robiulawaldev commited on
Commit
49ce875
·
verified ·
1 Parent(s): 19a30ad

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 sha256:74da00eef20da90360dbdf82b0100a44a98e8ba4a3ad4d754b0d6f5983b2cb32
3
  size 247944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ec8d78ecf673ccd569de960aeefb8c7de352f69b6d2b2632165e1516469a99
3
  size 247944
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0abe9372aab9600296cb01c6219bef6cdd7237b2da403766888872a6f82daf4
3
  size 263088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f7b8f2da3b44f4138669d505b41d2d7c7654d6cc7ce6c59e5524b432aec9b7
3
  size 263088
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f537d6df07787c716bf4621ea221744763bd88e92a07f95d1fa6f6a06d8ac757
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a016715ccb0112ab1394743f94acfb298ac9ccf9cd4cd745ca6d3b1bffe35a3
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": 0.014544098452358755,
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": 307.067,
61
  "eval_steps_per_second": 153.805,
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": 405591293952.0,
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": 0.018646280067126608,
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": 307.067,
61
  "eval_steps_per_second": 153.805,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.014917024053701287,
66
+ "grad_norm": 0.9695378541946411,
67
+ "learning_rate": 0.0002,
68
+ "loss": 21.7057,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.018646280067126608,
73
+ "grad_norm": 0.8949954509735107,
74
+ "learning_rate": 0.0002,
75
+ "loss": 21.6144,
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": 519988838400.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null