Best000 commited on
Commit
25f8d72
·
verified ·
1 Parent(s): dca32e4

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 sha256:5f24c89ba0a62a1cf8fe507ea509122de119c1179b1d842451f92220039497e4
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a08398e36e7855ad1449efcab861c27ccc9312395ccaaae6776e306340f108
3
  size 5752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61dfea36fbd7737cecf6cf756d93b9e1fed023bae8fd5b4027eee1c4d36c0565
3
  size 15814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abbf5cce6cb6d3bb58e5cccf5d7fd78c53eeccd37b26daa24e6d4fb696fac1b5
3
  size 15814
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
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": 0.00040958427196395656,
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": 26.38,
74
  "eval_steps_per_second": 13.19,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 149421588480.0,
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": 0.0006143764079459349,
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": 26.38,
74
  "eval_steps_per_second": 13.19,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00047784831729128267,
79
+ "grad_norm": 7.424625891871983e-06,
80
+ "learning_rate": 0.00014,
81
+ "loss": 46.0,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0005461123626186088,
86
+ "grad_norm": 1.8153745259041898e-05,
87
+ "learning_rate": 0.00016,
88
+ "loss": 46.0,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0006143764079459349,
93
+ "grad_norm": 1.0418201782158576e-05,
94
+ "learning_rate": 0.00018,
95
+ "loss": 46.0,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0006143764079459349,
100
+ "eval_loss": 11.5,
101
+ "eval_runtime": 235.0273,
102
+ "eval_samples_per_second": 26.244,
103
+ "eval_steps_per_second": 13.122,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 219151663104.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null