Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8d26d8a66510399de6491695e4b665308e1c7491987faa7235bcc54420c820
+oid sha256:8c10a863d2024a16eabdb38f36ff1b877741cf800f424ffde7bb1d789ce6bf2a
 size 267832560

run-1/checkpoint-2138/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": "4.36.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c10a863d2024a16eabdb38f36ff1b877741cf800f424ffde7bb1d789ce6bf2a
+size 267832560

run-1/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47b6f83d386fa4d034def2f98d698fca4112195349f9da0f8e12e89e085d120
+size 535727290

run-1/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a2e16f1ea1471458175c4ba68043637f6d6ee28de6970ff4bfa08e7a6ad823
+size 14244

run-1/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7324550fd6a275553df67d00fca12195160f5d5c7b8404c97821cb10ff18545
+size 1064

run-1/checkpoint-2138/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-2138/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-1/checkpoint-2138/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.4854632779262472,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.972945030670128e-05,
+      "loss": 0.5666,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0654526525656932e-05,
+      "loss": 0.5211,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5038339495658875,
+      "eval_matthews_correlation": 0.4051130128677346,
+      "eval_runtime": 0.7912,
+      "eval_samples_per_second": 1318.257,
+      "eval_steps_per_second": 83.418,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1579602744612585e-05,
+      "loss": 0.3564,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.50467896356824e-06,
+      "loss": 0.3321,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6782745122909546,
+      "eval_matthews_correlation": 0.4854632779262472,
+      "eval_runtime": 0.7525,
+      "eval_samples_per_second": 1386.109,
+      "eval_steps_per_second": 87.712,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 75607578860628.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.8804374087745627e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 18
+  }
+}

run-1/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909fa524061d6512cdc9000093fba071240645db37ca2a337df7a8b6661c2561
+size 4792

runs/Dec22_07-12-50_84c4b1f8dc6c/events.out.tfevents.1703229756.84c4b1f8dc6c.518.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41bf3f31d93b1c295224953698794183324f47fa3682b2274ba75b099531ed91
-size 5147
+oid sha256:245ec06bca1e35f4a577d69861e32a71b5753d0d271be6afd836d82981d40497
+size 5993