chauhoang commited on
Commit
9caa301
·
verified ·
1 Parent(s): 0c4afee

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:be8ce8cfc4011099fd03e59beef181464e8709106981052632d68c4aa3f4db0a
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66df446587efd615bcf768c3f45770faafde5ded710e805702fca97ad87f66cf
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5012a69ed4b968327c721bd7102c2b7909ecf988ced1aaf62a06f01bfb86a56f
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a8e66af693f35a5b1169548647e9f1c4e54b2f7faa3f423be2e4df2225b74e
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19345076a59d2345cb36b77781c9e57468c57d8d41c5a6f2c85d50f71a6f780a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f5b40e282f1eedfb4ca61f530370f998a6e7bdf8b2051ec73ea8f8590cc55f
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": 0.0005005607242728633,
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": 0.7798,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7675691629805568.0,
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": 0.000750841086409295,
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": 0.7798,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005775700664686885,
72
+ "grad_norm": 0.419593870639801,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.7425,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005775700664686885,
79
+ "eval_loss": 0.8312729001045227,
80
+ "eval_runtime": 2106.3291,
81
+ "eval_samples_per_second": 10.383,
82
+ "eval_steps_per_second": 5.192,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0006738317442134699,
87
+ "grad_norm": 0.5337291359901428,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.7527,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.132858101989376e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null