kk-aivio commited on
Commit
25e38b5
·
verified ·
1 Parent(s): 3bf0ec4

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 sha256:0094a4b86c3c6d70326ddedcb9b8bb7afa0768c56d2ec69af9234e048938a356
3
  size 1579352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510379b32e19db4e6757807083c49b7c2b65510101005ccf010c1cbf5239fbfa
3
  size 1579352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ad30d644254afa08b08215e02c311915ca3a06e7e6fe6e86985df808708d8f0
3
  size 857338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fffd611f6cb9a5b4473f60760c6ff4e8a260472bcf99d3501ab2d174690f43f
3
  size 857338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03d057dd57daf31a4f83fa1f977b30587086adcd472d02db30db1ae091bd8ff0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db79c5cc5439263656db6134fa199281305040d42833f95cc5ecf73b101d7d07
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": 0.00581254541051102,
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": 227.86,
74
  "eval_steps_per_second": 114.192,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 6644985495552.0,
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": 0.00871881811576653,
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": 227.86,
74
  "eval_steps_per_second": 114.192,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006781302978929523,
79
+ "grad_norm": 2108.6474609375,
80
+ "learning_rate": 0.00014,
81
+ "loss": 84.6611,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.007750060547348026,
86
+ "grad_norm": 4211.90576171875,
87
+ "learning_rate": 0.00016,
88
+ "loss": 81.414,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00871881811576653,
93
+ "grad_norm": 1921.15087890625,
94
+ "learning_rate": 0.00018,
95
+ "loss": 72.7033,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00871881811576653,
100
+ "eval_loss": 19.256641387939453,
101
+ "eval_runtime": 1.9014,
102
+ "eval_samples_per_second": 228.78,
103
+ "eval_steps_per_second": 114.653,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 9967478243328.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null