tuanna08go commited on
Commit
d0eae6a
·
verified ·
1 Parent(s): 734b279

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 sha256:9a3197404f67468ba81c6c25b3eecba21553d3d8cfd6c5534e3858c724fb1790
3
  size 114106856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb4246a3121934a3acc170369a219224fb3d6c35d30e72783075873c1e94ffc
3
  size 114106856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd4d097d7151eaa3e174a1d3f4358fa25a2972556767b94039f534de025ec044
3
  size 58562260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d3fc246afbfd72d4a51ba6898781e1da3416c7abb2c322f8231bdb16e39f53d
3
  size 58562260
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e9aef3c3f0d0ca9b6753984b0e3cb1d491c0785e4bc59a629365d175765fbff
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2556a93e19ae846c23294d8d1538c98306480c21d3cb7a74daeea73db340a640
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": 0.0015829046299960427,
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": 0.9073,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7415445502033920.0,
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": 0.002374356944994064,
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": 0.9073,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0018264284192262032,
72
+ "grad_norm": 23.289958953857422,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.6673,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0018264284192262032,
79
+ "eval_loss": 0.07907278090715408,
80
+ "eval_runtime": 658.9663,
81
+ "eval_samples_per_second": 10.495,
82
+ "eval_steps_per_second": 5.248,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002130833155763904,
87
+ "grad_norm": 13.350411415100098,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.3659,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.112316825305088e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null