robiulawaldev commited on
Commit
533a9d5
·
verified ·
1 Parent(s): 6a9f446

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:e5063a001b64180853b6055a10a64f96ef75aec95dd9f63195513e9aa7f83c9f
3
  size 209760536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11d23db594e4e809b5b2432c2fd2ae3ae30bfd6c8cb495b063ba1dbcfca9e90
3
  size 209760536
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:494793742b1191c28e0b84e4347890d06ad377a4e848a34fa55041077873e561
3
  size 106872596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e62ea043b72d8d7f5288c012fddb737d1e9d45e2a4fed28047714fcda7cc8194
3
  size 106872596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d06ee601a01d7be96561dd714084a421148fc0e23b021599d7a454e45b23b06
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c3aee2d0e98677c9fb67d2c1d0d57e6c1932e22326e7c179d6d42989e8b2bd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
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": 0.018258426966292134,
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": 23.826,
61
  "eval_steps_per_second": 11.913,
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": 6601911922851840.0,
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": 0.023408239700374533,
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": 23.826,
61
  "eval_steps_per_second": 11.913,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.018726591760299626,
66
+ "grad_norm": 3.9279940128326416,
67
+ "learning_rate": 0.0002,
68
+ "loss": 2.8988,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.023408239700374533,
73
+ "grad_norm": 4.066625118255615,
74
+ "learning_rate": 0.0002,
75
+ "loss": 2.9791,
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": 8645360851353600.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null