Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94908547df6ff7490766aff70d5a1eab6f9d3ef43a2f7b4cae0b81adf225d5f7
+oid sha256:cf56389d284dc967bd38dcf2944cabe6a3da7c03bca5a6af0caff09f7f6080d3
 size 267832560

run-1/checkpoint-4276/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": "4.45.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf56389d284dc967bd38dcf2944cabe6a3da7c03bca5a6af0caff09f7f6080d3
+size 267832560

run-1/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37219e41d50c17fe6a14fa18e664fcb1ed1313c2a94f391f4494308012d00910
+size 535727290

run-1/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b31091e06e34654f9cef4be26c7440466677bc00e19a83a73eaf034911434c
+size 14244

run-1/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438dd1dc0026992a320dffdd0a9e250c2dab5f43bdd58e58c180e8bbe0a9c9f0
+size 1064

run-1/checkpoint-4276/special_tokens_map.json

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

run-1/checkpoint-4276/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": false,
+  "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-1/checkpoint-4276/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.5538778174700708,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 4.76369571685791,
+      "learning_rate": 2.2292054345772622e-05,
+      "loss": 0.5655,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 15.750553131103516,
+      "learning_rate": 1.93402463021057e-05,
+      "loss": 0.4835,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.468739777803421,
+      "eval_matthews_correlation": 0.45788183343120153,
+      "eval_runtime": 0.7397,
+      "eval_samples_per_second": 1409.989,
+      "eval_steps_per_second": 89.223,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 2.3343119621276855,
+      "learning_rate": 1.6388438258438773e-05,
+      "loss": 0.3553,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 18.42914390563965,
+      "learning_rate": 1.3436630214771844e-05,
+      "loss": 0.3549,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5877938270568848,
+      "eval_matthews_correlation": 0.5113261407690263,
+      "eval_runtime": 0.7225,
+      "eval_samples_per_second": 1443.572,
+      "eval_steps_per_second": 91.348,
+      "step": 2138
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 66.43087005615234,
+      "learning_rate": 1.0484822171104921e-05,
+      "loss": 0.2535,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 2.8678722381591797,
+      "learning_rate": 7.533014127437994e-06,
+      "loss": 0.2356,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7891482710838318,
+      "eval_matthews_correlation": 0.5377587696044389,
+      "eval_runtime": 0.8084,
+      "eval_samples_per_second": 1290.228,
+      "eval_steps_per_second": 81.644,
+      "step": 3207
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 6.688732147216797,
+      "learning_rate": 4.581206083771068e-06,
+      "loss": 0.1868,
+      "step": 3500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 0.05465169623494148,
+      "learning_rate": 1.629398040104143e-06,
+      "loss": 0.1421,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8958505988121033,
+      "eval_matthews_correlation": 0.5538778174700708,
+      "eval_runtime": 0.8734,
+      "eval_samples_per_second": 1194.183,
+      "eval_steps_per_second": 75.567,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 150753332903676.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.524386238943955e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 11
+  }
+}

run-1/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3becf80cdc9221d5701481d18740c6b71586a42ea3a6944468cdacaf47dd2b83
+size 5304

runs/Oct02_05-18-55_0fd1839bafe2/events.out.tfevents.1727846874.0fd1839bafe2.228.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc83420981cb413444dfe7eb8715d8cc047d4ecae4a3be8ea43df6ab297dde6
-size 7407
+oid sha256:7a305522b20373f199996eca4954b0836a898ce6bb1c16aaa8862fdeda517e74
+size 8307