phungkhaccuong commited on
Commit
e70e7d0
·
verified ·
1 Parent(s): e9e3d35

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 sha256:67b9ca819b8eb3d6adef4f898f9a65fabf47d02bd1a7b1bdd06299f095960648
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c74466575c1b8245248bff4dfa50546b7202fc5a9e231769d267dd882a1d24
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f216fb383050efb8a8eda8072a42062277a006056951fe1c6d610c99be838f51
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a4b0237575affbe7e85618428c6c26e2fac627a2f377f3392566b9845bae13
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:b70a15b7847c8e61838121a6622a5b2d0734a021df91c806730421aab2237ead
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f44182fa5fd14f0c9c7ece47052110d2789c39637b32550f9fd390e6e98a012
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": 0.022336769759450172,
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": 2.9544,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5696176804331520.0,
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": 0.03350515463917526,
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": 2.9544,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.02577319587628866,
72
+ "grad_norm": 39.98679733276367,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.3217,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.02577319587628866,
79
+ "eval_loss": 0.5785247087478638,
80
+ "eval_runtime": 73.9753,
81
+ "eval_samples_per_second": 6.637,
82
+ "eval_steps_per_second": 3.325,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03006872852233677,
87
+ "grad_norm": 52.07625198364258,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.4132,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 8544265206497280.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null