tensor24 commited on
Commit
8989d84
1 Parent(s): 1a58f7a

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 sha256:595b05fc8363a4621debc5404af975f8d041717f926ffb4e7ab5b618b5242a6d
3
  size 60010048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db24bab980bd1f33651c7134011cf8ee9d8cbb51d7aabd2986fa20cec5a8edb3
3
  size 60010048
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea39050d2a736fd00654b5e921a2ba06bb1b587b8d2be0abb0b4a13c6cc95e24
3
  size 30839892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b035c874ce94ffbfffc3ba56750ead100bd438deefd946864864e5b5916756
3
  size 30839892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c18614e643ab6ea6a7570704da31a8529e4c28e827cc0141d66c634237c16463
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17112f18adb57bd8c3d3808f3312936260bf4574741894fd027bd7b76c17fa99
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": 0.006962576153176675,
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": 5.041,
74
  "eval_steps_per_second": 2.528,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1527501092290560.0,
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": 0.010443864229765013,
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": 5.041,
74
  "eval_steps_per_second": 2.528,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.008123005512039455,
79
+ "grad_norm": 0.4856230318546295,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.5106,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.009283434870902234,
86
+ "grad_norm": 0.32355302572250366,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.3177,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.010443864229765013,
93
+ "grad_norm": 0.7106059193611145,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.4037,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.010443864229765013,
100
+ "eval_loss": 0.5413673520088196,
101
+ "eval_runtime": 71.8887,
102
+ "eval_samples_per_second": 5.049,
103
+ "eval_steps_per_second": 2.532,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2291251638435840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null