phungkhaccuong commited on
Commit
8ccdb86
·
verified ·
1 Parent(s): 85e698f

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:de60dbe54bbf4a3d0fbbf25470a8fb67515377f0e48845cc5d58459b444dacaf
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77da02d4e2a0eb80068bf6f67a1dcde4360a9ad8867b5362309a9610c75594bd
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46778a96dade470000bff481fc8a2dc39352f4166390a484e4e0098f24afa2a9
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c53c397419c932c0b7174813fc81d37647d40f7f16abd0056e340f42a0dbe2
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:827d867f3fc7a4b22c4d5320b4a9d8e61428d7131b58037cdf8c85898b3652a1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e651d14e7ee52a338fd24cd91e6b6490d38a4418546e878a83bea1f77d0d566
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": 0.0006008296070343282,
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": 2.828,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 138027918163968.0,
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": 0.0009012444105514923,
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": 2.828,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0006932649311934555,
72
+ "grad_norm": 0.2757609188556671,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.2824,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0006932649311934555,
79
+ "eval_loss": 2.750725507736206,
80
+ "eval_runtime": 342.6113,
81
+ "eval_samples_per_second": 53.183,
82
+ "eval_steps_per_second": 26.593,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0008088090863923648,
87
+ "grad_norm": 0.27755308151245117,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.8928,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 205755902853120.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null