Best000 commited on
Commit
8771355
·
verified ·
1 Parent(s): cdc6265

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 sha256:8ea1383aa6972f950a496bbf127ae3c176a695185d404c17bb87a32f44442f7b
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5db564ea82da4535ae56dfbd0a6ef11487fde523b1e10a9cca0df7fd7ba11cd
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2af92d072fbbb7f76c05ab9fc41518bc10498cd0de1dae24e1ac690438d36f3f
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51e6829e6327205f75068c68534f944b3a44fb89c60b113e4eba1067ae5556f
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2c7b6cb315312c6c82b23cb21e455823073a3e69e8631d21018c71ee2b3e5c9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5588aff3cee8219990dfadcaebed17215cc4ab404606e462a877fa96227e0f0
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": 0.006188757091284167,
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": 15.145,
74
  "eval_steps_per_second": 7.591,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2293222971801600.0,
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": 0.009283135636926251,
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": 15.145,
74
  "eval_steps_per_second": 7.591,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.007220216606498195,
79
+ "grad_norm": 2.2471773624420166,
80
+ "learning_rate": 0.00014,
81
+ "loss": 9.3809,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.008251676121712223,
86
+ "grad_norm": 1.7351436614990234,
87
+ "learning_rate": 0.00016,
88
+ "loss": 8.6866,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.009283135636926251,
93
+ "grad_norm": 2.199270248413086,
94
+ "learning_rate": 0.00018,
95
+ "loss": 9.6241,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.009283135636926251,
100
+ "eval_loss": 2.258143424987793,
101
+ "eval_runtime": 27.0241,
102
+ "eval_samples_per_second": 15.135,
103
+ "eval_steps_per_second": 7.586,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3312433181491200.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null