kostiantynk-out commited on
Commit
22d54dc
·
verified ·
1 Parent(s): c34358a

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 sha256:03a618c804373e17358b08829f93ce35240669dee17a0c56a2828ee866037519
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7558fc34b13b9d6f89453dfbfbbc18c9f3c897f6ec4cef0c825218db7034eae
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77a26372bc60c0c9eb820d10862cde5152e01445d8df975dd857349d555623e8
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5120947287d4080b5f45371daae5396d4946b0298bf86e156b636b54c9cd7f5
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:daef4d440c8b18b4e8ed70951f06793ba8c673633b41a899a0c8049a3b7dbb4a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
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": 0.0010632171177955966,
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": 73.142,
74
  "eval_steps_per_second": 36.586,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 72376066768896.0,
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": 0.0015948256766933947,
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": 73.142,
74
  "eval_steps_per_second": 36.586,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0012404199707615293,
79
+ "grad_norm": 96.0009765625,
80
+ "learning_rate": 0.00014,
81
+ "loss": 21.3063,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.001417622823727462,
86
+ "grad_norm": 56.73752975463867,
87
+ "learning_rate": 0.00016,
88
+ "loss": 16.3515,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0015948256766933947,
93
+ "grad_norm": 55.107513427734375,
94
+ "learning_rate": 0.00018,
95
+ "loss": 19.0825,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0015948256766933947,
100
+ "eval_loss": 4.481025218963623,
101
+ "eval_runtime": 32.4589,
102
+ "eval_samples_per_second": 73.231,
103
+ "eval_steps_per_second": 36.631,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 109660707225600.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null