great0001 commited on
Commit
48cf2fa
·
verified ·
1 Parent(s): d3d9ef0

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76a47f57630222a166b640a22c97d102f80fb54cdda7cac8fe2b2008266df26a
3
  size 161714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1842f11bec02470d23c8a947bab1e284a82c32aada6f42e5deae32f43447861c
3
  size 161714
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34aa9db8a7c59065543044b85f2881acca3fc3ad794c5c83ed7fb57bcb2ee721
3
  size 64750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea021b1d71a58bfbf7931a05a36b8419823a08fb80f1d77cdc04957bd463363
3
  size 64750
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:399f12128758c20f45f058a67599e1b9a2d9cd495e1ccd71687a907821c8d121
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49593839f9d1f47c098855c411ae242b6ae0da44eb823919bbad1cbb6de79de6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0005657842004762017,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 422.477,
74
  "eval_steps_per_second": 211.239,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 10876225536.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0008486763007143026,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 422.477,
74
  "eval_steps_per_second": 211.239,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0006600815672222353,
79
+ "grad_norm": 0.08790659159421921,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.94,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0007543789339682689,
86
+ "grad_norm": 0.09065890312194824,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.9344,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0008486763007143026,
93
+ "grad_norm": 0.1054435595870018,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.9351,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0008486763007143026,
100
+ "eval_loss": 6.9367523193359375,
101
+ "eval_runtime": 10.4428,
102
+ "eval_samples_per_second": 427.662,
103
+ "eval_steps_per_second": 213.831,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 16479129600.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null