Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46e35262045695fe779ab9798365ffe0dd352674fe9d0ab12ca395987638eae
+oid sha256:5386555c23a3845ebed14108419d4c40442962dff0e8f0c3c2adccae7ef8d069
 size 267832560

run-0/checkpoint-536/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": "4.39.3",
+  "vocab_size": 30522
+}

run-0/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5386555c23a3845ebed14108419d4c40442962dff0e8f0c3c2adccae7ef8d069
+size 267832560

run-0/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5048653cea997fc66740ad8c3182caea5dba515b40df4cce6ac57b90eda46c
+size 535727290

run-0/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f827f37a1c9c2084582a7eebf927c4456d10117d230821f32569b32524a79921
+size 14244

run-0/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432f41fd2b6c42dd373353006f4bf55930d7735fb4d57b5ee114989a0bd8a061
+size 1064

run-0/checkpoint-536/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-536/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-536/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.44944855113368687,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-536",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5017370581626892,
+      "eval_matthews_correlation": 0.4386209168112411,
+      "eval_runtime": 0.9474,
+      "eval_samples_per_second": 1100.94,
+      "eval_steps_per_second": 69.666,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.115137100219727,
+      "learning_rate": 1.255312161688088e-06,
+      "loss": 0.4596,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.506603479385376,
+      "eval_matthews_correlation": 0.44944855113368687,
+      "eval_runtime": 0.7486,
+      "eval_samples_per_second": 1393.184,
+      "eval_steps_per_second": 88.159,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 95049498141888.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.8690203296244868e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 15
+  }
+}

run-0/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336fcd2eac216245af8a43eb6ce3300c8207fb1556028581e1cfb293d1259711
+size 4984

runs/Apr05_13-35-05_48c5213de69d/events.out.tfevents.1712324929.48c5213de69d.790.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31a8d26101534edefc7c8be0c81931c65fd4ee7523183ad95ab7f1e2d135907
-size 4929
+oid sha256:8f225ef593f792719fb7cf4043e01ee62bac9eebd2b96128a96b74b1ffeff670
+size 5829