kk-aivio commited on
Commit
89f9299
·
verified ·
1 Parent(s): 9879dc0

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 sha256:14d03aa7e33f46459ad8720c7eae0022caa17b0c099a5591e39b2e175b4e8a58
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778a10559c75f015d97e0aeb1fb2d865e6b2faead12ed5f60b05418efd3a36e2
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b0364f2d5d6c24ab0f435ad23e715a8be206f07bf0912ceb4b8e45cf6267098
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904eb5fc15de91ca0b4250de4b582fab81ceb5fe913c94454712fda358c88251
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7df84a2b73072e596576ed6a8ed3d1cfbd3c26c96d47bd7bdb99c207da369cac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80fb7161d4da5bbf7bc9c5055262ee3d254b042afaaa8c198be2625faf46c77b
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": 0.005038841066554693,
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": 15.922,
74
  "eval_steps_per_second": 7.961,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2293309699522560.0,
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": 0.007558261599832038,
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": 15.922,
74
  "eval_steps_per_second": 7.961,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.005878647910980474,
79
+ "grad_norm": 0.6797656416893005,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.7593,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.006718454755406256,
86
+ "grad_norm": 0.7729480862617493,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.7399,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.007558261599832038,
93
+ "grad_norm": 0.8539050817489624,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.6934,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.007558261599832038,
100
+ "eval_loss": 0.6700757741928101,
101
+ "eval_runtime": 31.4993,
102
+ "eval_samples_per_second": 15.937,
103
+ "eval_steps_per_second": 7.968,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3439964549283840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null