tuanna08go commited on
Commit
41f9b5d
·
verified ·
1 Parent(s): 5a837d9

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:e211a2a99f2232c0bd337c489dd10ece16be41a6ab36a32d6dfafc6e747398ca
3
  size 608249904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4885f8d9a8e52b4aaf09186d8e4680f94687f09fa84f199cabfd7ff2c4973655
3
  size 608249904
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43d8d7a052003f9a9fc4f703938d5c399ee65c4b433cfeb88f11c23e2d312e6f
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3969363bb474a641e1072eeca5c61ac3328d6a3631885aabeeb2606e019f1a
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
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": 0.0033068362480127185,
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": 0.6094,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9113888121421824.0,
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": 0.004960254372019078,
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": 0.6094,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0038155802861685214,
72
+ "grad_norm": 0.721843957901001,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.5875,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0038155802861685214,
79
+ "eval_loss": 0.5959174036979675,
80
+ "eval_runtime": 608.9676,
81
+ "eval_samples_per_second": 5.437,
82
+ "eval_steps_per_second": 2.719,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.004451510333863275,
87
+ "grad_norm": 0.6827080845832825,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.5832,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3670832182132736e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null