Hugging Face's logo

eclec
/
test_trainer

Text Classification
Transformers
Safetensors
longformer
Model card Files Community
eclec commited on
Commit
87da51a
·
verified ·
1 Parent(s): 89b724a

Training in progress, epoch 1

Browse files
Files changed (14) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-1/model.safetensors +1 -1
  3. run-0/checkpoint-1/optimizer.pt +1 -1
  4. run-0/checkpoint-1/rng_state.pth +2 -2
  5. run-0/checkpoint-1/scheduler.pt +1 -1
  6. run-0/checkpoint-1/trainer_state.json +15 -15
  7. run-0/checkpoint-1/training_args.bin +1 -1
  8. run-0/checkpoint-2/model.safetensors +1 -1
  9. run-0/checkpoint-2/optimizer.pt +1 -1
  10. run-0/checkpoint-2/rng_state.pth +2 -2
  11. run-0/checkpoint-2/scheduler.pt +1 -1
  12. run-0/checkpoint-2/trainer_state.json +19 -19
  13. run-0/checkpoint-2/training_args.bin +1 -1
  14. training_args.bin +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd776ea672c8973b53b4ae02d385a5ff68991133a89b6b338228b3d004de2713
3
  size 1738480904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eddafd616aa1aa4fda7c5c345b32e182b128932840acf5e942ed1c356bb2a203
3
  size 1738480904
run-0/checkpoint-1/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd776ea672c8973b53b4ae02d385a5ff68991133a89b6b338228b3d004de2713
3
  size 1738480904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eddafd616aa1aa4fda7c5c345b32e182b128932840acf5e942ed1c356bb2a203
3
  size 1738480904
run-0/checkpoint-1/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc8c0321a4ba5fbb4dad00f3e0a20d1ed794ca69c07fb2c979a82c2b01b89f98
3
  size 4554273
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869c2f770b588db551ee5eda7c822bd4008f7464b9ee051404fa2fec85324ff3
3
  size 4554273
run-0/checkpoint-1/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06431a06dc113891110756ec0ac4b014dd7d6b797f07e2f1b648bbb2758060f5
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71977f31ab5f87725eab7f9064a80b092f768fb2cf785918fc99462cd817c0e8
3
+ size 14244
run-0/checkpoint-1/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fefd6ea4e1c7c2e842dd37be41268003aeb0e3212cd073f3f3e3f389fec20cb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89dc3ded6c54981b4de3a87581360fc12132fced76df83d09988f2d4b3889ddd
3
  size 1064
run-0/checkpoint-1/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.7080078125,
3
  "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-1",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -12,29 +12,29 @@
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.0,
14
  "eval_f1": 0.0,
15
- "eval_loss": 0.7080078125,
16
- "eval_runtime": 0.1741,
17
- "eval_samples_per_second": 5.744,
18
- "eval_steps_per_second": 5.744,
19
  "step": 1
20
  }
21
  ],
22
  "logging_steps": 500,
23
- "max_steps": 5,
24
  "num_input_tokens_seen": 0,
25
- "num_train_epochs": 5,
26
  "save_steps": 500,
27
  "total_flos": 0,
28
  "train_batch_size": 8,
29
  "trial_name": null,
30
  "trial_params": {
31
- "gradient_accumulation_steps": 8,
32
- "learning_rate": 7.543213106016258e-06,
33
- "num_train_epochs": 5,
34
- "optimizer": "AdamW",
35
- "seed": 48,
36
- "warmup_ratio": 0.2668631355210866,
37
- "warmup_steps": 204,
38
- "weight_decay": 0.4761015845296048
39
  }
40
  }
 
1
  {
2
+ "best_metric": 0.787109375,
3
  "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-1",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.0,
14
  "eval_f1": 0.0,
15
+ "eval_loss": 0.787109375,
16
+ "eval_runtime": 0.1522,
17
+ "eval_samples_per_second": 6.568,
18
+ "eval_steps_per_second": 6.568,
19
  "step": 1
20
  }
21
  ],
22
  "logging_steps": 500,
23
+ "max_steps": 2,
24
  "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 2,
26
  "save_steps": 500,
27
  "total_flos": 0,
28
  "train_batch_size": 8,
29
  "trial_name": null,
30
  "trial_params": {
31
+ "gradient_accumulation_steps": 1,
32
+ "learning_rate": 6.404847217172767e-06,
33
+ "num_train_epochs": 2,
34
+ "optimizer": "AdaFactor",
35
+ "seed": 47,
36
+ "warmup_ratio": 0.06373313794247544,
37
+ "warmup_steps": 315,
38
+ "weight_decay": 0.3456353554922866
39
  }
40
  }
run-0/checkpoint-1/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75d07f95613d82874f5c1c1a8ba5956eb7a8647edfa0d0ba7a2261402aaea793
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00b7817af2658d242a38dfcf15be2d74a29e431f80133466dfee37241ad5414
3
  size 4856
run-0/checkpoint-2/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bda83432ab206b336b14b80cb5b48e2758bc3fc5ec581e270b0f274fade3ddd8
3
  size 1738480904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf7e4f44ff9e2dd7b2e25d52cad75585babff7cba69c2401a3e44a9769cd9c3
3
  size 1738480904
run-0/checkpoint-2/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:874f9d0f2fcd9fd9dfdd78ddbd055d96119cb6d852d3da1c227f562894e324d3
3
  size 4554273
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a36ad8945be20a73d0c630fadfa96ff397fe66fe2fa86b01c00b8c5c5159cee
3
  size 4554273
run-0/checkpoint-2/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf0ed4139a763528ed3a23c1215fa41fdaa933291d22d67cacc933a02acebabd
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b07b350379ad151f90be40377217cd4c7f7dad3b9128cc290e1f9b7e9dfa63
3
+ size 14244
run-0/checkpoint-2/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac4947eb2ade6578262c473d09b2551e736f6466515fea4bca3ceacece003b33
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d342961c9dc4c6d5f6141dcbf6bbab2c7fc58b9ffa1d71ba34bb8f93adde41d4
3
  size 1064
run-0/checkpoint-2/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.7080078125,
3
  "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-1",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -12,39 +12,39 @@
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.0,
14
  "eval_f1": 0.0,
15
- "eval_loss": 0.7080078125,
16
- "eval_runtime": 0.1741,
17
- "eval_samples_per_second": 5.744,
18
- "eval_steps_per_second": 5.744,
19
  "step": 1
20
  },
21
  {
22
  "epoch": 2.0,
23
  "eval_accuracy": 0.0,
24
  "eval_f1": 0.0,
25
- "eval_loss": 0.7080078125,
26
- "eval_runtime": 0.1514,
27
- "eval_samples_per_second": 6.605,
28
- "eval_steps_per_second": 6.605,
29
  "step": 2
30
  }
31
  ],
32
  "logging_steps": 500,
33
- "max_steps": 5,
34
  "num_input_tokens_seen": 0,
35
- "num_train_epochs": 5,
36
  "save_steps": 500,
37
  "total_flos": 0,
38
  "train_batch_size": 8,
39
  "trial_name": null,
40
  "trial_params": {
41
- "gradient_accumulation_steps": 8,
42
- "learning_rate": 7.543213106016258e-06,
43
- "num_train_epochs": 5,
44
- "optimizer": "AdamW",
45
- "seed": 48,
46
- "warmup_ratio": 0.2668631355210866,
47
- "warmup_steps": 204,
48
- "weight_decay": 0.4761015845296048
49
  }
50
  }
 
1
  {
2
+ "best_metric": 0.787109375,
3
  "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-1",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.0,
14
  "eval_f1": 0.0,
15
+ "eval_loss": 0.787109375,
16
+ "eval_runtime": 0.1522,
17
+ "eval_samples_per_second": 6.568,
18
+ "eval_steps_per_second": 6.568,
19
  "step": 1
20
  },
21
  {
22
  "epoch": 2.0,
23
  "eval_accuracy": 0.0,
24
  "eval_f1": 0.0,
25
+ "eval_loss": 0.787109375,
26
+ "eval_runtime": 0.1624,
27
+ "eval_samples_per_second": 6.158,
28
+ "eval_steps_per_second": 6.158,
29
  "step": 2
30
  }
31
  ],
32
  "logging_steps": 500,
33
+ "max_steps": 2,
34
  "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 2,
36
  "save_steps": 500,
37
  "total_flos": 0,
38
  "train_batch_size": 8,
39
  "trial_name": null,
40
  "trial_params": {
41
+ "gradient_accumulation_steps": 1,
42
+ "learning_rate": 6.404847217172767e-06,
43
+ "num_train_epochs": 2,
44
+ "optimizer": "AdaFactor",
45
+ "seed": 47,
46
+ "warmup_ratio": 0.06373313794247544,
47
+ "warmup_steps": 315,
48
+ "weight_decay": 0.3456353554922866
49
  }
50
  }
run-0/checkpoint-2/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75d07f95613d82874f5c1c1a8ba5956eb7a8647edfa0d0ba7a2261402aaea793
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00b7817af2658d242a38dfcf15be2d74a29e431f80133466dfee37241ad5414
3
  size 4856
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a73b7b66f98437f10f26a03c21f3514bf94524721820f55798ba5452426cb4b
3
- size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00b7817af2658d242a38dfcf15be2d74a29e431f80133466dfee37241ad5414
3
+ size 4856