Nexspear commited on
Commit
04ab955
·
verified ·
1 Parent(s): 1a95317

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31539a5a1f7dda4fab1abcdb9b775debd59ef2561686887b51994ec3efa2e098
3
  size 161533192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9f4b836c02afd7ed1c180ab6cce99bb10b41d1924ff812d5a431150f649e0f
3
  size 161533192
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64811813c09aa6a760f8f9e92ea533b6d2f48f77b2f3c242ea17a9585ac21b0e
3
  size 82460660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df86b5cb7ff5258ef8eebaa3e2bd8cf5c49f0c219eef989ba0db413622b6b185
3
  size 82460660
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cec08ca8ab09a6c6d779705e9f4bbbbe31cf5639aa8f66d53f3a7cc9aab1120d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6191367ab70dbb5534bf3c80f01e5a4ca78e25ec0c46e08a50a21a04fffcc593
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.008779417144250701,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 12.156,
74
  "eval_steps_per_second": 1.521,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2.796154773307392e+16,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.013169125716376053,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 12.156,
74
  "eval_steps_per_second": 1.521,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.010242653334959152,
79
+ "grad_norm": 0.4993043541908264,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 0.8698,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.011705889525667602,
86
+ "grad_norm": 0.4442359507083893,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 0.6909,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.013169125716376053,
93
+ "grad_norm": 0.4680705666542053,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 0.8662,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.013169125716376053,
100
+ "eval_loss": 0.8155685067176819,
101
+ "eval_runtime": 284.0968,
102
+ "eval_samples_per_second": 12.154,
103
+ "eval_steps_per_second": 1.521,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 4.299087963960115e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null