daniel40 commited on
Commit
5292893
·
verified ·
1 Parent(s): 3a62858

Training in progress, step 50, 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:db9f6a5bf69fd7bb1762cd9cce468099c2582b3da4429b723bce616a21815b7d
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041061cbf860240e8e427f98408142b6242a3f5782121858b35e1a304ee0330b
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:869fcdc8f27143a8710807c290be8968bab5645656e59b4021649c5f18c10449
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ef5a21c8c7c122d9d2e5e93a809cf579d4b20cdc00b8053da3640ad99ee501
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2370b71c7d694cb68d2a88a561fc6732a72c957a8e53e888b0d9060c59b88d31
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131b19ddd275d883c63922a09a14567c54c589cbe91eb3ec46a4b79dda8079b8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.0023059866962305987,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 34.246,
61
  "eval_steps_per_second": 17.123,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 6474214215254016.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0029563932002956393,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 34.246,
61
  "eval_steps_per_second": 17.123,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0023651145602365115,
66
+ "grad_norm": 0.7077562808990479,
67
+ "learning_rate": 2.9289321881345254e-05,
68
+ "loss": 1.4753,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0029563932002956393,
73
+ "grad_norm": 1.0900564193725586,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.501,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 8306538993156096.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null