chauhoang commited on
Commit
f1c80ad
·
verified ·
1 Parent(s): da85d69

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:ab809228656e777187033f6dc1e11ef930885396c42682a811cdcb05d2f2020e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd487c4ec4a32c02aaf5d86550676b9339c6823a39e3946176d28125323267b2
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c155321952a1b961e35a9f2906d187ccea11d8fcaffc6bad617b7be42f515f43
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43eb6e0667c7ea7216f77dcc7c86c566282f69d7d8483866b0a3929724243bf0
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cb92806e57e387dc4287cb8248c41b4894921324de83cad277fe9afa6586b2d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a87e4caf284f84836b86fbb9d15f85d95c4be4769dd1ae693ef400a82f62b7ca
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": 0.00039037720197140484,
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": 1.7103,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4947584363790336.0,
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": 0.0005855658029571073,
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": 1.7103,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.00045043523304392867,
72
+ "grad_norm": 1.5197194814682007,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.9845,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.00045043523304392867,
79
+ "eval_loss": 2.004338502883911,
80
+ "eval_runtime": 3540.2416,
81
+ "eval_samples_per_second": 7.921,
82
+ "eval_steps_per_second": 3.961,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0005255077718845835,
87
+ "grad_norm": 0.8008306622505188,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.734,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7398256992583680.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null