Hugging Face's logo

Yuvrajg2107
/
roberta-base-cpp

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
Yuvrajg2107 commited on
Commit
7fcccc1
·
verified ·
1 Parent(s): 35a804b

Training in progress, step 7000, checkpoint

Browse files
Files changed (6) 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/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +26 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ea438799779b7d5df6829426c8563db0aaf689f4b71b2db885dde813b47a656
3
  size 498612824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b090f420e4a4b79bb9b83dba51d26dd4e2b6d29f1d12b1510721e2bf6bd1ba5
3
  size 498612824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac7b943d7b3f892e05c3280199300655641226024c9d46fc2c36377844e09219
3
  size 997345931
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ebdd708712721a1fa8df534d43f59d69e107f5088893e47e9475f1c9a8e242
3
  size 997345931
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:903ae64856702f56aca34b3a83e463f26492f960398b5b01c03e210465cf26b7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4e3de49d1806c7044e452123303f3ec21f0d1186d1b23be8ec33eb1e34488d
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be40a03f70bb2a35bb567114fb5ceb05ce1222c8df24b1e1100746c617c5be10
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6ac56f1033e9e261dd3b41721e9cff6132800378e9f573cebb3fd9f04365c7d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5503916e083484344eb90ffdd7cef8671b9c273655dd45784cda2988a30dceb9
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 4000,
3
  "best_metric": 0.04343162104487419,
4
  "best_model_checkpoint": "./training_output/checkpoint-4000",
5
- "epoch": 0.3,
6
  "eval_steps": 1000,
7
- "global_step": 6000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -146,6 +146,29 @@
146
  "eval_samples_per_second": 54.993,
147
  "eval_steps_per_second": 3.437,
148
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
149
  }
150
  ],
151
  "logging_steps": 500,
@@ -165,7 +188,7 @@
165
  "attributes": {}
166
  }
167
  },
168
- "total_flos": 6314665328640000.0,
169
  "train_batch_size": 2,
170
  "trial_name": null,
171
  "trial_params": null
 
2
  "best_global_step": 4000,
3
  "best_metric": 0.04343162104487419,
4
  "best_model_checkpoint": "./training_output/checkpoint-4000",
5
+ "epoch": 0.35,
6
  "eval_steps": 1000,
7
+ "global_step": 7000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
146
  "eval_samples_per_second": 54.993,
147
  "eval_steps_per_second": 3.437,
148
  "step": 6000
149
+ },
150
+ {
151
+ "epoch": 0.325,
152
+ "grad_norm": 0.002066701650619507,
153
+ "learning_rate": 1.3501000000000002e-05,
154
+ "loss": 0.039,
155
+ "step": 6500
156
+ },
157
+ {
158
+ "epoch": 0.35,
159
+ "grad_norm": 0.06389991194009781,
160
+ "learning_rate": 1.3001000000000001e-05,
161
+ "loss": 0.0416,
162
+ "step": 7000
163
+ },
164
+ {
165
+ "epoch": 0.35,
166
+ "eval_accuracy": 0.9366,
167
+ "eval_loss": 0.11077161878347397,
168
+ "eval_runtime": 363.1946,
169
+ "eval_samples_per_second": 55.067,
170
+ "eval_steps_per_second": 3.442,
171
+ "step": 7000
172
  }
173
  ],
174
  "logging_steps": 500,
 
188
  "attributes": {}
189
  }
190
  },
191
+ "total_flos": 7367109550080000.0,
192
  "train_batch_size": 2,
193
  "trial_name": null,
194
  "trial_params": null