ardaspear commited on
Commit
7d56fcb
·
verified ·
1 Parent(s): df133f8

Training in progress, step 18, 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:c6036dd72c85fa373718882f6aa23b14be8e0267442c24de34382f21deda7298
3
  size 180385008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd030c5ed2843ec05e5fb277d77bdde344e3f12c7d3870609acb84e845d264f2
3
  size 180385008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b85ee131ec9ea1e677763aec10ea26ea2acc7e2b7d3b3b45e244aab7fbd6a2a
3
  size 91850362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2948c5dbc51bae5cb4e4976835544332c592fb9db305363cf3ff4068df714bbb
3
  size 91850362
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a874c609a782cce072b91aab7e0ddc54563b85396fc0a4c5327bc80820511339
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb05f0d759ae1c790e4c31eb74d4a60bc985859785fc219ddf4992451dd0252
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf83a2e8e60abc266eb939060af002b89aea4f4268fd719cbee186b10601a323
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d238195ca09ed8cbcd3cc35f5a395bf6b3bc853a4c8c7d3f2134fd9d41f2760
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": 1.2765957446808511,
5
  "eval_steps": 3,
6
- "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -90,6 +90,21 @@
90
  "eval_samples_per_second": 48.165,
91
  "eval_steps_per_second": 7.225,
92
  "step": 15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93
  }
94
  ],
95
  "logging_steps": 3,
@@ -109,7 +124,7 @@
109
  "attributes": {}
110
  }
111
  },
112
- "total_flos": 3002896849305600.0,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.5319148936170213,
5
  "eval_steps": 3,
6
+ "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
90
  "eval_samples_per_second": 48.165,
91
  "eval_steps_per_second": 7.225,
92
  "step": 15
93
+ },
94
+ {
95
+ "epoch": 1.5319148936170213,
96
+ "grad_norm": 3.459306001663208,
97
+ "learning_rate": 7.840323733655778e-05,
98
+ "loss": 2.6305,
99
+ "step": 18
100
+ },
101
+ {
102
+ "epoch": 1.5319148936170213,
103
+ "eval_loss": 2.800814151763916,
104
+ "eval_runtime": 0.4153,
105
+ "eval_samples_per_second": 48.16,
106
+ "eval_steps_per_second": 7.224,
107
+ "step": 18
108
  }
109
  ],
110
  "logging_steps": 3,
 
124
  "attributes": {}
125
  }
126
  },
127
+ "total_flos": 3603476219166720.0,
128
  "train_batch_size": 8,
129
  "trial_name": null,
130
  "trial_params": null