Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa16f4ad7735629159d0b17c8bb6475106028ef4c08958f9e4cfe8ee468271e
+oid sha256:682075003b57e601a8439ef50dd57a6fc26442079b6fc6e7b62c08b98b8f1a23
 size 267829484

run-4/checkpoint-144/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e62ba66a89926e77077e6643bf2908a9a0bfc9b6548d3f16923c4d229e189272
+oid sha256:67b96031aac114c6e35186c47bedb6093c9b1d8d7a35080d4af0e5427b7c0e7a
 size 267829484

run-4/checkpoint-144/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48acbba456f3eac77a3b888b44b914aa7af737743f83dfc1e9593d2d071663a1
+oid sha256:eb35cac1bb27bfb5fff6849dd603b20c0df6498f36f3c3399382e82c90dbfd99
 size 535721146

run-4/checkpoint-144/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab93f76e719fdcd90ef1bc59d1f118a003512417a83f1cb95fcf287d4ab5ea6
+oid sha256:ba4ef1c5e753a9401f18db6dd0e9badc9fb4e3e4956aafa5bbed209ec8cba9e0
 size 14244

run-4/checkpoint-144/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fe60709b17fdd284b4ee879ece7df87e285ef6401bd27d6fc1fa16511dc539
+oid sha256:a78e4fab71e71f8cfdac39d3ebd41054aafb6de39f3ccc727afec93c8a6994f8
 size 1064

run-4/checkpoint-144/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.5270714523203409,
+  "best_metric": 0.8072119226154155,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-144",
-  "epoch": 4.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 144,
   "is_hyper_param_search": true,
@@ -10,57 +10,37 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 3.607897996902466,
-      "eval_pearson": 0.20189901594611118,
-      "eval_runtime": 0.9286,
-      "eval_samples_per_second": 1615.373,
-      "eval_spearmanr": 0.19575057246397828,
-      "eval_steps_per_second": 101.23,
-      "step": 36
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 2.214840888977051,
-      "eval_pearson": 0.22452541125699038,
-      "eval_runtime": 0.9301,
-      "eval_samples_per_second": 1612.779,
-      "eval_spearmanr": 0.24754498733937647,
-      "eval_steps_per_second": 101.067,
+      "eval_loss": 1.9030543565750122,
+      "eval_pearson": 0.6173001362903047,
+      "eval_runtime": 0.7967,
+      "eval_samples_per_second": 1882.655,
+      "eval_spearmanr": 0.6065460603935124,
+      "eval_steps_per_second": 117.98,
       "step": 72
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 2.1850011348724365,
-      "eval_pearson": 0.44427892419195647,
-      "eval_runtime": 0.9423,
-      "eval_samples_per_second": 1591.797,
-      "eval_spearmanr": 0.4862668413482525,
-      "eval_steps_per_second": 99.753,
-      "step": 108
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 2.1628456115722656,
-      "eval_pearson": 0.5270714523203409,
-      "eval_runtime": 0.9378,
-      "eval_samples_per_second": 1599.452,
-      "eval_spearmanr": 0.5570093927998047,
-      "eval_steps_per_second": 100.232,
+      "epoch": 2.0,
+      "eval_loss": 1.0358508825302124,
+      "eval_pearson": 0.8072119226154155,
+      "eval_runtime": 0.8084,
+      "eval_samples_per_second": 1855.522,
+      "eval_spearmanr": 0.8100114657508573,
+      "eval_steps_per_second": 116.279,
       "step": 144
     }
   ],
   "logging_steps": 500,
-  "max_steps": 144,
+  "max_steps": 288,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 6.104946209890916e-06,
+    "learning_rate": 2.5574276250903696e-05,
     "num_train_epochs": 4,
-    "per_device_train_batch_size": 16,
-    "seed": 9
+    "per_device_train_batch_size": 8,
+    "seed": 40
   }
 }

run-4/checkpoint-144/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a91a99dd245b7ad0b44d46d2003409907fbff02d5cbdc46820df8e68c16a2dbf
+oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
 size 4920

run-4/checkpoint-216/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-4/checkpoint-216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e7ed4567edaf8cafd3b04aab5b2c4357198ecc55e0a732fb05e92389af23be
+size 267829484

run-4/checkpoint-216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445fbf7678428da33cc6ef3dab5c6183654679f7828b6489a42b3512166af7e3
+size 535721146

run-4/checkpoint-216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038e71594f5547a63cb7e467f33b50c0377a188cf2dc5dbbab756833f58c85c4
+size 14244

run-4/checkpoint-216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a286dc983477a9eeb41942ec56313b71758475c64c11b6678337da3196238271
+size 1064

run-4/checkpoint-216/special_tokens_map.json

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

run-4/checkpoint-216/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-4/checkpoint-216/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.811708722217708,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-216",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.9030543565750122,
+      "eval_pearson": 0.6173001362903047,
+      "eval_runtime": 0.7967,
+      "eval_samples_per_second": 1882.655,
+      "eval_spearmanr": 0.6065460603935124,
+      "eval_steps_per_second": 117.98,
+      "step": 72
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0358508825302124,
+      "eval_pearson": 0.8072119226154155,
+      "eval_runtime": 0.8084,
+      "eval_samples_per_second": 1855.522,
+      "eval_spearmanr": 0.8100114657508573,
+      "eval_steps_per_second": 116.279,
+      "step": 144
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8175650238990784,
+      "eval_pearson": 0.811708722217708,
+      "eval_runtime": 0.7965,
+      "eval_samples_per_second": 1883.148,
+      "eval_spearmanr": 0.81090938379838,
+      "eval_steps_per_second": 118.011,
+      "step": 216
+    }
+  ],
+  "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": 2.5574276250903696e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 40
+  }
+}

run-4/checkpoint-216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
+size 4920

run-4/checkpoint-288/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-4/checkpoint-288/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6125377ff48a62c6d03a21d9fb4b335d9f21de4693c8cb1a630ff4548111d41e
+size 267829484

run-4/checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aabc147b2850bcbb51f8aa3dae263c5d15dc8141718fe77ade4c5df57146576
+size 535721146

run-4/checkpoint-288/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f626927ff09c9fc535421ec8dad43c9dbeb3494a6f853f65416b0df7692c7c0
+size 14244

run-4/checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde1ecae63baaddae85f5be9fd342ed6778060c6fd18855f3528ca3e88271967
+size 1064

run-4/checkpoint-288/special_tokens_map.json

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

run-4/checkpoint-288/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-4/checkpoint-288/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.8210299726217956,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-288",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 288,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.9030543565750122,
+      "eval_pearson": 0.6173001362903047,
+      "eval_runtime": 0.7967,
+      "eval_samples_per_second": 1882.655,
+      "eval_spearmanr": 0.6065460603935124,
+      "eval_steps_per_second": 117.98,
+      "step": 72
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0358508825302124,
+      "eval_pearson": 0.8072119226154155,
+      "eval_runtime": 0.8084,
+      "eval_samples_per_second": 1855.522,
+      "eval_spearmanr": 0.8100114657508573,
+      "eval_steps_per_second": 116.279,
+      "step": 144
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8175650238990784,
+      "eval_pearson": 0.811708722217708,
+      "eval_runtime": 0.7965,
+      "eval_samples_per_second": 1883.148,
+      "eval_spearmanr": 0.81090938379838,
+      "eval_steps_per_second": 118.011,
+      "step": 216
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7593460083007812,
+      "eval_pearson": 0.8210299726217956,
+      "eval_runtime": 0.8059,
+      "eval_samples_per_second": 1861.168,
+      "eval_spearmanr": 0.8175945414249048,
+      "eval_steps_per_second": 116.633,
+      "step": 288
+    }
+  ],
+  "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": 2.5574276250903696e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 40
+  }
+}

run-4/checkpoint-288/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
+size 4920

run-6/checkpoint-36/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-6/checkpoint-36/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682075003b57e601a8439ef50dd57a6fc26442079b6fc6e7b62c08b98b8f1a23
+size 267829484

run-6/checkpoint-36/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb967429e79d5994e9bbee53ee756e4bd485fb25770e317eb5d665d5624aa4a
+size 535721146

run-6/checkpoint-36/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1759e9e584a8dfdbc46ee44ac9cb0fa528dc393f134f4baed8bc200cff4e9da6
+size 14244

run-6/checkpoint-36/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ed83d51e7a677680096eee72a2f302a4690ed8aa59b8b755d6677d26162cda
+size 1064

run-6/checkpoint-36/special_tokens_map.json

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

run-6/checkpoint-36/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-6/checkpoint-36/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.5682043731058958,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-6/checkpoint-36",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.9094555377960205,
+      "eval_pearson": 0.5682043731058958,
+      "eval_runtime": 0.8058,
+      "eval_samples_per_second": 1861.603,
+      "eval_spearmanr": 0.5712894898305707,
+      "eval_steps_per_second": 116.66,
+      "step": 36
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "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": 5.712636964604973e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 36
+  }
+}

run-6/checkpoint-36/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f7a49d428cc1a74ed02b4fda35aa90bed1b7778219bce664edeb44d1f7e361
+size 4920

runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752299.8a0d46b883ab.2624.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad5eed2f3c046092c5a21823082b1a7d17ca1c705ab721131332ce3b1154ebd
+size 4981

runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752304.8a0d46b883ab.2624.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88225183ae7ed111b0b79d8272c60931d239d29f05a81698b112152de0aab9bf
+size 6059

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
+oid sha256:09f7a49d428cc1a74ed02b4fda35aa90bed1b7778219bce664edeb44d1f7e361
 size 4920