ClarenceDan commited on
Commit
bcfb7cf
·
verified ·
1 Parent(s): dc5a7c2

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18f1df0702cf04675faf7d51842c28a81be52d5b0efd18f1e013deb4cbd4d1df
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af0646cff2988ca67f0ca212dbe0adcdc29da13155c073a27ccaeea42761f22
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:900af745b417bfdbd7f1bf167528409fee1c92701d9d36bdab37883a2d48e95b
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38c8d199d2e2bbf5c6e3b46dffd6f8f3e61b403fdd1c8401c40a2d0d49ac9fa
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cf5013b0491490a507b6d9b1cf6a87127c1fe017c693197dd1eaff518ed78a6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b3ee8f06a13ef0f4d0831c0c1d7840f1b54d75135d2aeb006e8d093e0945fe
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0009302325581395349,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 19.405,
74
  "eval_steps_per_second": 9.703,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1895803354349568.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0013953488372093023,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 19.405,
74
  "eval_steps_per_second": 9.703,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0010852713178294573,
79
+ "grad_norm": 0.641669750213623,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.2007,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00124031007751938,
86
+ "grad_norm": 0.6157209873199463,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.9989,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0013953488372093023,
93
+ "grad_norm": 0.5293413400650024,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.0255,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0013953488372093023,
100
+ "eval_loss": 1.0745004415512085,
101
+ "eval_runtime": 139.9501,
102
+ "eval_samples_per_second": 19.407,
103
+ "eval_steps_per_second": 9.703,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2820585478422528.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null