trenden commited on
Commit
258568c
·
verified ·
1 Parent(s): c5d3207

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:daf703881d881c9b339d72c27509f8a87bdd85c0800745a8dfcf039cf15f7969
3
  size 32856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7d1fc968addb87959ecf8bf6613c9d2abd917bbb5d8724cb40a52a8de7bbb0
3
  size 32856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3fd80031342ecc757bb8b4851c6f61a3ffcf5ba8ed171d894df473234e7fd4e
3
  size 71358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0fe75699a6a2a774c1ad0390d1294041ab5d53e3b12895d91d7164c8031c00
3
  size 71358
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ae59499d6fa89d93656a32994352236f76ecdb3c0d5d7d01bbf5e497aa8ee6c
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": 0.006800645189415406,
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": 476.997,
61
  "eval_steps_per_second": 238.597,
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": 29137305600.0,
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": 0.008718775883865906,
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": 476.997,
61
  "eval_steps_per_second": 238.597,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.006975020707092724,
66
+ "grad_norm": 0.5001388192176819,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 44.3126,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.008718775883865906,
73
+ "grad_norm": 0.8100123405456543,
74
+ "learning_rate": 0.0,
75
+ "loss": 44.3248,
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": 37355520000.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null