Hugging Face's logo

HiAmNear
/
cafebert-ViFE-task-1

Text Classification
Transformers
Safetensors
xlm-roberta
Model card Files
xet
 Community
HiAmNear commited on
Commit
51e704c
·
verified ·
1 Parent(s): 48b75c3

Training in progress, epoch 3, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +14 -5
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11050af1cbef3053f992eda27fd0e3b02133591eebd5174646e997d2eebd4616
3
  size 2239622772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa727963d5667b2ac5074cad0b68847061513f62fdbe2fb94b28a30f1905e9bf
3
  size 2239622772
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bccb47fb846ae27ee91aa75f2a42c19b60903bcc11a9596ec1fedf9d27cadf30
3
  size 4479480977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75608d535fe5173a65e4769804bf9311b460349a1b06d304fee9bd84606d3dc0
3
  size 4479480977
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83bbe5c66bfa3bb1942636b5a12127612d09fa333239c5391202efd7bba7a6b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5132521522cc42d383a76316a4117d6eb9d99da009fcbed961c4d920ca0db7f4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:551924683fca0047ad971c96a641e0170d2a6c1f235f436afeb70ddca2f6aceb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83a036b3b0a8d5c84d9db52175bad13c03fd731bf03851a1ec5d23242dc4772
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7779552715654952,
3
- "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-117",
4
- "epoch": 2.9904153354632586,
5
  "eval_steps": 500,
6
- "global_step": 117,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -34,6 +34,15 @@
34
  "eval_samples_per_second": 37.737,
35
  "eval_steps_per_second": 4.732,
36
  "step": 117
 
 
 
 
 
 
 
 
 
37
  }
38
  ],
39
  "logging_steps": 500,
@@ -53,7 +62,7 @@
53
  "attributes": {}
54
  }
55
  },
56
- "total_flos": 6971953160550870.0,
57
  "train_batch_size": 8,
58
  "trial_name": null,
59
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7899361022364217,
3
+ "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-156",
4
+ "epoch": 3.987220447284345,
5
  "eval_steps": 500,
6
+ "global_step": 156,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
34
  "eval_samples_per_second": 37.737,
35
  "eval_steps_per_second": 4.732,
36
  "step": 117
37
+ },
38
+ {
39
+ "epoch": 3.987220447284345,
40
+ "eval_accuracy": 0.7899361022364217,
41
+ "eval_loss": 0.5209566354751587,
42
+ "eval_runtime": 33.2273,
43
+ "eval_samples_per_second": 37.68,
44
+ "eval_steps_per_second": 4.725,
45
+ "step": 156
46
  }
47
  ],
48
  "logging_steps": 500,
 
62
  "attributes": {}
63
  }
64
  },
65
+ "total_flos": 9295937547401160.0,
66
  "train_batch_size": 8,
67
  "trial_name": null,
68
  "trial_params": null