jssky commited on
Commit
7552626
·
verified ·
1 Parent(s): f6052b6

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 sha256:5c6ebc4d6ad772044af258c05e6ea90b574d8a7b359e2457ab595b3064c22660
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:616573af24727964882e6508d3f897e9251a6780f4e739535f0fe4076eed6fca
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc9d317b342767fb572406b168b31291ed7de7ed8b7dc6bdcdac359b273badc
3
  size 42608388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5666e2acfa1048f352e4b25c44449f21bc1d2d2b7da20e1c9dc34ed5f97c6baf
3
  size 42608388
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b9e29ca9f1840ccec759292965b44b25e81d2b6f5643637c96ef211cfb804af
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:975e2fef0ce023c45a0d7bbabf76a79358b37a1de8f82a4354020f8b97bfa2fa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.004085106382978723,
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": 7.687,
74
  "eval_steps_per_second": 7.687,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1206357948628992.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006127659574468085,
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": 7.687,
74
  "eval_steps_per_second": 7.687,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004765957446808511,
79
+ "grad_norm": 11.895439147949219,
80
+ "learning_rate": 0.00012,
81
+ "loss": 7.4861,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.005446808510638298,
86
+ "grad_norm": 13.066421508789062,
87
+ "learning_rate": 0.00014,
88
+ "loss": 7.6098,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.006127659574468085,
93
+ "grad_norm": 11.546978950500488,
94
+ "learning_rate": 0.00016,
95
+ "loss": 6.4677,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.006127659574468085,
100
+ "eval_loss": 6.334994792938232,
101
+ "eval_runtime": 40.3134,
102
+ "eval_samples_per_second": 7.69,
103
+ "eval_steps_per_second": 7.69,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1809536922943488.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null