jssky commited on
Commit
a94b10f
·
verified ·
1 Parent(s): c755e3e

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 sha256:1b81a68fc81c77ce7f6932364307582494a0d9e880b5b651108c428526825884
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d634f504e770a835852ee9ebf936c0c0121a545633f9264b1fed89216739b2d3
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50bcae4ea3c75f1ba4eb2bc13d3fa8ebbc7fec7f3f165af5cb0a2593f2167170
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f6f8a9d55631166f179ae6339a6ccd80e5390c625e0defecde6b9316c35bbd
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
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": 0.005156854318865492,
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": 4.794,
74
  "eval_steps_per_second": 4.794,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4451323701362688.0,
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": 0.007735281478298238,
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": 4.794,
74
  "eval_steps_per_second": 4.794,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006016330038676407,
79
+ "grad_norm": 4.985762119293213,
80
+ "learning_rate": 0.00012,
81
+ "loss": 3.5523,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.006875805758487323,
86
+ "grad_norm": 5.663036823272705,
87
+ "learning_rate": 0.00014,
88
+ "loss": 3.8084,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.007735281478298238,
93
+ "grad_norm": 5.977775573730469,
94
+ "learning_rate": 0.00016,
95
+ "loss": 2.787,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.007735281478298238,
100
+ "eval_loss": 2.5680861473083496,
101
+ "eval_runtime": 51.2453,
102
+ "eval_samples_per_second": 4.781,
103
+ "eval_steps_per_second": 4.781,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6676985552044032.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null