Hugging Face's logo

ipeksnmz
/
bert-base-uncased-finetuned-rte-run_3

Text Classification
Transformers
TensorBoard
Safetensors
bert
glue
rte
max_length_128
dropout_0.4
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
ipeksnmz commited on
Commit
6d60b2b
·
verified ·
1 Parent(s): 8d1ac27

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-156/model.safetensors +1 -1
  3. run-4/checkpoint-156/optimizer.pt +1 -1
  4. run-4/checkpoint-156/rng_state.pth +1 -1
  5. run-4/checkpoint-156/scheduler.pt +1 -1
  6. run-4/checkpoint-156/trainer_state.json +14 -41
  7. run-4/checkpoint-156/training_args.bin +1 -1
  8. runs/Apr07_19-56-35_578d22db0b7b/events.out.tfevents.1744056434.578d22db0b7b.632.6 +3 -0
  9. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc777af6911bc2f91e0cdceced703b8e4a09d550e56d6e621ac9c0b57def38f8
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4891c85923eb1751121423e083e3404c8fb6eb4a4dc52922ad262d2fb76bb6fe
3
  size 437958648
run-4/checkpoint-156/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:091d7bdfe35eee5321912b1130707bb180c1b8383540aebcdd5b811dd9e02b85
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4891c85923eb1751121423e083e3404c8fb6eb4a4dc52922ad262d2fb76bb6fe
3
  size 437958648
run-4/checkpoint-156/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b76ae83cfb9431889bec17add5055c820d69e2a396f43988feb1bdb62c52586f
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b5a136660a6335182e8ce171d2e55464c5c6ffc6ee7f5898ae26a4ce6bd2f9
3
  size 876038394
run-4/checkpoint-156/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d60a11c2570e4f4dcd3b0d8e0823b5f74c0a337374c5c14747c4176f53063dcc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a764c8fbd65482b3f8f8bebeef4f213015cd8ce9bbf6f431f02795e508eff51
3
  size 14244
run-4/checkpoint-156/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb4543e15ce524d8cdae5864121ba50315398ef6d234d80fc67c7104c936b029
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc44addf19f848a84ad40df65eac282a4fe932831f89985fb0de0de4c8088882
3
  size 1064
run-4/checkpoint-156/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_global_step": 39,
3
- "best_metric": 0.4729241877256318,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-4/checkpoint-39",
5
- "epoch": 4.0,
6
  "eval_steps": 500,
7
  "global_step": 156,
8
  "is_hyper_param_search": true,
@@ -11,45 +11,18 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.4729241877256318,
15
- "eval_loss": 0.7156691551208496,
16
- "eval_runtime": 2.0183,
17
- "eval_samples_per_second": 137.242,
18
- "eval_steps_per_second": 1.486,
19
- "step": 39
20
- },
21
- {
22
- "epoch": 2.0,
23
- "eval_accuracy": 0.4693140794223827,
24
- "eval_loss": 0.7056853771209717,
25
- "eval_runtime": 1.992,
26
- "eval_samples_per_second": 139.054,
27
- "eval_steps_per_second": 1.506,
28
- "step": 78
29
- },
30
- {
31
- "epoch": 3.0,
32
- "eval_accuracy": 0.4657039711191336,
33
- "eval_loss": 0.7013823986053467,
34
- "eval_runtime": 2.0128,
35
- "eval_samples_per_second": 137.618,
36
- "eval_steps_per_second": 1.49,
37
- "step": 117
38
- },
39
- {
40
- "epoch": 4.0,
41
  "eval_accuracy": 0.4657039711191336,
42
- "eval_loss": 0.6988705992698669,
43
- "eval_runtime": 2.0026,
44
- "eval_samples_per_second": 138.317,
45
- "eval_steps_per_second": 1.498,
46
  "step": 156
47
  }
48
  ],
49
  "logging_steps": 500,
50
- "max_steps": 195,
51
  "num_input_tokens_seen": 0,
52
- "num_train_epochs": 5,
53
  "save_steps": 500,
54
  "stateful_callbacks": {
55
  "TrainerControl": {
@@ -64,13 +37,13 @@
64
  }
65
  },
66
  "total_flos": 0,
67
- "train_batch_size": 64,
68
  "trial_name": null,
69
  "trial_params": {
70
  "dropout": 0.2,
71
- "learning_rate": 1.958741210329851e-06,
72
  "max_length": 256,
73
- "num_train_epochs": 5,
74
- "per_device_train_batch_size": 64
75
  }
76
  }
 
1
  {
2
+ "best_global_step": 156,
3
+ "best_metric": 0.4657039711191336,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-4/checkpoint-156",
5
+ "epoch": 1.0,
6
  "eval_steps": 500,
7
  "global_step": 156,
8
  "is_hyper_param_search": true,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "eval_accuracy": 0.4657039711191336,
15
+ "eval_loss": 0.706757128238678,
16
+ "eval_runtime": 0.4712,
17
+ "eval_samples_per_second": 587.806,
18
+ "eval_steps_per_second": 19.098,
19
  "step": 156
20
  }
21
  ],
22
  "logging_steps": 500,
23
+ "max_steps": 312,
24
  "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 2,
26
  "save_steps": 500,
27
  "stateful_callbacks": {
28
  "TrainerControl": {
 
37
  }
38
  },
39
  "total_flos": 0,
40
+ "train_batch_size": 16,
41
  "trial_name": null,
42
  "trial_params": {
43
  "dropout": 0.2,
44
+ "learning_rate": 1.8147223767636534e-06,
45
  "max_length": 256,
46
+ "num_train_epochs": 2,
47
+ "per_device_train_batch_size": 16
48
  }
49
  }
run-4/checkpoint-156/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0d8957a4f6591d87d73465c1ee2c1044ed338281f563612ab9e9ba3d8188200
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d8caec19e178a735778696a9c43ef8907bddc1a4617e8297fd3706a848b696
3
  size 5432
runs/Apr07_19-56-35_578d22db0b7b/events.out.tfevents.1744056434.578d22db0b7b.632.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7965d3569f6344ef05e9ec264282fb0ea4cb77c95f785abcc8578f7e6da3581
3
+ size 6102
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e3245604cac2709b0dab5c3ce10afa8e9bee1f4e19b928623f07264875b418
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d8caec19e178a735778696a9c43ef8907bddc1a4617e8297fd3706a848b696
3
  size 5432