great0001 commited on
Commit
5368b89
·
verified ·
1 Parent(s): 71c918b

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 sha256:3f03120207eaa765b900e1a703b34cd94bce64de20a13054e99699a28602e689
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfac929da93260c9db8432d1804e3040cf64af3dd5538f26ae16bfab6e79f19f
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bda7077529b296a6f09c10913bd901bbbfd0e13949c7fccd18f01024381bca2
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f685eed4f71d44abb56b75509797e9dcad4afbdcd6249f9a9ebb748c30f8224
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": 0.0034139402560455193,
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": 15.396,
74
  "eval_steps_per_second": 7.698,
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": 0.005120910384068279,
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": 15.396,
74
  "eval_steps_per_second": 7.698,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.003982930298719772,
79
+ "grad_norm": 0.8321022391319275,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.6618,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004551920341394026,
86
+ "grad_norm": 1.18330717086792,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.6162,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.005120910384068279,
93
+ "grad_norm": 1.5175787210464478,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.4511,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.005120910384068279,
100
+ "eval_loss": 1.5452752113342285,
101
+ "eval_runtime": 48.0543,
102
+ "eval_samples_per_second": 15.399,
103
+ "eval_steps_per_second": 7.7,
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