ClarenceDan commited on
Commit
5054d92
·
verified ·
1 Parent(s): f1371c3

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 sha256:63ab9bbaef12efd164b48a5b410498f41f20c102aa3cefd74de74acab48eaf9a
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94af9da60f69458942958c5728cebad732e7ee40a18a71f7e55713ce9d85f60a
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9360bd6ceaff7eea2eb86383f222bd9b3e8b1075afbb8e7fa1e727a51625a29
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30843a6ef7e13e66f3e8382e3b859b315ad3601bcf46d8ffc6b6cd77dc186f0
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ed361f2d63bb82818e33c366fb6b15db6cde149e93fdff111aa1f4ea8e127b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d4d6f0339a64145471a731f39983c4abd2c3231f0b38c2e13cc0df069dada1e
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": 0.015493867010974823,
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": 28.325,
74
  "eval_steps_per_second": 14.249,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 234531877552128.0,
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": 0.023240800516462233,
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": 28.325,
74
  "eval_steps_per_second": 14.249,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.018076178179470628,
79
+ "grad_norm": 0.5470597147941589,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.1244,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.02065848934796643,
86
+ "grad_norm": 0.635410726070404,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.2349,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.023240800516462233,
93
+ "grad_norm": 0.5770888328552246,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.4146,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.023240800516462233,
100
+ "eval_loss": 3.38030743598938,
101
+ "eval_runtime": 5.7882,
102
+ "eval_samples_per_second": 28.161,
103
+ "eval_steps_per_second": 14.167,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 378859186814976.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null