lesso commited on
Commit
99c6b98
·
verified ·
1 Parent(s): 96afa7a

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 sha256:82268eb4ebc284da022ba2a9876cc8ca39128b9fb076a2ff162338b619ffedb7
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:880f638dd69be5eeef21502dc379ee8776c713240bb60196607bde85a7f1224c
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a712b99c069e5d84e2999ce04a3787ef3a8c95f730e89e8e74262bdde18bc9ca
3
  size 160172858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a54fe0c70409214e22dca0d5e80dc0e911fc2a1cf038b9987c6cf7dfea81bb2
3
  size 160172858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
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": 0.0026414263702399295,
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": 14.956,
74
  "eval_steps_per_second": 14.956,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 985898535616512.0,
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": 0.003962139555359894,
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": 14.956,
74
  "eval_steps_per_second": 14.956,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0030816640986132513,
79
+ "grad_norm": 6.760335922241211,
80
+ "learning_rate": 0.00012,
81
+ "loss": 11.4293,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0035219018269865726,
86
+ "grad_norm": 10.758153915405273,
87
+ "learning_rate": 0.00014,
88
+ "loss": 12.74,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.003962139555359894,
93
+ "grad_norm": 11.617557525634766,
94
+ "learning_rate": 0.00016,
95
+ "loss": 10.8383,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.003962139555359894,
100
+ "eval_loss": 10.073469161987305,
101
+ "eval_runtime": 32.1815,
102
+ "eval_samples_per_second": 14.884,
103
+ "eval_steps_per_second": 14.884,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1478847803424768.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null