harrisr-smu commited on
Commit
0496121
1 Parent(s): 076b644

Training in progress, epoch 2

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef12c4c560830a70915ed8990bd15246b45cd4cede20136292a3713df20d7f38
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7ae91360481ab1aead09d557d58d1b42a726caf7a77a9bf10bee6acbb84e11
3
  size 267832560
run-0/checkpoint-268/config.json CHANGED
@@ -20,6 +20,6 @@
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.38.2",
24
  "vocab_size": 30522
25
  }
 
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.40.0",
24
  "vocab_size": 30522
25
  }
run-0/checkpoint-268/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50b00da9b88c63da26861699eb35b54804a1a5d446a9c579c44ba575cc6e5839
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7ae91360481ab1aead09d557d58d1b42a726caf7a77a9bf10bee6acbb84e11
3
  size 267832560
run-0/checkpoint-268/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3c921fa31b6bf63969ca37245eea6b4fffb137d74dcd041f9c60ccd5e671056
3
  size 535724410
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e36d2c78b2d43a012843b07013247032c4258abd6bff2336658df8ff1338cde8
3
  size 535724410
run-0/checkpoint-268/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71a648ba44ab0f8aad220b8a1dd63144a108690234e45a733e0e861c48c570d1
3
  size 13990
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40392f19c38e19bfbfcebe085910b1abec4b89b63722fd76161650b6b9ab4f74
3
  size 13990
run-0/checkpoint-268/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1586e250c0804dd1701f6acc583b509801d53f57ef9d8d782491154daa9649d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6e9b4c10b2fe900a0592868e9e260872a8150c34e046a0a406aae783984c67e
3
  size 1064
run-0/checkpoint-268/tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
run-0/checkpoint-268/tokenizer_config.json CHANGED
@@ -45,7 +45,7 @@
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
- "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
 
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
run-0/checkpoint-268/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.45744157534977586,
3
- "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-268",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 268,
7
  "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.4704936742782593,
14
- "eval_matthews_correlation": 0.45744157534977586,
15
- "eval_runtime": 30.3484,
16
- "eval_samples_per_second": 34.367,
17
- "eval_steps_per_second": 2.175,
 
 
 
 
 
 
 
 
 
18
  "step": 268
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 536,
23
  "num_input_tokens_seen": 0,
24
  "num_train_epochs": 2,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
- "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 9.01334118373162e-05,
31
  "num_train_epochs": 2,
32
- "per_device_train_batch_size": 32,
33
- "seed": 1
34
  }
35
  }
 
1
  {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-134",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 268,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.5772179365158081,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 28.4405,
16
+ "eval_samples_per_second": 36.673,
17
+ "eval_steps_per_second": 2.321,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5522039532661438,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 29.7327,
25
+ "eval_samples_per_second": 35.079,
26
+ "eval_steps_per_second": 2.22,
27
  "step": 268
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 268,
32
  "num_input_tokens_seen": 0,
33
  "num_train_epochs": 2,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
+ "train_batch_size": 64,
37
  "trial_name": null,
38
  "trial_params": {
39
+ "learning_rate": 6.016083409160101e-06,
40
  "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 6
43
  }
44
  }
run-0/checkpoint-268/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e68dcaeaaa7b85726310fa2d1d977e77e5a2fd412333729b7b500e3b6fc5de5
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6e654bc5562972689e528d7506196f0ff109bd86fc3e0cc344b82d96435ef0
3
+ size 5048
runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713886483.309eb7d6022b.9612.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5654a81b4d4920d79bc9bf7da087b1dfdff6be20f81dcf8a07763ea82e18138
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3906461454f9b112af0d41fc6222c06cf8da549a78953ab46f65f1cd96bf24e7
3
+ size 5673