Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9882e08f77ef61cf3890e4d49b37e6a04999c83de772ce9c5cd467521d72f0f
+oid sha256:055564f687620d7d6550f30d9c9dcf699d2c2e87fb4ca1b56fed0741161d3f41
 size 267832560

run-3/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-3/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055564f687620d7d6550f30d9c9dcf699d2c2e87fb4ca1b56fed0741161d3f41
+size 267832560

run-3/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda87bcf8e52682803351a3fc2681131b0d9bd579ffff4e68c39debe725e894e
+size 535727290

run-3/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e82e8e5c924089bf2d105c906ca0a273a99d7892d3964255fbc0c1f9f92600
+size 14308

run-3/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41163f09fa6c0e61e44e220a575458c8987ab1e5310ee7aeaa30f98cd9661167
+size 1064

run-3/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-3/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-3/checkpoint-2138/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.4863512385958954,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1069",
+  "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": 1.2538588476474406e-05,
+      "loss": 0.5581,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.711180516622632e-06,
+      "loss": 0.4917,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48650237917900085,
+      "eval_matthews_correlation": 0.4863512385958954,
+      "eval_runtime": 0.7606,
+      "eval_samples_per_second": 1371.338,
+      "eval_steps_per_second": 86.777,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.883772556770861e-06,
+      "loss": 0.3582,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0563645969190893e-06,
+      "loss": 0.3426,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5801453590393066,
+      "eval_matthews_correlation": 0.48193970397464586,
+      "eval_runtime": 0.7674,
+      "eval_samples_per_second": 1359.149,
+      "eval_steps_per_second": 86.006,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 75365670622848.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6365996436326178e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 33
+  }
+}

run-3/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9616c49508ca82d01d650e6cbc7fedd5e4cbf7972d56a7566bab0f1e347efa
+size 4792

runs/Dec23_01-44-29_cab255cafe95/events.out.tfevents.1703296464.cab255cafe95.13310.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5035e4fc64c86a983db37b52f15d712da8fc1f84acdfbbfd63e22b8af4cb4eb5
-size 5150
+oid sha256:f377326094fe414bf4a97496b7ccd653354d7153845f8cf74744d53a4175570f
+size 5996