adammandic87 commited on
Commit
36d887f
·
verified ·
1 Parent(s): 8b4d5ef

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:b9016285e1f31231898eb518172873cc78658cc614a66dba64b8515e134bd862
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993e4537a095e6911873b53bd956e690a65e1d4fb468b5deff7513fbec8adeb2
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:397a2770f026b07ba8f908a07b4515b95e3208b81b6d55a2b496485931a90bd6
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590e8831158721e107f22b3d80fdfa883bf7475a5f05db1ec31a4002abd6975b
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:354fcbfab35beb320321fc72abe28e2ba17d63b820a2c10b34cfe337af85be52
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd9f9fa4f12eb656180c05ab6d0e11868fa1b817f9a6c422f3c0302601735f4e
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": 0.010900705750821046,
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": 20.602,
61
  "eval_steps_per_second": 10.308,
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": 1.234820118085632e+16,
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": 0.013975263783103906,
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": 20.602,
61
  "eval_steps_per_second": 10.308,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.011180211026483125,
66
+ "grad_norm": 2.6180880069732666,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.4861,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.013975263783103906,
73
+ "grad_norm": 1.5887194871902466,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.4589,
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": 1.5831027154944e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null