jssky commited on
Commit
3c71e47
·
verified ·
1 Parent(s): 6d7a087

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:bfe31788b275852562bd680de0a1d15cadea9cbfce95896527c5eea4807a10f0
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa06f15067e60ffb71e6222feefac00a4d7d896808e5d23087a70aded7477fd
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aa2b1ec616e0c34c16de9d9cdcd95fa82b88f9475c929a9d9c28403c1f10aa6
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c56abdbecd3037c153038b30e118aeee3295260b1b273009a029f0f20d4a81
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c360d3fd521981afbe1dfe0d527be160f7b375ae97bb2c2e2d4d7405b0da8608
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ae472d02b3de5b61691bbbd328158341b9b01fb8bb042f73ebc115b2c91abda
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.2823529411764706,
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": 1.878,
74
  "eval_steps_per_second": 1.878,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4451323701362688.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.4235294117647059,
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": 1.878,
74
  "eval_steps_per_second": 1.878,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.32941176470588235,
79
+ "grad_norm": 3.698115110397339,
80
+ "learning_rate": 0.00012,
81
+ "loss": 3.7312,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.3764705882352941,
86
+ "grad_norm": 4.615599155426025,
87
+ "learning_rate": 0.00014,
88
+ "loss": 4.2832,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.4235294117647059,
93
+ "grad_norm": 5.853390693664551,
94
+ "learning_rate": 0.00016,
95
+ "loss": 3.3254,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.4235294117647059,
100
+ "eval_loss": 4.819329261779785,
101
+ "eval_runtime": 2.6673,
102
+ "eval_samples_per_second": 1.875,
103
+ "eval_steps_per_second": 1.875,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6676985552044032.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null