shibajustfor commited on
Commit
7dfc56d
·
verified ·
1 Parent(s): 42bb84f

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:f371e69118aa24af46b3112fdf48a413b931380bd21e38f71b480e6b25d9db12
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3844f0a7028023f6bd1f3563535d47279c1082f3b50dc0d56e49a39f31b6f0a
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61d6b93c04f9bb567ade70b1e83dbf10414462ce2db099f60e015501adefc646
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb53bc3c62a26da5f09d9ce16ccbc36d016fe6fa8c928ee9d516f0e519dca66e
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c0de88f52f1b25312b7f144e1e148e127d3627d4243a31e7bcdc603bb56931
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.04441913439635535,
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": 145.724,
61
  "eval_steps_per_second": 72.862,
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": 4376032837632.0,
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": 0.05694760820045558,
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": 145.724,
61
  "eval_steps_per_second": 72.862,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.04555808656036447,
66
+ "grad_norm": 0.9106863141059875,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 7.2574,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.05694760820045558,
73
+ "grad_norm": 1.717692494392395,
74
+ "learning_rate": 0.0,
75
+ "loss": 7.2503,
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": 5506917728256.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null