duyphu commited on
Commit
86c7773
·
verified ·
1 Parent(s): c5b6de6

Training in progress, step 39, 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:aaef4218a185d73b542e08567efb3efe53a3b9b3b3451cc5edea2952f676aadf
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abdd074a2359fc679d60404f02520658c7da973a3b8396ba8c4ec38065446079
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22349e90c86e9a812a427f5c138269d1049fcf38153fb128d185615faa04824f
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa25374cadf17a46fcc5c5ba014d8ae5f45ce50b3a9617fe6ce0743fad90cd9e
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e821233b20919d3c89485c13b08f65a9085ff4f3839c7c72d215170c5adce6b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a63f420b9e7de84bbc3c5a80fdd9facfc42c1cda1e04aef6966e66fbe6f161f1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.0047783138065701815,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.2493,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4530853719834624.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.007167470709855272,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.2493,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.005513439007580979,
72
+ "grad_norm": 0.6202302575111389,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.9636,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.005513439007580979,
79
+ "eval_loss": 1.8148504495620728,
80
+ "eval_runtime": 144.1095,
81
+ "eval_samples_per_second": 15.898,
82
+ "eval_steps_per_second": 7.952,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.006432345508844475,
87
+ "grad_norm": 0.8994152545928955,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.7743,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6796280579751936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null