Hugging Face's logo

HiAmNear
/
cafebert-ViFE-task-1

Text Classification
Transformers
Safetensors
xlm-roberta
Model card Files
xet
 Community
HiAmNear commited on
Commit
ec8ccef
·
verified ·
1 Parent(s): 09d52b2

Training in progress, epoch 5, 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 sha256:2c95f094b1849ad37adb524b2b32fe0ed35369a86f735f5527bb5834d420c931
3
  size 2239622772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397797976e31bd63489cf78a47cea1d63b4a66ede2167d3b2e8e8789b092bf32
3
  size 2239622772
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:488c218548f6a272b1f03cbd8262d072956f965fbae3dc63d3ff4b7670976bb6
3
  size 4479480977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c72678eb33152f45431d1b4461dfb7de8912437774e6d6130bbc9e1e284eff
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:c1d199696fa260379e7e66bd8e81ab7711f1d9ddff0db691d968dbd82daf5acc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc74ff2acef2b6fa0795fbcd61055b5f026bbc755f0ae4877226b45fb890e98
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d45b5ae0bbbda8e986dabb22da819431f04bf448a3f66c2e021aa9732f02406
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b9ab65981fb317d9bcd8764ff5dad92d81de46cff5cae47e2ec0946cafca3e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8170926517571885,
3
- "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-195",
4
- "epoch": 4.984025559105431,
5
  "eval_steps": 500,
6
- "global_step": 195,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,15 @@
52
  "eval_samples_per_second": 37.761,
53
  "eval_steps_per_second": 4.735,
54
  "step": 195
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 500,
@@ -71,7 +80,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 1.161992193425145e+16,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8298722044728435,
3
+ "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-234",
4
+ "epoch": 5.980830670926517,
5
  "eval_steps": 500,
6
+ "global_step": 234,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 37.761,
53
  "eval_steps_per_second": 4.735,
54
  "step": 195
55
+ },
56
+ {
57
+ "epoch": 5.980830670926517,
58
+ "eval_accuracy": 0.8298722044728435,
59
+ "eval_loss": 0.45184266567230225,
60
+ "eval_runtime": 33.1468,
61
+ "eval_samples_per_second": 37.771,
62
+ "eval_steps_per_second": 4.737,
63
+ "step": 234
64
  }
65
  ],
66
  "logging_steps": 500,
 
80
  "attributes": {}
81
  }
82
  },
83
+ "total_flos": 1.394390632110174e+16,
84
  "train_batch_size": 8,
85
  "trial_name": null,
86
  "trial_params": null