Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5532eacb19539cc92d43257b0ea0db854bae37c452c8278162825aa2bb5f0a
+oid sha256:ab41e82c228d8f150e54a59d833c05ac5f781cf932a0c37eb815c398e0f57c0c
 size 437958648

run-2/checkpoint-270/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-270/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07451da21ccb792dd90d49fd72a57a75570d2a1261df0d51e91c84a1e10db348
+size 437958648

run-2/checkpoint-270/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46c1cb578b0335ab9587af0e0d372fa370ebd5afa73428b14fc5549232a4e5b
+size 876038394

run-2/checkpoint-270/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcdf6a962f8e9377adf6478f9058c09825747228afe344b044ccda4701f1351
+size 14308

run-2/checkpoint-270/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18f549909ad51f109e44fc57157b1efdcdf92fa66dad0ddb775fa74eb078544
+size 1064

run-2/checkpoint-270/special_tokens_map.json

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

run-2/checkpoint-270/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-270/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.06479227964096512,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-54",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 270,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6800838708877563,
+      "eval_matthews_correlation": 0.06479227964096512,
+      "eval_runtime": 1.3179,
+      "eval_samples_per_second": 791.421,
+      "eval_steps_per_second": 50.08,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6333577036857605,
+      "eval_matthews_correlation": 0.06354272869611655,
+      "eval_runtime": 1.4106,
+      "eval_samples_per_second": 739.39,
+      "eval_steps_per_second": 46.788,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6208921074867249,
+      "eval_matthews_correlation": 0.04129856774209186,
+      "eval_runtime": 3.1494,
+      "eval_samples_per_second": 331.174,
+      "eval_steps_per_second": 20.956,
+      "step": 162
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.615740180015564,
+      "eval_matthews_correlation": 0.0407377624184135,
+      "eval_runtime": 3.8341,
+      "eval_samples_per_second": 272.03,
+      "eval_steps_per_second": 17.214,
+      "step": 216
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6141827702522278,
+      "eval_matthews_correlation": 0.049848138106847704,
+      "eval_runtime": 1.3956,
+      "eval_samples_per_second": 747.371,
+      "eval_steps_per_second": 47.293,
+      "step": 270
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.420124179212326e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 26
+  }
+}

run-2/checkpoint-270/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42783ab338ba78bc9a261fef02bd6d857622f28fcbf5b914d81d574b8f77a67
+size 4920

run-3/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad205eb70a581ad8b5fb7fdef160c29c51ccc7322fb925c298680a6d45ea54c0
+oid sha256:ab41e82c228d8f150e54a59d833c05ac5f781cf932a0c37eb815c398e0f57c0c
 size 437958648

run-3/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69c87de4a22389003fc531f17e26b0497d7341ff972eb8cf703fec968ff7f77
+oid sha256:32f4a288a5427e9dada6edb4c6993e6b5e24dc62b36d675d83b3f04d8b8b98b9
 size 876038394

run-3/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:190ed7e16b7dd169c6b481d5991795f911c91f8173dc280bbfdc780cdff13754
+oid sha256:73ccdd151ac8d1156e8347ba126b5af26d4c09b5e16c2d468dceec482eedd9b8
 size 14244

run-3/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616a72f3abb3b56a7b99fb5738365e66552337efc9458dcc66d9b099d03a2d3d
+oid sha256:881229adabc25afd84a75a33c814844da8e3149e444fc877758d26f7599013c5
 size 1064

run-3/checkpoint-54/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.008874995467744727,
+  "best_metric": 0.0,
   "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-3/checkpoint-54",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6695083975791931,
-      "eval_matthews_correlation": 0.008874995467744727,
-      "eval_runtime": 1.3066,
-      "eval_samples_per_second": 798.284,
-      "eval_steps_per_second": 50.515,
+      "eval_loss": 0.613477885723114,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.303,
+      "eval_samples_per_second": 800.44,
+      "eval_steps_per_second": 50.651,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 162,
+  "max_steps": 54,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.169206507177718e-06,
-    "num_train_epochs": 3,
+    "learning_rate": 1.344131587717838e-05,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 16,
-    "seed": 38
+    "seed": 16
   }
 }

run-3/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681009adf129985f1b550e6f1e9a7faeef8564fd524685bfc7430d9426ac9489
+oid sha256:c5c47c2cd3e51fcc7e19abd77db424201098a3bfa026aa7349d75ad812a50ed7
 size 4920

runs/Mar05_08-21-06_22d65867544c/events.out.tfevents.1709629091.22d65867544c.687.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2593cb0d2db5c30f559f556d6d87151dd1a04aae366a05521301b7a75931a8ef
+size 5313

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42783ab338ba78bc9a261fef02bd6d857622f28fcbf5b914d81d574b8f77a67
+oid sha256:c5c47c2cd3e51fcc7e19abd77db424201098a3bfa026aa7349d75ad812a50ed7
 size 4920