robiulawaldev commited on
Commit
5af6bc0
·
verified ·
1 Parent(s): afcd2c8

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:d931e2247811a7f61b3873d96c7d58c935081777e367920926ae08b439db9ef3
3
  size 166182480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8193ffe7bb320a7ec150209f501feda4d0bd0c4c827eb56c2b6cf38eeb8359
3
  size 166182480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7fc3eaebaa9b1c0929c320bc04e328edfeae9d4df6b13baa33dd6eb18cb93fa
3
  size 84792708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:886b7f2f5a8f228e6f14582ad06f7b1fb0ef771a6a7fbc7292fa1c875919a39e
3
  size 84792708
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6171317cf8e717851dec53300293d0446c6f44360527b412c9609232fc44066f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b778996118ec1e7678c689be9b0bcad4d9492f4c959afff3821ec9fd45bb9617
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": 0.00036349909824262165,
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": 29.337,
61
  "eval_steps_per_second": 14.669,
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": 1548645961826304.0,
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": 0.00046602448492643803,
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": 29.337,
61
  "eval_steps_per_second": 14.669,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.00037281958794115045,
66
+ "grad_norm": 1.4730262756347656,
67
+ "learning_rate": 0.0002,
68
+ "loss": 2.067,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.00046602448492643803,
73
+ "grad_norm": 1.2356326580047607,
74
+ "learning_rate": 0.0002,
75
+ "loss": 2.0745,
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": 1954848181321728.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null