robiulawaldev commited on
Commit
25b1814
·
verified ·
1 Parent(s): 5b9d044

Training in progress, step 55, 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:d7f5935a67f281138b98a6927fad8aa2859ea7b8f182c3a42bb38661469d97d3
3
  size 500770656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c9dcb018e797ac6a369d7d064d8ddeaeede7f1e7e74bec29bf62c468937988b
3
  size 500770656
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f44db4c7fa1388ca9ba59c960d8a826f961285f8d35d4b56bf622a68ab27123
3
  size 254917780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3038bd7ab5fc634975b873ca94c9f4b04dd041becaf3f803b8108ac56a83d8aa
3
  size 254917780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33e02238a8e649454d4c26768a776fd2b8f8d5c5c9dba31e65b83f67a248c57b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6c26b78eb6cdfb60d1368c70e239cf81c5baf6c949ab17916393b298a782ed8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43352a0ea01b8f309df99bb65027960564fe5f2f452a04b8b6c955b0ecfed4cf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b16062161cca6c6d42c840fa02f9c59f431931479788fa87a822481c8e65827
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": 0.023986293546544833,
5
  "eval_steps": 14,
6
- "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -67,6 +67,13 @@
67
  "eval_samples_per_second": 17.224,
68
  "eval_steps_per_second": 8.635,
69
  "step": 42
 
 
 
 
 
 
 
70
  }
71
  ],
72
  "logging_steps": 10,
@@ -81,12 +88,12 @@
81
  "should_evaluate": false,
82
  "should_log": false,
83
  "should_save": true,
84
- "should_training_stop": false
85
  },
86
  "attributes": {}
87
  }
88
  },
89
- "total_flos": 7494846382080000.0,
90
  "train_batch_size": 2,
91
  "trial_name": null,
92
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03141062250142775,
5
  "eval_steps": 14,
6
+ "global_step": 55,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
67
  "eval_samples_per_second": 17.224,
68
  "eval_steps_per_second": 8.635,
69
  "step": 42
70
+ },
71
+ {
72
+ "epoch": 0.028555111364934323,
73
+ "grad_norm": 0.8667274117469788,
74
+ "learning_rate": 0.0002,
75
+ "loss": 0.9007,
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": 9807086223360000.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null