Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45c3ba60a60dff294267f3bea2ba45ed664d24bfe50bf5d02c09d52ea6d967f
+oid sha256:b81d1cde9ce9fa79f45b951a8bc435cc75ed206aab0999ba52f97181882307c8
 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": "4.39.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81d1cde9ce9fa79f45b951a8bc435cc75ed206aab0999ba52f97181882307c8
+size 267832560

run-0/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2043c1d346659b9bf07a03c2f13e6e0e547c179d3d3c66132711f9d4fd02fc28
+size 535727290

run-0/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26af2b4948d1fe8968a3b7386be83753654d6dfda0a8712c9351d45576bdacf
+size 14244

run-0/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da67596f93e1265e3f13e345c13be86d473d6cc8b75854c0b7d830a0ca947fa4
+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": 0.402173248634525,
+  "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": 0.5428110361099243,
+      "eval_matthews_correlation": 0.16816948860566025,
+      "eval_runtime": 0.759,
+      "eval_samples_per_second": 1374.206,
+      "eval_steps_per_second": 86.958,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.443307876586914,
+      "learning_rate": 1.5262367752217109e-06,
+      "loss": 0.5463,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5213160514831543,
+      "eval_matthews_correlation": 0.402173248634525,
+      "eval_runtime": 0.7335,
+      "eval_samples_per_second": 1421.887,
+      "eval_steps_per_second": 89.976,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 95368506545292.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.036494629204788e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 23
+  }
+}

run-0/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf874ce22791d9f1993c027b375528da647df85379a06a734ed6731c3d7f669
+size 4984

runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160300.52e0cb6c1736.459.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36997bc96cd4731543e5f1ceb24965e8b6b70bea3b4dfb1765f4a6b78fe687f0
-size 4921
+oid sha256:a026122fa53a34719107c827ec166d87385f39d4e31da964ccdb2c8c12bc44be
+size 5467