Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75ef795694a37c59eabe5580c8f71587d7bdb179153ffc025570cec3117e5a9
+oid sha256:e4c6e97dc9d7f6cba0bc6e33c3bca56fc1d04469546d0fb29b2ca1c4deff51d8
 size 267832560

run-7/checkpoint-108/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": "4.38.1",
+  "vocab_size": 30522
+}

run-7/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99d198a172ef6731b5444349a8154be6ddcb892d1d4349f1510c08fed9fe21b
+size 267832560

run-7/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f817c99621e83daf475bb83487c0fc89de1f430c960a969d4f3af323f7e561ae
+size 535727290

run-7/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54a361f238e28b9db2e8ee53cc7934e2a3c60530ced5ef737b8f9e89ecea631
+size 14308

run-7/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fef4ac30dc1e34199e9bf15d14a456964fa9ed04c711bde2b3c010548c53233
+size 1064

run-7/checkpoint-108/special_tokens_map.json

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

run-7/checkpoint-108/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-7/checkpoint-108/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.3312436955874473,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-108",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.586409866809845,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7287,
+      "eval_samples_per_second": 1431.276,
+      "eval_steps_per_second": 90.57,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5660433173179626,
+      "eval_matthews_correlation": 0.3312436955874473,
+      "eval_runtime": 0.7857,
+      "eval_samples_per_second": 1327.558,
+      "eval_steps_per_second": 84.007,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7959735372448385e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 20
+  }
+}

run-7/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd55c91aeb42289c4cefe7204fc1209bf65261be738db6a48600ffc171c38ba
+size 4984

run-7/checkpoint-162/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": "4.38.1",
+  "vocab_size": 30522
+}

run-7/checkpoint-162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622d53138d040ca64660df09796fc8563973dacc2572629865fb99b9068c936a
+size 267832560

run-7/checkpoint-162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0cab478017d84a49b494779141442ff1de5222eeb91fed8dc0ea86336b6016
+size 535727290

run-7/checkpoint-162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8872adf08e4ab32c4e97d1dc6e8f87379a6850658875411f6feb9a75c1d50e3
+size 14308

run-7/checkpoint-162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8ed5d97df025efc10808521b69b1d3a4b7831a7ba83395c48f508d725c8c4a
+size 1064

run-7/checkpoint-162/special_tokens_map.json

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

run-7/checkpoint-162/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-7/checkpoint-162/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.3312436955874473,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-108",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 162,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.586409866809845,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7287,
+      "eval_samples_per_second": 1431.276,
+      "eval_steps_per_second": 90.57,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5660433173179626,
+      "eval_matthews_correlation": 0.3312436955874473,
+      "eval_runtime": 0.7857,
+      "eval_samples_per_second": 1327.558,
+      "eval_steps_per_second": 84.007,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6065305471420288,
+      "eval_matthews_correlation": 0.32940166149822514,
+      "eval_runtime": 0.7822,
+      "eval_samples_per_second": 1333.359,
+      "eval_steps_per_second": 84.374,
+      "step": 162
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7959735372448385e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 20
+  }
+}

run-7/checkpoint-162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd55c91aeb42289c4cefe7204fc1209bf65261be738db6a48600ffc171c38ba
+size 4984

run-8/checkpoint-14/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": "4.38.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-14/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c6e97dc9d7f6cba0bc6e33c3bca56fc1d04469546d0fb29b2ca1c4deff51d8
+size 267832560

run-8/checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72fb97190fac5fbfe19b33e2d916d109e719bb32ca1227b94a9377da88c8e5b0
+size 535727290

run-8/checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0bc369b29d41a9e7b00637a61568cf186a63a65c9f4c40638e0a09d8a26917
+size 14244

run-8/checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64bd3899c482e0c4e8e06c8774f8c333d0221570b3de96cfcbbccd820de2bc1b
+size 1064

run-8/checkpoint-14/special_tokens_map.json

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

run-8/checkpoint-14/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-8/checkpoint-14/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.07665945899456443,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-14",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7001938819885254,
+      "eval_matthews_correlation": 0.07665945899456443,
+      "eval_runtime": 0.755,
+      "eval_samples_per_second": 1381.458,
+      "eval_steps_per_second": 87.417,
+      "step": 14
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.5791210224410365e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 64,
+    "seed": 27
+  }
+}

run-8/checkpoint-14/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bcec68b82ffa6e0dbb9043a22ee954608e013dc4b9efdb11625c6eff6cbe35
+size 4984

runs/Feb27_13-15-48_39d530476097/events.out.tfevents.1709040952.39d530476097.262.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4fc34d2412622746989e64152e1f1074b7772f91494c51b43abe31d3a4dad2
+size 5220

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd55c91aeb42289c4cefe7204fc1209bf65261be738db6a48600ffc171c38ba
+oid sha256:14bcec68b82ffa6e0dbb9043a22ee954608e013dc4b9efdb11625c6eff6cbe35
 size 4984