great0001 commited on
Commit
0814850
·
verified ·
1 Parent(s): ab5b941

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:a7eceb5ab7d268e6f0220a69ab1b53903e6fc4c356bbb4a4c759ad630461d94e
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c410270fb076312cd792118f35ddcbfc8da87e19ce63642826f00b7675e3a1
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10efc2d54d0e1ab1e1d1c7f3f6bde01b3d0039a6ddf68c44b45f054ca18d7af7
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f2d80d3654bed65563a02a0bdb8b9b18b68e3e7bfbd121b3f4f9e89752a6d2b
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2de705390d283bbd81a5e93dee1b31313fa27cc6d82af844c64763adad18b049
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c8ed40ec98a023147d5dc738d793bbc1a12d076092bf16d3e44b95b06849d3f
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": 0.014268727705112961,
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": 35.923,
74
  "eval_steps_per_second": 17.962,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 497064811167744.0,
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": 0.02140309155766944,
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": 35.923,
74
  "eval_steps_per_second": 17.962,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.016646848989298454,
79
+ "grad_norm": 0.22511990368366241,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.0205,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.019024970273483946,
86
+ "grad_norm": 0.29633215069770813,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.9259,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.02140309155766944,
93
+ "grad_norm": 0.29478707909584045,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.9776,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.02140309155766944,
100
+ "eval_loss": 1.9992634057998657,
101
+ "eval_runtime": 5.0221,
102
+ "eval_samples_per_second": 35.443,
103
+ "eval_steps_per_second": 17.722,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 788447631507456.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null