nat-hunt commited on
Commit
f594159
·
verified ·
1 Parent(s): 4f4d9f6

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 sha256:20bb86ab3d419301df827324402ab85ca4c2a36fbaab2c4cb3493cc8339b4072
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9fb72c818d636ef98bcfe85fc5da2cb6b31e7441cce90cb70ecc8705d120bd
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14336e1c2b7b105ef4f2253f24000a0607ef6bf369147feee5d356b776e683db
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64cbf58fef940612c0b00b5c7b75dc1570e87a28aa6a758b9f6edf234dda59ad
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a13307056da4bbb211ad48ade25632cd037a6f559d3df7d1e4eebdbef92276c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894ae9e2dd56efcd745c69d81e84d269bfa54a0f8cbcf8e14a4428f929aae407
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": 0.0002768006458681737,
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": 26.14,
74
  "eval_steps_per_second": 13.072,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1294717522280448.0,
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": 0.00041520096880226054,
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": 26.14,
74
  "eval_steps_per_second": 13.072,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00032293408684620263,
79
+ "grad_norm": 0.682282567024231,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.8114,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003690675278242316,
86
+ "grad_norm": 0.69523686170578,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.8753,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00041520096880226054,
93
+ "grad_norm": 0.6659558415412903,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.6686,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00041520096880226054,
100
+ "eval_loss": 0.6748826503753662,
101
+ "eval_runtime": 349.4345,
102
+ "eval_samples_per_second": 26.119,
103
+ "eval_steps_per_second": 13.061,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2034556106440704.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null