VERSIL91 commited on
Commit
e72c1ff
·
verified ·
1 Parent(s): 5cd9b40

Training in progress, step 5, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:479e450eea28d64df74c5594627f2feaa9c4329fc9539e77f716c8cbf50f4453
3
  size 32856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c3ef81fc556d9d8c76684b75b259bcd4fd6cb3abf2c51726d5fdb6ea21f72e
3
  size 32856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3df2fe596ff91207bbb6b764e2affad7898f6bbe6cd714ffad77b5c36a57430b
3
  size 71358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e72d3a9bd728c236a4a399487bde5fda75f06e1ac2707bf600b8024cb66e9a
3
  size 71358
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b5059cf0c71c51f02ee969590c9c397dea8c41610c914bdf8477692d8344aa4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d166138c211ea2b813851b6edd159e795dd85ee746ab388ba70c4682c9616b3b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
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": 0.8421052631578947,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,13 @@
59
  "eval_samples_per_second": 181.029,
60
  "eval_steps_per_second": 90.514,
61
  "step": 4
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -73,12 +80,12 @@
73
  "should_evaluate": false,
74
  "should_log": false,
75
  "should_save": true,
76
- "should_training_stop": false
77
  },
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 21292646400.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.1052631578947367,
5
  "eval_steps": 2,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 181.029,
60
  "eval_steps_per_second": 90.514,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 1.1052631578947367,
65
+ "grad_norm": 1.09108567237854,
66
+ "learning_rate": 5e-05,
67
+ "loss": 177.25,
68
+ "step": 5
69
  }
70
  ],
71
  "logging_steps": 1,
 
80
  "should_evaluate": false,
81
  "should_log": false,
82
  "should_save": true,
83
+ "should_training_stop": true
84
  },
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 27082752000.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null