adammandic87 commited on
Commit
318c77e
·
verified ·
1 Parent(s): 1263560

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 sha256:4a6067ff67660282a50cf5ed5d55303ca913712d7de10a59d6fc27e7edcf88a1
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b35851a526fcc6a6dd65946e932681c3ad721b90f5dd3acc2c545ea662671d
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7eefc738f6041a759071afc0e7efa4ed8b434b4dfc063b1098ba6bd7f501a170
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e290545dd15afca21066428ced535e8e1fc464ff699213f864bdfc8de2476dc
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d68d2a8ec68d97e9f6781386cdc5d11673589bf128caf93d024b660045d53f99
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c794a47edc9435384cbc7bbda79d6455642ccecbb17e631e8dfd483567816013
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": 0.00020749040356883493,
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": 19.351,
74
  "eval_steps_per_second": 9.675,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1954479763095552.0,
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": 0.0003112356053532524,
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": 19.351,
74
  "eval_steps_per_second": 9.675,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002420721374969741,
79
+ "grad_norm": 0.17472119629383087,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.4136,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00027665387142511324,
86
+ "grad_norm": 0.19215179979801178,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.4949,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003112356053532524,
93
+ "grad_norm": 0.15618515014648438,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.3213,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003112356053532524,
100
+ "eval_loss": 0.358873575925827,
101
+ "eval_runtime": 629.382,
102
+ "eval_samples_per_second": 19.346,
103
+ "eval_steps_per_second": 9.673,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2931719644643328.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null