HiAmNear commited on
Commit
e86ff05
·
verified ·
1 Parent(s): 44f23b3

Training in progress, epoch 9, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3b6fd49dcb51d58987ba238c28571b6262d52f8709e141cdffd5141a977b307
3
  size 2239622772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8557197285aa474040732b3faf52393778ccfe00bf2845374700a5667bdcd056
3
  size 2239622772
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f78255ca9cf2a135abd321d6297f1632c4cd363dbac2e62500a0bfeb939cb8be
3
  size 4479480977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e59aaa067c95b6cfddb464e72f58685323c6ab29970b47228c7420a4a065fc
3
  size 4479480977
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0b14f2fa17aed792a194336b75f1cee9a25d8f7c703a6aaafa7f7365361b1ec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec783a1bdc155c6d7712fc7ca4a10a43873c934e423ff7ca10b82cc4bb429b4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:491c58b5642033f99f7c2115fead8df27804a68b4ef32e8aee5ac48551abbb29
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b8fc6c968c09b32ebacd5345c995f5b98e128622b1e398ff34fccb1711fb5a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.7774524158125915,
3
  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 1592,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -100,6 +100,15 @@
100
  "eval_samples_per_second": 11.785,
101
  "eval_steps_per_second": 5.893,
102
  "step": 1592
 
 
 
 
 
 
 
 
 
103
  }
104
  ],
105
  "logging_steps": 500,
@@ -119,7 +128,7 @@
119
  "attributes": {}
120
  }
121
  },
122
- "total_flos": 2.364550840896768e+16,
123
  "train_batch_size": 2,
124
  "trial_name": null,
125
  "trial_params": null
 
1
  {
2
  "best_metric": 0.7774524158125915,
3
  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
4
+ "epoch": 9.0,
5
  "eval_steps": 500,
6
+ "global_step": 1791,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
100
  "eval_samples_per_second": 11.785,
101
  "eval_steps_per_second": 5.893,
102
  "step": 1592
103
+ },
104
+ {
105
+ "epoch": 9.0,
106
+ "eval_accuracy": 0.7693997071742313,
107
+ "eval_loss": 1.7513818740844727,
108
+ "eval_runtime": 113.5331,
109
+ "eval_samples_per_second": 12.032,
110
+ "eval_steps_per_second": 6.016,
111
+ "step": 1791
112
  }
113
  ],
114
  "logging_steps": 500,
 
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 2.660119696008864e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null