Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ce79a93171c7fac1d8d2cec4d14117b0d67f2c1a13ae9c193efa6d0885e5f9
+oid sha256:b80c424485b9c3c5eba6ebd458009ca761dbaa2e8de5dacded457209de1e331d
 size 267832560

run-0/checkpoint-1070/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": "4.41.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80c424485b9c3c5eba6ebd458009ca761dbaa2e8de5dacded457209de1e331d
+size 267832560

run-0/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7201bfdb94004407b369dc28ba1e713e1533de56e1b39b9016ebbb763235de86
+size 535727290

run-0/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b535181cb9c2a1afbdc4de90ce0dd0c37c60c5a8d80d84537f151e98b1d6c3b
+size 14244

run-0/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72c396af8dd878d8492b83b28f68e560422d57a35b48612d38a726eab6101ca
+size 1064

run-0/checkpoint-1070/special_tokens_map.json

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

run-0/checkpoint-1070/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-0/checkpoint-1070/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.19076704585900842,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1070",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 2.1133761405944824,
+      "learning_rate": 1.2463453586617104e-06,
+      "loss": 0.6018,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.575204074382782,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.971,
+      "eval_samples_per_second": 1074.116,
+      "eval_steps_per_second": 134.908,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 4.266573905944824,
+      "learning_rate": 6.82388182796683e-07,
+      "loss": 0.5438,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.54793781042099,
+      "eval_matthews_correlation": 0.19076704585900842,
+      "eval_runtime": 1.3928,
+      "eval_samples_per_second": 748.864,
+      "eval_steps_per_second": 94.057,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 85437332526912.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.8103025345267377e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 40
+  }
+}

run-0/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fcef4eee61fb187280f3ff80b3955a537cbf7caa39c30fbf8e6226870c957a
+size 5176

runs/Jun16_07-07-37_5152ff55fb03/events.out.tfevents.1718522299.5152ff55fb03.1457.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6d2149cf5ea2cac0bf8dbf45232172112791cd0459931b896facae9b4f4094
-size 5334
+oid sha256:1ab0b04aa76ac81daf1c679d6ab70500151c22c3b8c26040fbb786c9bb08e803
+size 5880