robiual-awal commited on
Commit
859eedf
·
verified ·
1 Parent(s): 272b814

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 sha256:7e3d659b823a2f0da2a29d55589e6f0de0cc3346d01d527ae5edf656ea8278bb
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af462bfdefdcdc75be1ad30dc01e3c5c2f738b60ea205de6fb4241617af195a
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8550a506d7d436eedb70abf73f761cb59725c5bf685282e90643e46b1e0873b0
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5569b49a4d1772af2f8ac29125f501ea892a4bafb9869e778368fe2e190f3e12
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e9a0298ce1f5239bff29210b1df36c4c4d8fcaea2534cfd59acbe3a0872f2c2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d1e2f62bcd8f9c4f40a4b2bf8d3b1487ddade040a76030966ec7ebea410fbb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.007238307349665924,
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": 16.146,
61
  "eval_steps_per_second": 8.077,
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": 1.409881957466112e+16,
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": 0.009279881217520415,
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": 16.146,
61
  "eval_steps_per_second": 8.077,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.007423904974016332,
66
+ "grad_norm": 0.5926054120063782,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.1644,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.009279881217520415,
73
+ "grad_norm": 0.7355955243110657,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.1577,
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": 1.76895301779456e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null