Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e553e2860acfded9c99abc744521668bf1b75b8efba3201285d4261d48a43acf
+oid sha256:62c13ed1752c5829337c9cd4f6c86a5dad2076b7710448fa0f9ac4b15b1c5e02
 size 267832560

run-1/checkpoint-17805/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": "4.37.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-17805/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c13ed1752c5829337c9cd4f6c86a5dad2076b7710448fa0f9ac4b15b1c5e02
+size 267832560

run-1/checkpoint-17805/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:719831f9c5119ef6664473732879b72bc14002fb939329b45761418535a1560a
+size 535727290

run-1/checkpoint-17805/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc061068a6b1f4c703b8f3f84ac136ff2a882d7aeab19db9a3e6c8bc6bdac140
+size 14244

run-1/checkpoint-17805/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:650606a32ed5fcac4a02b3c9ae294f00af8f7a70e9c8f5392362418b1bafdfd3
+size 1064

run-1/checkpoint-17805/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-17805/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-17805/trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": 0.8416666666666667,
+  "best_model_checkpoint": "relevant_model/run-1/checkpoint-17805",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 17805,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.101665655728474e-06,
+      "loss": 0.5111,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.078498947704027e-06,
+      "loss": 0.4216,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.0553322396795785e-06,
+      "loss": 0.4711,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.0321655316551306e-06,
+      "loss": 0.4472,
+      "step": 2000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.0089988236306835e-06,
+      "loss": 0.4429,
+      "step": 2500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.985832115606236e-06,
+      "loss": 0.5083,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.962665407581788e-06,
+      "loss": 0.469,
+      "step": 3500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.93949869955734e-06,
+      "loss": 0.4424,
+      "step": 4000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.916331991532892e-06,
+      "loss": 0.472,
+      "step": 4500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.893165283508445e-06,
+      "loss": 0.4344,
+      "step": 5000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.869998575483997e-06,
+      "loss": 0.4255,
+      "step": 5500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.846831867459549e-06,
+      "loss": 0.4293,
+      "step": 6000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.823665159435101e-06,
+      "loss": 0.4581,
+      "step": 6500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.8004984514106537e-06,
+      "loss": 0.4235,
+      "step": 7000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.777331743386206e-06,
+      "loss": 0.4334,
+      "step": 7500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.7541650353617583e-06,
+      "loss": 0.3703,
+      "step": 8000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.7309983273373104e-06,
+      "loss": 0.4415,
+      "step": 8500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.7078316193128626e-06,
+      "loss": 0.4234,
+      "step": 9000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.684664911288415e-06,
+      "loss": 0.4184,
+      "step": 9500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.661498203263967e-06,
+      "loss": 0.3912,
+      "step": 10000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.6383314952395193e-06,
+      "loss": 0.4158,
+      "step": 10500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.615164787215072e-06,
+      "loss": 0.3966,
+      "step": 11000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.591998079190624e-06,
+      "loss": 0.4171,
+      "step": 11500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.568831371166176e-06,
+      "loss": 0.381,
+      "step": 12000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.5456646631417285e-06,
+      "loss": 0.3867,
+      "step": 12500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5224979551172806e-06,
+      "loss": 0.4438,
+      "step": 13000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.4993312470928328e-06,
+      "loss": 0.3806,
+      "step": 13500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.4761645390683853e-06,
+      "loss": 0.391,
+      "step": 14000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.4529978310439374e-06,
+      "loss": 0.3947,
+      "step": 14500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.42983112301949e-06,
+      "loss": 0.397,
+      "step": 15000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.406664414995042e-06,
+      "loss": 0.4048,
+      "step": 15500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.383497706970594e-06,
+      "loss": 0.4648,
+      "step": 16000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.3603309989461466e-06,
+      "loss": 0.3751,
+      "step": 16500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.3371642909216987e-06,
+      "loss": 0.3951,
+      "step": 17000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.313997582897251e-06,
+      "loss": 0.4386,
+      "step": 17500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8416666666666667,
+      "eval_loss": 0.3926413059234619,
+      "eval_runtime": 7.7212,
+      "eval_samples_per_second": 512.357,
+      "eval_steps_per_second": 8.03,
+      "step": 17805
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 89025,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2758404863768208.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.124832363752922e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 40
+  }
+}

run-1/checkpoint-17805/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1edfb4d32c4b440688a42ad772fd577e72d0a24c0764a9f6c27730006d6a58ce
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df89df61b84ded72d02ff4835a2b8c5b60aca9d2d6b90b2f2b5c3e742846d5d1
+oid sha256:1edfb4d32c4b440688a42ad772fd577e72d0a24c0764a9f6c27730006d6a58ce
 size 4664