Training in progress, epoch 1

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
+metrics:
+- matthews_correlation
 model-index:
 - name: distilbert-base-uncased-finetuned-cola
   results: []
@@ -15,12 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.7374
-- eval_matthews_correlation: 0.0
-- eval_runtime: 0.8208
-- eval_samples_per_second: 1270.779
-- eval_steps_per_second: 80.414
-- step: 0
+- Loss: 0.6927
+- Matthews Correlation: 0.5324
 
 ## Model description
 
@@ -47,9 +45,20 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 5
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
+| 0.5444        | 1.0   | 535  | 0.4784          | 0.4217               |
+| 0.4206        | 2.0   | 1070 | 0.4567          | 0.5146               |
+| 0.3071        | 3.0   | 1605 | 0.5392          | 0.5134               |
+| 0.2517        | 4.0   | 2140 | 0.6712          | 0.5154               |
+| 0.2141        | 5.0   | 2675 | 0.6972          | 0.5279               |
+
+
 ### Framework versions
 
 - Transformers 4.38.2
-- Pytorch 2.1.0+cu121
+- Pytorch 2.2.1
 - Datasets 2.18.0
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1369a8794345bb16aacbde3dfb9750a018f47f5d6ad0bd953333cfe4123d794
+oid sha256:b570c5b24c8f16451c59666ae9747b537ee676f3eb9142c285910f298f565b5b
 size 267832560

run-0/checkpoint-14/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01dea21155b76ee81916bb36ab74676d53ff7dfc1a91fa1c2d6f52439d0e9cb5
+oid sha256:000084a5c09ce2f304a7a30367eac2b4b929c0bb2f932cbc147c16bc8270c8cb
 size 267832560

run-0/checkpoint-14/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc3a63eb6fc137ae586be466444a353c9a4d9a13f2e8144b64b58752fcfb6a8
-size 535727290
+oid sha256:8c04a4ddea247102f0b89cfcbb4bb6edb7b9fa7bfb2b4083f03c838b8e55e178
+size 535724410

run-0/checkpoint-14/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e24fc292984749c88110ec25fd9ff0d17a54f4360aec4dbcbbce59a3aa0de4
-size 14244
+oid sha256:b35282b35757a076ae637e2485765a8ff52783228da034059e59636da73d9116
+size 13990

run-0/checkpoint-14/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba06a15393ab004358877a1c1a15c76de27bc45fc71c2e37605a7d933415c21
+oid sha256:ad808127937629f024be1b1df977f47dde93819e2ea51d7e505c749e74d67ea0
 size 1064

run-0/checkpoint-14/trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5823530554771423,
+      "eval_loss": 0.6129326224327087,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7382,
-      "eval_samples_per_second": 1412.921,
-      "eval_steps_per_second": 89.408,
+      "eval_runtime": 0.9743,
+      "eval_samples_per_second": 1070.497,
+      "eval_steps_per_second": 67.74,
       "step": 14
     }
   ],
   "logging_steps": 500,
-  "max_steps": 14,
+  "max_steps": 42,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 8.775986258400349e-05,
-    "num_train_epochs": 1,
+    "learning_rate": 3.412035426521437e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 64,
-    "seed": 23
+    "seed": 6
   }
 }

run-0/checkpoint-14/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef837b91c98e7e0d6bdd9b58e77858a83fad7f1d2746c13214f67d41f4c922
-size 4984
+oid sha256:a6c8860da068b6062f4d15741401ea4de48f82b68563be615a3787b9c9bd6a91
+size 4920

run-1/checkpoint-14/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeedc397da2e50e1a369df839169ff3baed592b5728d9aafb1c487511f42da10
+oid sha256:0311124ca6d6f42eabe8bc7265a08e9750159fa4c790c2f721b461a58c128159
 size 267832560

run-1/checkpoint-14/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a545043af087d88cb61946690dce0d4316653a781ff446f6dded8115db1ce97
-size 535727290
+oid sha256:e976fff47601f46c663aa7521ea909ac258ac4ad08d847fc70bac928f2d53a33
+size 535724410

run-1/checkpoint-14/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b9d795f1087cbe638ed3fc6f2a698bfc22c35fc0179fd12b285b35f69e1a1c
-size 14308
+oid sha256:34b9c3df3f05d5551943ee2ae4717a2d2d8ea37bd63922f720e2415a871e5c8f
+size 14054

run-1/checkpoint-14/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1c6676752252a8249a2db6e352a680a5d9428014a5b912dfae3a454c2ec41b
+oid sha256:59695f1c31ed790d03091068b49e6240888e5c79ab7ffa6676708cefcd054951
 size 1064

run-1/checkpoint-14/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.010498792427994534,
+  "best_metric": 0.0,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-14",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6844037771224976,
-      "eval_matthews_correlation": 0.010498792427994534,
-      "eval_runtime": 2.387,
-      "eval_samples_per_second": 436.947,
-      "eval_steps_per_second": 27.65,
+      "eval_loss": 0.6369564533233643,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8932,
+      "eval_samples_per_second": 1167.76,
+      "eval_steps_per_second": 73.895,
       "step": 14
     }
   ],
@@ -27,9 +27,9 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.4416085092769088e-06,
+    "learning_rate": 8.838852125860309e-06,
     "num_train_epochs": 1,
     "per_device_train_batch_size": 64,
-    "seed": 32
+    "seed": 26
   }
 }

run-1/checkpoint-14/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f8e48ec1e03a914d1ec7892684e65a5bc3727dd12f0f3c52c01699c33d2156
-size 4984
+oid sha256:6ad18fb18504d68dd935334ff557f2382d1a779bd413a8efbaff6563d6f9613c
+size 4920

run-2/checkpoint-214/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b33bebca3c31b2a59033909ad09f352f795168df035fa5e21068f27d4fb1f40
+oid sha256:cceb3a83ab394eb8a0dea770f94abc545d75ce2815d0a35ecabbd69c9274ac72
 size 267832560

run-2/checkpoint-214/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c50fc3ffbe867daf58825f8193d0cfba84cc14252afd8a598cd321986402aa
-size 535727290
+oid sha256:a4f36c957d92a8002c5e97555d48a42de471a903f723339272d115811e7a7207
+size 535724410

run-2/checkpoint-214/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6642b66e64e0b7ca68e0c6a1ce3642e5ff680df66b6e523921454a079ed214ed
-size 14244
+oid sha256:18ed5be6d1ae819250215f2e56084152c3080260defb1f705b62ca73ce19da57
+size 14054

run-2/checkpoint-214/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:353a0f8e9cdb591b044d3c5506a10aa1733632724e4365b86c27c74a86c0ae67
+oid sha256:aaddcbc282ebbe13886a2ae0010153a1ceb6098f8f03e24ff7369f1380257318
 size 1064

run-2/checkpoint-214/trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.622901976108551,
+      "eval_loss": 0.6176151633262634,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6976,
-      "eval_samples_per_second": 1495.146,
-      "eval_steps_per_second": 94.611,
+      "eval_runtime": 0.9481,
+      "eval_samples_per_second": 1100.056,
+      "eval_steps_per_second": 69.61,
       "step": 214
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1070,
+  "max_steps": 856,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.121152845919556e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 4.2783203586043606e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 4,
-    "seed": 12
+    "seed": 20
   }
 }

run-2/checkpoint-214/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
-size 4984
+oid sha256:b7d59a3030f49e6d9ba6b53703d0aecc5a3cdf0ff9b87524d64c50670dec0e33
+size 4920

run-2/checkpoint-428/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f91ce0d32e3d331a97bec4766b3625708317c7a462015a589e5c58aa17a0a83e
+oid sha256:d7feb3ea5cfcc0719d9aa3e8828e87201c6ba1874b1b9dda6a72a11196b3465a
 size 267832560

run-2/checkpoint-428/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01beac2a03a926258b352eb83e0b8f6bdba3eee64c73cb47aa03f1d58a2e3343
-size 535727290
+oid sha256:01af5387baa500deae7a60ef01607a213628612baa70b49dab4c8444e09983b3
+size 535724410

run-2/checkpoint-428/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123a5343f68ec13b68a2b560055939797bee709d54072612e9bb907a91476f28
-size 14244
+oid sha256:2d30d176f4709947ef5e20ca28f86e3ac8c85d9b22de4d4222b40eaa3316066d
+size 14054

run-2/checkpoint-428/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30bc9c1aed483a88d8d8aec183321452b5964d4c251bdf3c79ed88b67776916
+oid sha256:b4b4f4d37419af893e7c0515177d5a99af69ac0b950cded792175bcc7ced3722
 size 1064

run-2/checkpoint-428/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.11842631274491741,
+  "best_metric": 0.25145549881333384,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-428",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.622901976108551,
+      "eval_loss": 0.6176151633262634,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6976,
-      "eval_samples_per_second": 1495.146,
-      "eval_steps_per_second": 94.611,
+      "eval_runtime": 0.9481,
+      "eval_samples_per_second": 1100.056,
+      "eval_steps_per_second": 69.61,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.6693491339683533,
-      "eval_matthews_correlation": 0.11842631274491741,
-      "eval_runtime": 1.934,
-      "eval_samples_per_second": 539.286,
-      "eval_steps_per_second": 34.125,
+      "eval_loss": 0.7769425511360168,
+      "eval_matthews_correlation": 0.25145549881333384,
+      "eval_runtime": 0.9343,
+      "eval_samples_per_second": 1116.319,
+      "eval_steps_per_second": 70.64,
       "step": 428
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1070,
+  "max_steps": 856,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.121152845919556e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 4.2783203586043606e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 4,
-    "seed": 12
+    "seed": 20
   }
 }

run-2/checkpoint-428/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
-size 4984
+oid sha256:b7d59a3030f49e6d9ba6b53703d0aecc5a3cdf0ff9b87524d64c50670dec0e33
+size 4920

run-2/checkpoint-642/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955e9d37c7ccf9fb2880c11ea1f35e7ffd6a30ab6bb769dfa19b27a03652e9cc
+oid sha256:21d37aded1f4476bbe051cc3bfcec41462be35bfe49b40bc6597fbe45a146bc1
 size 267832560

run-2/checkpoint-642/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49e846a73ef024263b9276d16b7bbf1b5a16de68a3a7164b8fdf60475011e3da
-size 535727290
+oid sha256:ef5020ece8eb289d5cf85d6fc8e8bee89797830e5366db88b5dd8f4aae439706
+size 535724410

run-2/checkpoint-642/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459a440c9d15ba5e5b2229c7ffbe3145e047b6e5e97660610634d47c20f261e5
-size 14244
+oid sha256:466fe0e260a39f52aac06c5607d4735d2c8103b2ac9ad54f5e71129ba4c43fb2
+size 14054

run-2/checkpoint-642/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380f2c8df8ab872e64b071c5a78cf09b05e00c6ec4fb7780bd08fd5e87023ef7
+oid sha256:524be37aab3f413fec1d7104c5de4e629f9090793566ac787fa2c9f2c4d95a2b
 size 1064

run-2/checkpoint-642/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.16411291424457647,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-642",
+  "best_metric": 0.25145549881333384,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-428",
   "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 642,
@@ -10,51 +10,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.622901976108551,
+      "eval_loss": 0.6176151633262634,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6976,
-      "eval_samples_per_second": 1495.146,
-      "eval_steps_per_second": 94.611,
+      "eval_runtime": 0.9481,
+      "eval_samples_per_second": 1100.056,
+      "eval_steps_per_second": 69.61,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.6693491339683533,
-      "eval_matthews_correlation": 0.11842631274491741,
-      "eval_runtime": 1.934,
-      "eval_samples_per_second": 539.286,
-      "eval_steps_per_second": 34.125,
+      "eval_loss": 0.7769425511360168,
+      "eval_matthews_correlation": 0.25145549881333384,
+      "eval_runtime": 0.9343,
+      "eval_samples_per_second": 1116.319,
+      "eval_steps_per_second": 70.64,
       "step": 428
     },
     {
       "epoch": 2.34,
-      "grad_norm": 1.357163667678833,
-      "learning_rate": 3.7935113291347165e-05,
-      "loss": 0.6007,
+      "grad_norm": 0.6545006036758423,
+      "learning_rate": 1.7793014575504117e-05,
+      "loss": 0.536,
       "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.3187288045883179,
-      "eval_matthews_correlation": 0.16411291424457647,
-      "eval_runtime": 0.7002,
-      "eval_samples_per_second": 1489.531,
-      "eval_steps_per_second": 94.256,
+      "eval_loss": 1.5843945741653442,
+      "eval_matthews_correlation": 0.1975523186260999,
+      "eval_runtime": 0.9037,
+      "eval_samples_per_second": 1154.164,
+      "eval_steps_per_second": 73.034,
       "step": 642
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1070,
+  "max_steps": 856,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 8429531866428.0,
+  "total_flos": 8269898302032.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.121152845919556e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 4.2783203586043606e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 4,
-    "seed": 12
+    "seed": 20
   }
 }

run-2/checkpoint-642/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
-size 4984
+oid sha256:b7d59a3030f49e6d9ba6b53703d0aecc5a3cdf0ff9b87524d64c50670dec0e33
+size 4920

run-2/checkpoint-856/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d7fc0ebbfd3955802d3bc98ef627cbaaa60a67957d6617d060aa879e86f74b5
+oid sha256:e27626274def27c9e5f0ede06699eccc9fca618421c5670171c59a5b7bb0bc50
 size 267832560

run-2/checkpoint-856/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c7ccf331c7f4f77d0cf84856691943b9acee52ec3eab295724b9ad971db10f
-size 535727290
+oid sha256:91f7394c728500aa68bbe29a75db3198b7d0c751ffc1593b88ea2fba588d8c42
+size 535724410

run-2/checkpoint-856/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0959e4fc49f256382e0dc2b5eaaf6de1ebc7372d1c9b5b34f8bda98d7f54a5b9
-size 14244
+oid sha256:4a8a81a3e9c375ac5e32a3bec083b8fd3ff43e0f665a1ebc2f09c530719bc7eb
+size 14054

run-2/checkpoint-856/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de31a0e7adf5d8ef4931b73625e96f3d7d082ff90485a5440fb14cbcadca1600
+oid sha256:6101755e70840fa69ae18a6720e6b0998296d977a410bf72ba3a6ac1d5932863
 size 1064

run-2/checkpoint-856/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.18954364972242177,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-856",
+  "best_metric": 0.25145549881333384,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-428",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 856,
@@ -10,60 +10,60 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.622901976108551,
+      "eval_loss": 0.6176151633262634,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6976,
-      "eval_samples_per_second": 1495.146,
-      "eval_steps_per_second": 94.611,
+      "eval_runtime": 0.9481,
+      "eval_samples_per_second": 1100.056,
+      "eval_steps_per_second": 69.61,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.6693491339683533,
-      "eval_matthews_correlation": 0.11842631274491741,
-      "eval_runtime": 1.934,
-      "eval_samples_per_second": 539.286,
-      "eval_steps_per_second": 34.125,
+      "eval_loss": 0.7769425511360168,
+      "eval_matthews_correlation": 0.25145549881333384,
+      "eval_runtime": 0.9343,
+      "eval_samples_per_second": 1116.319,
+      "eval_steps_per_second": 70.64,
       "step": 428
     },
     {
       "epoch": 2.34,
-      "grad_norm": 1.357163667678833,
-      "learning_rate": 3.7935113291347165e-05,
-      "loss": 0.6007,
+      "grad_norm": 0.6545006036758423,
+      "learning_rate": 1.7793014575504117e-05,
+      "loss": 0.536,
       "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.3187288045883179,
-      "eval_matthews_correlation": 0.16411291424457647,
-      "eval_runtime": 0.7002,
-      "eval_samples_per_second": 1489.531,
-      "eval_steps_per_second": 94.256,
+      "eval_loss": 1.5843945741653442,
+      "eval_matthews_correlation": 0.1975523186260999,
+      "eval_runtime": 0.9037,
+      "eval_samples_per_second": 1154.164,
+      "eval_steps_per_second": 73.034,
       "step": 642
     },
     {
       "epoch": 4.0,
-      "eval_loss": 1.7241299152374268,
-      "eval_matthews_correlation": 0.18954364972242177,
-      "eval_runtime": 0.7297,
-      "eval_samples_per_second": 1429.361,
-      "eval_steps_per_second": 90.449,
+      "eval_loss": 1.8945112228393555,
+      "eval_matthews_correlation": 0.2128478036255419,
+      "eval_runtime": 0.9124,
+      "eval_samples_per_second": 1143.125,
+      "eval_steps_per_second": 72.336,
       "step": 856
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1070,
+  "max_steps": 856,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 8429531866428.0,
+  "total_flos": 8269898302032.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.121152845919556e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 4.2783203586043606e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 4,
-    "seed": 12
+    "seed": 20
   }
 }

run-2/checkpoint-856/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
-size 4984
+oid sha256:b7d59a3030f49e6d9ba6b53703d0aecc5a3cdf0ff9b87524d64c50670dec0e33
+size 4920

run-5/checkpoint-28/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-5/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3870056ca24fafee07ce79ab45e6b95a3156bf5747508d1fbce91a02d96c474d
+size 267832560

run-5/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e491c136ecfc48c363b85867de74f1f5bc69f61aaf0a2cd7b3589cd2897b1b
+size 535724410

run-5/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf7dbdf5cb584b6776cc0d7cd018dbcc9dfa4522834880ffc17add855bbc60f
+size 13990

run-5/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da0bb45cdd1b7bdc99a21e8ab1eaf1b69554a76306fe4ec72b83d15cda1e2cd
+size 1064

run-5/checkpoint-28/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-5/checkpoint-28/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-5/checkpoint-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.17581089404252895,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-28",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5979461073875427,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.0048,
+      "eval_samples_per_second": 1038.014,
+      "eval_steps_per_second": 65.685,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5687254667282104,
+      "eval_matthews_correlation": 0.17581089404252895,
+      "eval_runtime": 1.0579,
+      "eval_samples_per_second": 985.874,
+      "eval_steps_per_second": 62.385,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.9276893971916006e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 22
+  }
+}

run-5/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a121abecd11f4dbfb22eb2392c7ce8cc09e31d72e9ff9cd173496bfe855538
+size 4920

run-5/checkpoint-42/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}