tensor24 commited on
Commit
5bae453
·
verified ·
1 Parent(s): a27f4a5

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 sha256:4aabf299ac00c500c06126f0b6e1f33b463f93e668490e9d5d0a72d4d38ab116
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e156eb53450930ed9929fccca4e5e82e6d973d3ca94e1f90df72626b045bc08
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c49fd001a1fedf1024a7346d18bd45e174c0ee8f3ef7d5ede659e516570269c
3
  size 25986148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7772edef7fdb7d835529a91b8ff9a8708b193b15a04c68e749f97f345524fe
3
  size 25986148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0e3316d2cf3807eae9dbf9a639db4bf3b211c11598d00a94e92fb77034b1be1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a23d8c54930bcfa400a42faf2dd8310c9fa2fc3255471da30515ca920d46e8eb
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": 8.899535370090886e-05,
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": 6.759,
74
  "eval_steps_per_second": 3.379,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1235242526441472.0,
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": 0.0001334930305513633,
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": 6.759,
74
  "eval_steps_per_second": 3.379,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00010382791265106034,
79
+ "grad_norm": 0.4554048180580139,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.6983,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00011866047160121182,
86
+ "grad_norm": 0.33600732684135437,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.4306,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0001334930305513633,
93
+ "grad_norm": 0.3740876019001007,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.5837,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0001334930305513633,
100
+ "eval_loss": 1.642859697341919,
101
+ "eval_runtime": 4200.056,
102
+ "eval_samples_per_second": 6.759,
103
+ "eval_steps_per_second": 3.379,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1852863789662208.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null