Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f641b610c3774edf49c88d4ee959e7069d39793234bf5385c7fe81c66126ac2b
+oid sha256:193eafc1a8a054e2125b9000585ca1e9ef912e9070ea24787555b3596dd2f1c6
 size 267829484

run-0/checkpoint-72/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-72/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193eafc1a8a054e2125b9000585ca1e9ef912e9070ea24787555b3596dd2f1c6
+size 267829484

run-0/checkpoint-72/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4624a6bd1a8f3668bdd4bbd491024e1a328d9f0ca3d221b13d1cdef02946c510
+size 535721146

run-0/checkpoint-72/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4bccc032167d6736137944244a6658841689a7a7b626ec227ea770908c36c8
+size 14244

run-0/checkpoint-72/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772f7bd0e0fd1749f17173eb0e130ffc4c7670795655ba0893854f1f9bc385d5
+size 1064

run-0/checkpoint-72/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-72/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-72/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.7567095621264116,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-72",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0813779830932617,
+      "eval_pearson": 0.7567095621264116,
+      "eval_runtime": 0.9163,
+      "eval_samples_per_second": 1637.038,
+      "eval_spearmanr": 0.7572162649891061,
+      "eval_steps_per_second": 102.588,
+      "step": 72
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 288,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.8584811748752325e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 40
+  }
+}

run-0/checkpoint-72/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9a09d3e6d841ee4f64161d2a8c27492f996273463a537d8f3f6e05968d37fe
+size 4920

runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709675915.fe13c9557656.828.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440f684f615e35018cce413c625605e335a7ec3f5f47344931a3f83fde63aacd
+size 4975

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e59c704ac80cace0ae69aaa6a2234c640b577b1460318fc785124be9b89222d
+oid sha256:fd9a09d3e6d841ee4f64161d2a8c27492f996273463a537d8f3f6e05968d37fe
 size 4920