Hugging Face's logo

HiAmNear
/
cafebert-ViFE-task-1

Text Classification
Transformers
Safetensors
xlm-roberta
Model card Files
xet
 Community
HiAmNear commited on
Commit
6046378
·
verified ·
1 Parent(s): 3ff19a4

Training in progress, epoch 4, 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:aa727963d5667b2ac5074cad0b68847061513f62fdbe2fb94b28a30f1905e9bf
3
  size 2239622772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c95f094b1849ad37adb524b2b32fe0ed35369a86f735f5527bb5834d420c931
3
  size 2239622772
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75608d535fe5173a65e4769804bf9311b460349a1b06d304fee9bd84606d3dc0
3
  size 4479480977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488c218548f6a272b1f03cbd8262d072956f965fbae3dc63d3ff4b7670976bb6
3
  size 4479480977
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5132521522cc42d383a76316a4117d6eb9d99da009fcbed961c4d920ca0db7f4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d199696fa260379e7e66bd8e81ab7711f1d9ddff0db691d968dbd82daf5acc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f83a036b3b0a8d5c84d9db52175bad13c03fd731bf03851a1ec5d23242dc4772
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d45b5ae0bbbda8e986dabb22da819431f04bf448a3f66c2e021aa9732f02406
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -43,6 +43,15 @@
43
  "eval_samples_per_second": 37.68,
44
  "eval_steps_per_second": 4.725,
45
  "step": 156
 
 
 
 
 
 
 
 
 
46
  }
47
  ],
48
  "logging_steps": 500,
@@ -62,7 +71,7 @@
62
  "attributes": {}
63
  }
64
  },
65
- "total_flos": 9295937547401160.0,
66
  "train_batch_size": 8,
67
  "trial_name": null,
68
  "trial_params": null
 
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,
 
43
  "eval_samples_per_second": 37.68,
44
  "eval_steps_per_second": 4.725,
45
  "step": 156
46
+ },
47
+ {
48
+ "epoch": 4.984025559105431,
49
+ "eval_accuracy": 0.8170926517571885,
50
+ "eval_loss": 0.4626227915287018,
51
+ "eval_runtime": 33.1556,
52
+ "eval_samples_per_second": 37.761,
53
+ "eval_steps_per_second": 4.735,
54
+ "step": 195
55
  }
56
  ],
57
  "logging_steps": 500,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 1.161992193425145e+16,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null