havinash-ai commited on
Commit
137259d
·
verified ·
1 Parent(s): bffc072

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ec10ea63bbc7f60d7a55d56d76b2ed44e6cd758b49bf79ced40ff16984d2b94
3
  size 556856304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1908db1fbbf9a741c78b0254137ff3fc3df72de3e1ee046a72f6fd7f3a4cb972
3
  size 556856304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b5dea273525115b1f3c9e9adc484d25289d1f2eb7f2940764c924fd533399bc
3
  size 21599060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b7fd0e40c1fa9f95ce4ceb2713c7603f52031fff85e34a7ea6e70c65a31c92
3
  size 21599060
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f22ee2bd42680b5f198191658fb24f22c66fd0968ab26c6e7ce687248687a73
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5adca46d5768b2528d11214bf50c169d41422785e8b729921c5399a7fed5df
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.06842105263157895,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 59.298,
61
  "eval_steps_per_second": 29.649,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 2546502362726400.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.08771929824561403,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 59.298,
61
  "eval_steps_per_second": 29.649,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.07017543859649122,
66
+ "grad_norm": 6.831262588500977,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 6.7491,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.08771929824561403,
73
+ "grad_norm": 6.219384670257568,
74
+ "learning_rate": 0.0,
75
+ "loss": 6.3964,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 3264746618880000.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null