VERSIL91 commited on
Commit
35d087d
·
verified ·
1 Parent(s): d8b3f7c

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:e3f2efad9ad399a529d11a48792a59e61debba1850964c5ad01e32a82286d042
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aead67378eb080b6439e73f92b79b22ba3fff6719672a9daece2960f68cbfb9
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c528a55bdc1a39a005cb6fdddb33815ab93fccc79c5ea068297fe212cc02d9c
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28dc4ef51aaf7b90827fc66fd26b60dfedb06701a7589abb0499ddf65ebb125c
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7824cda9b09088755df9c1fad3a0258c249f3861ebeb526074259caef60b1595
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe0152387846c1162de177cdc53167a9183696b149d3eb20d4cf5fbd6b53e78
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
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": 0.0235236461651556,
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": 343.358,
74
  "eval_steps_per_second": 171.679,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1573405065216.0,
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": 0.035285469247733396,
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": 343.358,
74
  "eval_steps_per_second": 171.679,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0274442538593482,
79
+ "grad_norm": 2.0904550552368164,
80
+ "learning_rate": 7e-05,
81
+ "loss": 7.0724,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0313648615535408,
86
+ "grad_norm": 1.8750410079956055,
87
+ "learning_rate": 8e-05,
88
+ "loss": 6.8382,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.035285469247733396,
93
+ "grad_norm": 1.808696985244751,
94
+ "learning_rate": 9e-05,
95
+ "loss": 6.9148,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.035285469247733396,
100
+ "eval_loss": 6.91793966293335,
101
+ "eval_runtime": 1.2501,
102
+ "eval_samples_per_second": 343.979,
103
+ "eval_steps_per_second": 171.989,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2360107597824.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null