duyphu commited on
Commit
3e0a8de
·
verified ·
1 Parent(s): e287c9e

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 sha256:8c1dc18906179a12ed0c3b1a3ed21ed1b2327cdb2d797fd9aacbf9cf8edc724a
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e6ddaf11da8a9da6f7c907ad6f64b6354fb52b72e0f14141127c5bbdd92717
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64ad16e7c66ef8a8876f311781fb728d9104a5678baacb211cfd6067723240ee
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e79cac7be291f93ad869b2e3d82925b2e242254e3b6096c0a11e7e8ed4fb78
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85e13fa025c9a824f965c7766c9716c9550812a29eb06c59107269912ce31e69
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4354521c2092ad7a21b56230fbe72d6846ab1c72092965f7eb5cebfbbf30a51
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": 0.0008055957923112078,
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": 1.0445,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8445092482252800.0,
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": 0.0012083936884668119,
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": 1.0445,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0009295336065129322,
72
+ "grad_norm": 0.33603912591934204,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.9271,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0009295336065129322,
79
+ "eval_loss": 0.9617733359336853,
80
+ "eval_runtime": 1465.4277,
81
+ "eval_samples_per_second": 9.274,
82
+ "eval_steps_per_second": 4.637,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0010844558742650874,
87
+ "grad_norm": 0.29064711928367615,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.9954,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.268823650992128e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null