d226a899068a295415cfc8e8058a7c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551c6190aa7460da0f5f87f766f1e262863111d15319ee98d5b09ac189feeb2f
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": 0.042939719240297276,
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": 2.6728,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 665059143450624.0,
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": 0.06440957886044592,
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": 2.6728,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0495458298926507,
72
+ "grad_norm": 1.4843695163726807,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.368,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0495458298926507,
79
+ "eval_loss": 2.1857614517211914,
80
+ "eval_runtime": 7.9481,
81
+ "eval_samples_per_second": 32.083,
82
+ "eval_steps_per_second": 16.105,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.057803468208092484,
87
+ "grad_norm": 1.5671559572219849,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.0396,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 997588715175936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null