shibajustfor commited on
Commit
bb0133d
·
verified ·
1 Parent(s): 041a970

Training in progress, step 42, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:998f8dfe1a4fe152e269c54d2027d8c95f64fc9d73b3ec1e62452e05d3e802ff
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a04478a6eb03e6510900e28206005ddd886c32257ac48e9d4c1cb51df7218d9
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93996bc4196dfaca8d2de518388e9d2ccf3818aadb9aedc1e1af60d7bf73b721
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81bfd0205bc29bc072146a965d37b1ca07674f8357dc3a0e1a1b2b38fe154fda
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c24c62e4cd7b0332ff8817426a459e70a6e7e90cb15d9bcaac496100d630999
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07d8c860cd7de8ee301f608ccd3584f3827e66ed38993f94733b1c5732af739
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5307556de25fa7df1caa893b2d8321c1b847c59c86eb876afa5cf1f8077bc325
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2e7edae03699c1cd9559730363e2f67d4336103b5fded6865a5437f817ac2d
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": 0.7904191616766467,
5
  "eval_steps": 11,
6
- "global_step": 33,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,13 @@
60
  "eval_samples_per_second": 61.897,
61
  "eval_steps_per_second": 30.948,
62
  "step": 33
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +81,12 @@
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": 1615276718161920.0,
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": 1.0179640718562875,
5
  "eval_steps": 11,
6
+ "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 61.897,
61
  "eval_steps_per_second": 30.948,
62
  "step": 33
63
+ },
64
+ {
65
+ "epoch": 0.9580838323353293,
66
+ "grad_norm": 0.003072954947128892,
67
+ "learning_rate": 1.4384089652291543e-06,
68
+ "loss": 0.0001,
69
+ "step": 40
70
  }
71
  ],
72
  "logging_steps": 10,
 
81
  "should_evaluate": false,
82
  "should_log": false,
83
  "should_save": true,
84
+ "should_training_stop": true
85
  },
86
  "attributes": {}
87
  }
88
  },
89
+ "total_flos": 2055806732206080.0,
90
  "train_batch_size": 2,
91
  "trial_name": null,
92
  "trial_params": null