auxyus commited on
Commit
be518db
·
verified ·
1 Parent(s): 89a7c8b

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:c1fe0479153ce92d40972792ba369e86604b90c69eb28cd23aba4bec076f34f1
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e180431901e1ce634b774363f43e832c57d1af94eb43193c1d3326e1046d5e
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94d328a4c2d27269f1f8c0d79e0278e224c98baf81a938f349f3cc9b4efe5be8
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c745f53dba14c5841ad408ba7f0df2f35e551bf11db41194c987ce4622d2c46
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26cf808e73e6140e5ecde31f80b68f89a7834cc9c3708999fb97dd64e6dd848f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0157d26a6c9880b1ce48a0bee6735b6a2e075272af9c2ec140c34f306deed1f1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
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": 0.01011804384485666,
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": 18.207,
74
  "eval_steps_per_second": 2.278,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 9405135625125888.0,
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": 0.01517706576728499,
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": 18.207,
74
  "eval_steps_per_second": 2.278,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.011804384485666104,
79
+ "grad_norm": 0.1957426816225052,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 0.7759,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.013490725126475547,
86
+ "grad_norm": 0.1535039246082306,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 0.7502,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.01517706576728499,
93
+ "grad_norm": 0.15373417735099792,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 0.7894,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.01517706576728499,
100
+ "eval_loss": 0.7679686546325684,
101
+ "eval_runtime": 164.638,
102
+ "eval_samples_per_second": 18.204,
103
+ "eval_steps_per_second": 2.278,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1.4107703437688832e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null