duyphu commited on
Commit
3a3eabe
·
verified ·
1 Parent(s): 1d1919d

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 sha256:553acc9f9cdcb7da52a46a5e00562faa2ac995a5cf3cf16d04c90c42ad100e0d
3
  size 25192496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36f6aa2398273b62e32dbfb00c601589fb41011e537464526cad6b1128a5622
3
  size 25192496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd51d1c37adda1c0e8e7f699782dd23d85ce18b3237e961696b91091996133c
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7838ecba53a53b93d1f5261f87ade720bac5032b8af700146d668ec499f7c46f
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65b58d2aad375fd1e2e4ce0c4b4d0a807fc7033ff7f4547cfdac637b84364c9f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90384182705d69a10eb7aa26085504559145f0c755cd85f72c0a72716a70220f
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": 0.00421274354923644,
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": 5.428,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 850931251937280.0,
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": 0.00631911532385466,
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": 5.428,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.004860857941426662,
72
+ "grad_norm": 2.8310935497283936,
73
+ "learning_rate": 5e-05,
74
+ "loss": 4.559,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.004860857941426662,
79
+ "eval_loss": 1.3071575164794922,
80
+ "eval_runtime": 72.0775,
81
+ "eval_samples_per_second": 36.058,
82
+ "eval_steps_per_second": 18.036,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005671000931664439,
87
+ "grad_norm": 3.963855028152466,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 5.45,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1291325496360960.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null