Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0b11a066b5b85812fc06a84ae4968da5eacdbd054d62f07b18f68dc3bc0151
+oid sha256:cffb7a8e9ee30295ab5e972de99fe26e741caafcbd7831d33afd03395f81b23a
 size 267832560

run-9/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-9/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7910ea5112c67305d1fa48677dbe7a8d460cea780a0d71f701a716b4f0a9504b
+size 267832560

run-9/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b217b3dd2baa9845d475a953dc2d9e459d36e228619fdcba1fb44545260a288
+size 535727290

run-9/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2911afa4abdeeb57e3580afaa7ddf8091c39843d465e0ac3e03cfaa2cdd804
+size 14308

run-9/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ae5a53285e13e008c8a1124ec8250c886871cf4563770c68621329095eeb2a
+size 1064

run-9/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-9/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-9/checkpoint-2138/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.5117946747628033,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/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": 1.942054911488753e-05,
+      "loss": 0.5525,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5833451014612775e-05,
+      "loss": 0.4922,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4696793258190155,
+      "eval_matthews_correlation": 0.4691032179514943,
+      "eval_runtime": 0.7564,
+      "eval_samples_per_second": 1378.966,
+      "eval_steps_per_second": 87.26,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.2246352914338016e-05,
+      "loss": 0.364,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.659254814063262e-06,
+      "loss": 0.3351,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6338055729866028,
+      "eval_matthews_correlation": 0.5117946747628033,
+      "eval_runtime": 0.84,
+      "eval_samples_per_second": 1241.606,
+      "eval_steps_per_second": 78.568,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 134171622786756.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3007647215162288e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-9/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca0d14927e03b866cc3e1bf18d0c09980fa2cb73785088015390dc1d85c1cbc
+size 4792

run-9/checkpoint-3207/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-9/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffb7a8e9ee30295ab5e972de99fe26e741caafcbd7831d33afd03395f81b23a
+size 267832560

run-9/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5333ad881afab25edb94a35270040bf77ff403c831303c89ac7be37b299fe0
+size 535727290

run-9/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01282e5fd4f25eaa9ace4dd4e05976fe70604c63993f2e2d23b3271c46eac390
+size 14308

run-9/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c44188bd38b678a8b7f010ca0bb818e9ef5e620c69fe52208340a7ab2da0553
+size 1064

run-9/checkpoint-3207/special_tokens_map.json

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

run-9/checkpoint-3207/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-9/checkpoint-3207/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": 0.5235221651747541,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-3207",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3207,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.942054911488753e-05,
+      "loss": 0.5525,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5833451014612775e-05,
+      "loss": 0.4922,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4696793258190155,
+      "eval_matthews_correlation": 0.4691032179514943,
+      "eval_runtime": 0.7564,
+      "eval_samples_per_second": 1378.966,
+      "eval_steps_per_second": 87.26,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.2246352914338016e-05,
+      "loss": 0.364,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.659254814063262e-06,
+      "loss": 0.3351,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6338055729866028,
+      "eval_matthews_correlation": 0.5117946747628033,
+      "eval_runtime": 0.84,
+      "eval_samples_per_second": 1241.606,
+      "eval_steps_per_second": 78.568,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.072156713788506e-06,
+      "loss": 0.2633,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.4850586135137493e-06,
+      "loss": 0.2356,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7711848020553589,
+      "eval_matthews_correlation": 0.5235221651747541,
+      "eval_runtime": 0.7565,
+      "eval_samples_per_second": 1378.793,
+      "eval_steps_per_second": 87.249,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 171808922429892.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3007647215162288e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-9/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca0d14927e03b866cc3e1bf18d0c09980fa2cb73785088015390dc1d85c1cbc
+size 4792

runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298952.48296f50e732.508.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d482aaf6c80aab8d29bb2ddc527fa8b8e82210695f8ccca74b13b541e5e0ab77
-size 5801
+oid sha256:3db1006dd3e4bc76a46a6dc499093b64f3bcb33d9095c2686ec520e86a9c754c
+size 6647