robiulawaldev commited on
Commit
644723d
·
verified ·
1 Parent(s): bfc0b62

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 sha256:4dbe90ce024061665532ca13307215f5e517880b4ee0fb931d90cb33392a37e7
3
  size 315888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd2693f18e2a2efb86d832ee39f8950b76cba497396dde19ec34aa13e9dfb90
3
  size 315888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0328076d600bc588b447c05c10cd28862ef9b13b05ca70396836724f982264ae
3
  size 450264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5166cf2ca79c29b1215a58f52f24da4bf0cb724b24a429205b2258628dc06830
3
  size 450264
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c0c0336914a0c44d806ff704a7a21ab4f87333bc1ad2180cf0128310cdd7c33
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ce8e81a10f7fbe90c4210a20e4ef5650ef4396562aa75f81b8b92bce23f6b1
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": 0.004622241787266825,
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": 398.221,
68
  "eval_steps_per_second": 199.214,
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": 1878046801920.0,
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": 0.006052935673801794,
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": 398.221,
68
  "eval_steps_per_second": 199.214,
69
  "step": 42
70
+ },
71
+ {
72
+ "epoch": 0.005502668794365267,
73
+ "grad_norm": 0.4459260106086731,
74
+ "learning_rate": 0.0002,
75
+ "loss": 10.6161,
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": 2462328029184.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null