trenden commited on
Commit
6c3b4c3
·
verified ·
1 Parent(s): 4b64fdc

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:ded4cf24479904237a3c2c4a817b5c512a6b8f3aef69f865f4d845cb176194a8
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5fb3c3c30c1132724892f1a9a919596b7ffe7eadb6619f910e9a792ed7cb14
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14983122aab585322b5c2abcc231806e15f1a54e395e66555c1734e71601299e
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18236cdad5a2fb24c293d75d0949e0b93b6898f461dedd5897f10549f993a9aa
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
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": 0.0001929663756090501,
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": 323.393,
74
  "eval_steps_per_second": 161.696,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 84050903040.0,
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": 0.0002894495634135752,
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": 323.393,
74
  "eval_steps_per_second": 161.696,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00022512743821055849,
79
+ "grad_norm": 0.030777351930737495,
80
+ "learning_rate": 0.00014,
81
+ "loss": 10.3733,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00025728850081206683,
86
+ "grad_norm": 0.05287371948361397,
87
+ "learning_rate": 0.00016,
88
+ "loss": 10.3731,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002894495634135752,
93
+ "grad_norm": 0.03980984911322594,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.3822,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002894495634135752,
100
+ "eval_loss": 10.376822471618652,
101
+ "eval_runtime": 40.6101,
102
+ "eval_samples_per_second": 322.383,
103
+ "eval_steps_per_second": 161.192,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 126076354560.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null