duyphu commited on
Commit
4dbb435
·
verified ·
1 Parent(s): f65dded

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 sha256:08989101063cabaec60eaadc620e875b3abecb08f3bc852332aba08f6b3ff897
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0489ff5897762a9cc1b91b0fe04a47b8ba0d140b6c593d02082b5257ba623dbf
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c040b515527ff167ee69f9dc8e68f261a8aa15823427b86f5e3352b80df3420
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261638ef2ebda5e7a2546c5a55206e5be82575d8e105053c1b5511cdef9ed4e6
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bf412d30b18818e2351cf6d5110fbccb862bfa929ffef67208cf557b9c74f65
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37adb5394c4804269d78dc27188509a76c73da44d7fd278481460ae8f3e8251
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": 0.0010958326747800432,
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": 1.9743,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8894799163686912.0,
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": 0.0016437490121700648,
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": 1.9743,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001264422317053896,
72
+ "grad_norm": 3.5818986892700195,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.0424,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001264422317053896,
79
+ "eval_loss": 0.5147128701210022,
80
+ "eval_runtime": 1132.2037,
81
+ "eval_samples_per_second": 8.824,
82
+ "eval_steps_per_second": 4.412,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001475159369896212,
87
+ "grad_norm": 3.088940382003784,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.0867,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3407923862503424e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null