tuanna08go commited on
Commit
8c78991
·
verified ·
1 Parent(s): 79cde8b

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 sha256:011048f9134558f57dc0a880c03ad72cf23152038ce6d92228aa8e20854eacf5
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ce9e0bb76b82aed5076df1efe737525d7d1bd47930719c246a8e233f5cbcb20
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:298d0e941a5ccf17e985c219e609a623b537258c8dd070fad3b3ea0d976b60cd
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d120c4e3741df739bd5703ee0541475293b73317f4743cca40740aabbf4f65c6
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f024375d7496e4b835d6d595543dfd9295d475bb8a4c7fc4ddf17e04330097e0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0afe795030fa7402c0c7d8bf543446a4e0c36611010ca4250fa1b7707b0fa1a3
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": 0.0091605742975425,
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": 0.3496,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5255501394739200.0,
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": 0.01374086144631375,
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": 0.3496,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.010569893420241346,
72
+ "grad_norm": 8.205277442932129,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.1392,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.010569893420241346,
79
+ "eval_loss": 0.20344699919223785,
80
+ "eval_runtime": 357.0046,
81
+ "eval_samples_per_second": 3.347,
82
+ "eval_steps_per_second": 1.675,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.012331542323614903,
87
+ "grad_norm": 17.674755096435547,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.2083,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7978806662922240.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null