Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db52acd502c4e20e3b7af750eb92b81ade4a18e85c7dc1aa28253bdbe0bb7de
+oid sha256:ed7607757531a0d94c65185f850961773e46fcb5d119d13e3863e3c032cea5c7
 size 267829484

run-0/checkpoint-9/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-9/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7607757531a0d94c65185f850961773e46fcb5d119d13e3863e3c032cea5c7
+size 267829484

run-0/checkpoint-9/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56767472c0e4d4198194df7f7120021bd7533a01fa83803560f3bf641087884b
+size 535721146

run-0/checkpoint-9/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0628cec758e075b259c6a730232907c8a667241d8e97a9db6dc34062350c612c
+size 14244

run-0/checkpoint-9/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d27024e44c494ad9fc8a5e273b59caa9e40de909254f40876c0dacfd47db5cf
+size 1064

run-0/checkpoint-9/special_tokens_map.json

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

run-0/checkpoint-9/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-0/checkpoint-9/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.11274566771797583,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-9",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 9,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.302802324295044,
+      "eval_pearson": 0.11274566771797583,
+      "eval_runtime": 0.9178,
+      "eval_samples_per_second": 1634.281,
+      "eval_spearmanr": 0.12987920930990302,
+      "eval_steps_per_second": 102.415,
+      "step": 9
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.481764265618048e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 34
+  }
+}

run-0/checkpoint-9/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c09fba38efbfaed97000a3a94d8c55aa1cde1316bbda4831aa4e5e1bd7ee7a7
+size 4920

runs/Mar07_00-50-37_758c92e55f7e/events.out.tfevents.1709772772.758c92e55f7e.2638.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048b3c57ec4cf0949fbf3aafd90be914f80ff1eb5e16c863e47520ab96394027
+size 5343

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8dad1552776a59ae9e978123a1e2d60c4f24fc4dc6daaa0fcd9a28a0700cc9
+oid sha256:5c09fba38efbfaed97000a3a94d8c55aa1cde1316bbda4831aa4e5e1bd7ee7a7
 size 4920