Training in progress, epoch 2

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc03d6730cedf94c065cccb684601215248ed70177281b48f84551c77862f299
+oid sha256:a86f1bda26ad1640354bf6c188d80244a7f5f2b6694b2012f67143f6edbdaed7
 size 98725415

run-4/checkpoint-214/config.json

@@ -24,7 +24,7 @@
   "pad_token_id": 0,
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.27.2",
   "trigram_input": true,
   "true_hidden_size": 128,
   "type_vocab_size": 2,

run-4/checkpoint-214/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fdbf96832c06e52bb8b1cde816e42cfad4a0757faf8bd66785932f6b7fb0d06
-size 197593757
+oid sha256:d8a32cd30cf33bbf1b108a26d3d75ea9840ac3185d314d19bfbbaadb45d4f804
+size 197314895

run-4/checkpoint-214/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22549d8b7cdd063e2742ba38507f50641316f8e06710e574d061547c35ed8c7b
-size 14244
+oid sha256:89eb09fce7bbf8122a2c597fc54308b6b95066415fc5d099681a8e68d19f4869
+size 14575

run-4/checkpoint-214/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c2aa66da65c248eea02a8e8f0b50cf1f7ae270c245373af6ebf25ec8a644b5
-size 1064
+oid sha256:88668f3a4e695b514f2a6547cc3d5ecbea753cfa5e4fad0bb9d8f868327d0bd1
+size 627

run-4/checkpoint-214/tokenizer_config.json

@@ -1,53 +1,11 @@
 {
-  "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": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "MobileBertTokenizer",

run-4/checkpoint-214/trainer_state.json

@@ -1,8 +1,7 @@
 {
-  "best_metric": 0.03718764224408827,
-  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-4/checkpoint-214",
-  "epoch": 1.0,
-  "eval_steps": 500,
+  "best_metric": 0.007984019525529589,
+  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-4/checkpoint-107",
+  "epoch": 2.0,
   "global_step": 214,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
@@ -10,26 +9,31 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 108810.078125,
-      "eval_matthews_correlation": 0.03718764224408827,
-      "eval_runtime": 3.0667,
-      "eval_samples_per_second": 340.1,
-      "eval_steps_per_second": 21.521,
+      "eval_loss": 0.7695204615592957,
+      "eval_matthews_correlation": 0.007984019525529589,
+      "eval_runtime": 2.6807,
+      "eval_samples_per_second": 389.079,
+      "eval_steps_per_second": 24.621,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.982637345790863,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.5108,
+      "eval_samples_per_second": 415.4,
+      "eval_steps_per_second": 26.286,
       "step": 214
     }
   ],
-  "logging_steps": 500,
-  "max_steps": 214,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 500,
+  "max_steps": 428,
+  "num_train_epochs": 4,
   "total_flos": 0,
-  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.6926940399761e-06,
-    "num_train_epochs": 1,
-    "per_device_train_batch_size": 4,
-    "seed": 4
+    "learning_rate": 2.428172543385948e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 12
   }
 }

run-4/checkpoint-214/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd329de3edddbb0dd3482875f0b22efe973dc98362a309a016e3810926e0724
-size 4920
+oid sha256:134616c5175b1859b10e1348047fd02338d55705f285410aa8f7fdae509fbe5f
+size 3643

runs/Mar10_12-23-35_f87fe01c66be/1710074696.770817/events.out.tfevents.1710074696.f87fe01c66be.29486.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25350c39541fbe7bafb01ffedb88851d1a5dfc9c61b16e93dd0147955877ea6c
+size 5884

runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710074624.f87fe01c66be.29486.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a6582370f3e422230415b8f1f5198912e25cdd14d7cac60415c577de47130e
-size 5269
+oid sha256:de10155ab0556d5bf9c88de7caca085933fe30da4d1cd65496f47156a7ed0a34
+size 5623

runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710074696.f87fe01c66be.29486.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bd31bc34a38d0bfc349aa96b54ab6cae7f916e7f449d80b111a337a43ced0d
+size 4938

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f666641269d2be95ebba45cd0c3329b54e018e7cffd36b81419b54a5c946a9fe
+oid sha256:134616c5175b1859b10e1348047fd02338d55705f285410aa8f7fdae509fbe5f
 size 3643