tuanna08go commited on
Commit
9a18116
·
verified ·
1 Parent(s): b3ef96d

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 sha256:423f9b882745e0a9ec74bbdbf9fb25a7268257af03310895a21f0ebeae44dcc3
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b731c15778727381cc2e7d5933fad8b42e9331217d02c203e30d7aa14fcb088c
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:711e5edd124de36d9cf7b6c8e5eacb0cac6a31d9356f01a159cc9b68fd287bb1
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da374e66568fa19ab6e02a93c5cb75a239086dbf72603e4142fc99d625cec491
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:175fdf30b8c703f05d00042db9939bec57bbba272d0f4b5d546a8649ed6d732e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125724582db1a62dac8cbcb3104285de08f049398c980919acba95a3edd476e7
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": 0.00829743098771342,
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": 0.5891,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1310933888532480.0,
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": 0.01244614648157013,
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": 0.5891,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.009573958831977022,
72
+ "grad_norm": 0.1621832549571991,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.5783,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.009573958831977022,
79
+ "eval_loss": 0.5724042654037476,
80
+ "eval_runtime": 44.2025,
81
+ "eval_samples_per_second": 29.863,
82
+ "eval_steps_per_second": 14.931,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.011169618637306526,
87
+ "grad_norm": 0.13507747650146484,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.5216,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1975993031983104.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null