Hugging Face's logo

HiAmNear
/
cafebert-ViFE-task-1

Text Classification
Transformers
Safetensors
xlm-roberta
Model card Files
xet
 Community
HiAmNear commited on
Commit
f5fa770
·
verified ·
1 Parent(s): befd706

Training in progress, epoch 8, 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:a7db41af601ffd60bfa4105c8c16b986efdc1e9fa93874af1be1d7cb7c437137
3
  size 2239622772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88916cdb7d81d69692ffeba992bc5c2199e90a674924564cb6a81af6a6845ef9
3
  size 2239622772
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f9724527bba66268edf248059764c593fb934d8e0bfc9082ecf2bda45d0c5b6
3
  size 4479480977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5bfa0bcc0b969528175295f53c514c946e2f0a9da26424e4488a24d20bca515
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:d32f62f96192ffdbb148a7e122226910db24c1e4ae0e6d3e48b8f0cdfe2bb76c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d49c753ae2680a1eef00fd6d127178f4aa95d602cc379641d3d1eeab9ea474
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b13906a4cefbe1686d2beb36f581ff63e2cbcf3a3c79241892ccfba58095cf5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2474c8b2ccfcd5a22c50d41eed735491623b7ca3387d4404c88ad00998e1cbf0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8554313099041534,
3
- "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-313",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 313,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -79,6 +79,15 @@
79
  "eval_samples_per_second": 37.596,
80
  "eval_steps_per_second": 4.714,
81
  "step": 313
 
 
 
 
 
 
 
 
 
82
  }
83
  ],
84
  "logging_steps": 500,
@@ -98,7 +107,7 @@
98
  "attributes": {}
99
  }
100
  },
101
- "total_flos": 1.859187509480232e+16,
102
  "train_batch_size": 8,
103
  "trial_name": null,
104
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8650159744408946,
3
+ "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-352",
4
+ "epoch": 8.996805111821086,
5
  "eval_steps": 500,
6
+ "global_step": 352,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
79
  "eval_samples_per_second": 37.596,
80
  "eval_steps_per_second": 4.714,
81
  "step": 313
82
+ },
83
+ {
84
+ "epoch": 8.996805111821086,
85
+ "eval_accuracy": 0.8650159744408946,
86
+ "eval_loss": 0.396475613117218,
87
+ "eval_runtime": 33.2277,
88
+ "eval_samples_per_second": 37.679,
89
+ "eval_steps_per_second": 4.725,
90
+ "step": 352
91
  }
92
  ],
93
  "logging_steps": 500,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2.091585948165261e+16,
111
  "train_batch_size": 8,
112
  "trial_name": null,
113
  "trial_params": null