trenden commited on
Commit
3a9221b
·
verified ·
1 Parent(s): c173b71

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 sha256:25869fe564bf44371eb585742c998f025f6e4b2857ea2401bea37c4ec0e5f1e1
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9217aba7328276fea07e6e324f20da4951c03797c61a364d8aa26e81cdafc62
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a979119ab3a134bd31bc8682c81ddd13938f428d0c36a40740777cf8f75cb440
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d19c0cbfe35c843886c00da8004cf4429f2e97491c11042b4f0b349616013a
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5817e34a23dad8579be74f67510479ce037dc285a340462762d7eaee096563e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b26abbf1b59934080d069888ddc280966a21772b32c06587e6b149de3c91db2
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": 0.0024489795918367346,
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": 24.872,
74
  "eval_steps_per_second": 12.436,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2139604018790400.0,
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": 0.003673469387755102,
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": 24.872,
74
  "eval_steps_per_second": 12.436,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002857142857142857,
79
+ "grad_norm": 1.4988536834716797,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.4837,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0032653061224489797,
86
+ "grad_norm": 2.0944082736968994,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.0673,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.003673469387755102,
93
+ "grad_norm": 1.5092041492462158,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.5947,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.003673469387755102,
100
+ "eval_loss": 0.9217643737792969,
101
+ "eval_runtime": 41.5439,
102
+ "eval_samples_per_second": 24.841,
103
+ "eval_steps_per_second": 12.421,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3280726162145280.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null