Training in progress, epoch 1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a548db670667b39e6e00288a18aaaf48d52bd80b56c9d3f6aff058ca916a8d
+oid sha256:5d3dcb8db9e9a4344360a99db7d4e33b152ae516c9694d490c6b2e0f886fc60b
 size 98725415

run-1/checkpoint-107/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-1/checkpoint-107/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75695d0ec28e65956fdbc99a40eb0b7cdf1896f11e0eebff858a4d2adac3c7cc
-size 197593757
+oid sha256:02f7298883f12e26bcdf8d0fff70dae073d4771a5b9a81361edc5cfb35b1ac8c
+size 197314895

run-1/checkpoint-107/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab35835b51e69dc0d866f1a96b23c8b60392e9925e9f4953ccc19005e2139269
-size 14244
+oid sha256:9b6f0c18fbee1d7f8ad376fa794f0006133beee1128d6a7f90af52d714eb9c2d
+size 14639

run-1/checkpoint-107/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90d19029660688f403eead20211ac214c74b0a60595ca447132c47b3eaed519
-size 1064
+oid sha256:c4ff4443ed6e43081c45888f1e4cb88d8a11b2d262952f1e95f9f6232849a6cd
+size 627

run-1/checkpoint-107/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-1/checkpoint-107/trainer_state.json

@@ -1,8 +1,7 @@
 {
-  "best_metric": -0.018847626164931814,
+  "best_metric": 0.06620236880686593,
   "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-1/checkpoint-107",
   "epoch": 1.0,
-  "eval_steps": 500,
   "global_step": 107,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
@@ -10,26 +9,22 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.9640177488327026,
-      "eval_matthews_correlation": -0.018847626164931814,
-      "eval_runtime": 2.6187,
-      "eval_samples_per_second": 398.297,
-      "eval_steps_per_second": 25.204,
+      "eval_loss": 2033.5955810546875,
+      "eval_matthews_correlation": 0.06620236880686593,
+      "eval_runtime": 2.3881,
+      "eval_samples_per_second": 436.757,
+      "eval_steps_per_second": 27.638,
       "step": 107
     }
   ],
-  "logging_steps": 500,
   "max_steps": 107,
-  "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.5492555631387056e-05,
+    "learning_rate": 1.9906632280964458e-05,
     "num_train_epochs": 1,
     "per_device_train_batch_size": 8,
-    "seed": 27
+    "seed": 37
   }
 }

run-1/checkpoint-107/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11fe290c72177dbff95233c8663ee7f96cc2591331d417e8290c19d95336fe8f
-size 4920
+oid sha256:4b137d57fb347739b81396c98a7da4b9009e311d363bc98388c1f9ac467155ae
+size 3643

runs/Mar10_12-23-35_f87fe01c66be/1710074385.1919856/events.out.tfevents.1710074385.f87fe01c66be.29486.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07f60f1b8511f3102d63942778d61f7a1df5c11461678bab17cf7d4325f8829e
+size 5884

runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710074345.f87fe01c66be.29486.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f6e7eebba9db24bd6600664933a530d3362b88a1375466112c4ae6e6dcfd4f
-size 4604
+oid sha256:2989ddf43b510bc0547d7768ad0b1464b4f4a2d2ecab93a01e5a8787200ad2a2
+size 4952

runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710074385.f87fe01c66be.29486.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdeb3566beba25ecd1bb0f173b126b092963a5b3df64c3a63c83f89cffad3b09
+size 4604

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32916f54e2646003ed29b16234a983b2b91c71ca7bff0aec272cd719ceb38019
+oid sha256:4b137d57fb347739b81396c98a7da4b9009e311d363bc98388c1f9ac467155ae
 size 3643