Hugging Face's logo

heavyhelium
/
roberta-large-touche-base-binary

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
heavyhelium commited on
Commit
faf4fa1
·
verified ·
1 Parent(s): da99e2b

Training in progress, epoch 1, checkpoint

Browse files
Files changed (5) hide show
  1. checkpoint-93/model.safetensors +1 -1
  2. checkpoint-93/optimizer.pt +1 -1
  3. checkpoint-93/scaler.pt +1 -1
  4. checkpoint-93/trainer_state.json +16 -16
  5. checkpoint-93/training_args.bin +1 -1
checkpoint-93/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57c680f46703b1b760bac86e759260c30c13da3203537d00048ba5069a710e12
3
  size 1421495416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25f25b7bcdbe18184802551892de73cb8d2568ffa02fdd39d3f20c8d215d11a
3
  size 1421495416
checkpoint-93/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb8160e60ea05a078da8ba2406b422d84afdf3e3cf2de64b1710ad8a4186d2b9
3
  size 2843229182
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc76a9a85c589732e1e2f5d2040ef2b2ff93869690fd12447dc0c6a7b205430
3
  size 2843229182
checkpoint-93/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b96b6ceb21b7e54a63d7b02c78f6360111c4cef38c9e1118025fdc14bb0b79e3
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db70d2911554ed5520dea1b4de337d5aaf475a5f99aadd8b817f4f9fb444fb5
3
  size 1383
checkpoint-93/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "best_global_step": 93,
3
- "best_metric": 0.44147644487615345,
4
  "best_model_checkpoint": "models/roberta-large-touche-base-binary/trainer/checkpoint-93",
5
  "epoch": 1.0,
6
  "eval_steps": 500,
@@ -46,41 +46,41 @@
46
  },
47
  {
48
  "epoch": 0.6486486486486487,
49
- "grad_norm": 11.706809997558594,
50
  "learning_rate": 1.752988047808765e-05,
51
- "loss": 1.3295562744140625,
52
  "step": 60
53
  },
54
  {
55
  "epoch": 0.7567567567567568,
56
- "grad_norm": 8.710282325744629,
57
  "learning_rate": 1.6733067729083667e-05,
58
- "loss": 1.4055770874023437,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 0.8648648648648649,
63
- "grad_norm": 25.93303871154785,
64
  "learning_rate": 1.593625498007968e-05,
65
- "loss": 1.348858642578125,
66
  "step": 80
67
  },
68
  {
69
  "epoch": 0.972972972972973,
70
- "grad_norm": 21.619033813476562,
71
  "learning_rate": 1.5139442231075698e-05,
72
- "loss": 1.3660049438476562,
73
  "step": 90
74
  },
75
  {
76
  "epoch": 1.0,
77
- "eval_accuracy": 0.54,
78
- "eval_fallacy_f1": 0.676056338028169,
79
- "eval_loss": 0.6844885349273682,
80
- "eval_macro_f1": 0.44147644487615345,
81
- "eval_runtime": 1.3356,
82
- "eval_samples_per_second": 149.747,
83
- "eval_steps_per_second": 9.734,
84
  "step": 93
85
  }
86
  ],
 
1
  {
2
  "best_global_step": 93,
3
+ "best_metric": 0.38837920489296635,
4
  "best_model_checkpoint": "models/roberta-large-touche-base-binary/trainer/checkpoint-93",
5
  "epoch": 1.0,
6
  "eval_steps": 500,
 
46
  },
47
  {
48
  "epoch": 0.6486486486486487,
49
+ "grad_norm": 11.744357109069824,
50
  "learning_rate": 1.752988047808765e-05,
51
+ "loss": 1.3298416137695312,
52
  "step": 60
53
  },
54
  {
55
  "epoch": 0.7567567567567568,
56
+ "grad_norm": 8.649158477783203,
57
  "learning_rate": 1.6733067729083667e-05,
58
+ "loss": 1.40760498046875,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 0.8648648648648649,
63
+ "grad_norm": 15.254891395568848,
64
  "learning_rate": 1.593625498007968e-05,
65
+ "loss": 1.349920654296875,
66
  "step": 80
67
  },
68
  {
69
  "epoch": 0.972972972972973,
70
+ "grad_norm": 21.086435317993164,
71
  "learning_rate": 1.5139442231075698e-05,
72
+ "loss": 1.3678375244140626,
73
  "step": 90
74
  },
75
  {
76
  "epoch": 1.0,
77
+ "eval_accuracy": 0.515,
78
+ "eval_fallacy_f1": 0.6666666666666666,
79
+ "eval_loss": 0.6907617449760437,
80
+ "eval_macro_f1": 0.38837920489296635,
81
+ "eval_runtime": 1.539,
82
+ "eval_samples_per_second": 129.957,
83
+ "eval_steps_per_second": 8.447,
84
  "step": 93
85
  }
86
  ],
checkpoint-93/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f971fc8774df1933b8a79b44365200d70bf8c947215295450c3dd984620ca6
3
  size 5393
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b57361bd3df136d106452d8a34502b0e6fe2a74596feef14daa5dc9d043af2d9
3
  size 5393