Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd60892855368adab2635b1abf61c8d8782ca78b3194afc97b781d08eff95df
+oid sha256:8357e3cf72ba41bd25262090e6e95281616150b9d952eb10a025c0d1de28ad8f
 size 267832560

run-4/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": "4.40.0",
+  "vocab_size": 30522
+}

run-4/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8357e3cf72ba41bd25262090e6e95281616150b9d952eb10a025c0d1de28ad8f
+size 267832560

run-4/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a0e9d232b41c493283ca7b6a39856bdd39f9d3476b7198d061b702b2fc5b73
+size 535724410

run-4/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb810bab9e4831414c4acb4e04fccf084c387b368d924ebcea64e52b3fbd3a9
+size 14054

run-4/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1d97994b24fb42d1a3d336e07ce7b5f92d0a5fd8f7845b28eeb50f9bc2638c
+size 1064

run-4/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-4/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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-536/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.47854164992705517,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.5019019842147827,
+      "eval_matthews_correlation": 0.40644314565079237,
+      "eval_runtime": 27.9447,
+      "eval_samples_per_second": 37.324,
+      "eval_steps_per_second": 2.362,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 6.935309410095215,
+      "learning_rate": 8.001458853591762e-06,
+      "loss": 0.485,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4858323633670807,
+      "eval_matthews_correlation": 0.47854164992705517,
+      "eval_runtime": 28.7617,
+      "eval_samples_per_second": 36.264,
+      "eval_steps_per_second": 2.295,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 95845337435376.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2764231980729716e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 24
+  }
+}

run-4/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19411c681d04745834060671fa9537cbeac30cebb34e847f78553376e4a242cd
+size 5048

runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713898062.309eb7d6022b.9612.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da993dada9dea456c5ef7bf521ef35c742563ff9ac0120e113b61285eb9f5b0d
-size 4986
+oid sha256:cde52a2243f61228979a2a7e5f1ed083292c6b1a14485782703222cad7997dc7
+size 5532