trenden commited on
Commit
3d783d7
·
verified ·
1 Parent(s): c3abf03

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:fa17b6750abed3869b7c55b698a8c86aa214ebbe45fd1c4d8bdeb6837f989b33
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ec50603644d698035557d55e91532b34b1e4bd21a00d5652f1303db38b6d37
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b682ce08bc14065df5c5af2d4180bf77611d765940aaf8eb829113453e8dce77
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93bc6a769233b0d772dffb5c6f27524089d4ee8837a654b6528513a22f7f2e2c
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e83968c2d0fcbd9ce3decdbd850180096a3c3813ec3f1e2e7fbcdcb1b335e3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487921a1acd258b82e58b9ec98a7bf8fbb6715ade97fa26c5f93634426742553
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": 0.000975371860521824,
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": 37.313,
74
  "eval_steps_per_second": 18.664,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 979486818435072.0,
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": 0.001463057790782736,
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": 37.313,
74
  "eval_steps_per_second": 18.664,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0011379338372754612,
79
+ "grad_norm": 2.6334381103515625,
80
+ "learning_rate": 0.00014,
81
+ "loss": 8.1998,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0013004958140290985,
86
+ "grad_norm": 2.1267759799957275,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.1844,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.001463057790782736,
93
+ "grad_norm": 2.1368281841278076,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.9146,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.001463057790782736,
100
+ "eval_loss": 1.9331262111663818,
101
+ "eval_runtime": 69.4231,
102
+ "eval_samples_per_second": 37.322,
103
+ "eval_steps_per_second": 18.668,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1469230227652608.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null