Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:137ea9a9d64c2fca4ff0672ce3b388497cdd88b583117dcb14cf56ef06450dd2
+oid sha256:81b8c78fe5026c94af7a8215ef418f077d1b268ab1a05d9f5b3ae585fa964aa3
 size 267829484

run-4/checkpoint-36/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

run-4/checkpoint-36/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bd7b149fb8cbcc4a98c1a500b77cf2498f7d115a33b7c3c58030ec49f7ab84
+oid sha256:d20118c73fee6e2ffd1a04b4ef9b5c0bae119e45aa91b1b9e7fbb3d10c8d80c0
 size 267829484

run-4/checkpoint-36/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b9ee39c83a3485f89033746bc673df88e46052d3beddf40596ab7d759b591dc
+oid sha256:66aa05a285d25e91b539d74ff9b7f232f2067ac95c9fbc27db8c037ef4626e8e
 size 535721146

run-4/checkpoint-36/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef671614c0d6f27cd73dcd86b2ff032aa12d8c88e7fd3678f3e0a264d90dbfa
-size 14244
+oid sha256:9eb8f8664a2b45cfb12e77df00681b8d6678be929fd7d39849fa12809d714800
+size 14180

run-4/checkpoint-36/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5fd7f61c7117cf44e1b5dcb41fba06e442d903463f3acc9daaac3751d9061b0
+oid sha256:d42f3f1deeff721e6f888ada4bb06135f66f6bba142092c77481410eacdc7fb9
 size 1064

run-4/checkpoint-36/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.24101392328980611,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-9",
-  "epoch": 4.0,
+  "best_metric": 0.8698177849938507,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-18",
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 36,
   "is_hyper_param_search": true,
@@ -10,57 +10,37 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 6.916525363922119,
-      "eval_pearson": 0.24101392328980611,
-      "eval_runtime": 0.9549,
-      "eval_samples_per_second": 1570.783,
-      "eval_spearmanr": 0.23527578828258416,
-      "eval_steps_per_second": 98.436,
-      "step": 9
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 6.322813987731934,
-      "eval_pearson": 0.21685934779589452,
-      "eval_runtime": 1.3518,
-      "eval_samples_per_second": 1109.622,
-      "eval_spearmanr": 0.19981399518979143,
-      "eval_steps_per_second": 69.536,
+      "eval_loss": 0.5605268478393555,
+      "eval_pearson": 0.8698177849938507,
+      "eval_runtime": 0.7833,
+      "eval_samples_per_second": 1914.894,
+      "eval_spearmanr": 0.8653376248792928,
+      "eval_steps_per_second": 120.0,
       "step": 18
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 5.925507068634033,
-      "eval_pearson": 0.19966300919689736,
-      "eval_runtime": 2.0553,
-      "eval_samples_per_second": 729.829,
-      "eval_spearmanr": 0.18294599603450873,
-      "eval_steps_per_second": 45.736,
-      "step": 27
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 5.775755882263184,
-      "eval_pearson": 0.19587323739505505,
-      "eval_runtime": 1.1748,
-      "eval_samples_per_second": 1276.801,
-      "eval_spearmanr": 0.17919550590843902,
-      "eval_steps_per_second": 80.013,
+      "epoch": 2.0,
+      "eval_loss": 0.5489152073860168,
+      "eval_pearson": 0.8696541826078176,
+      "eval_runtime": 0.7851,
+      "eval_samples_per_second": 1910.528,
+      "eval_spearmanr": 0.8655096971822834,
+      "eval_steps_per_second": 119.726,
       "step": 36
     }
   ],
   "logging_steps": 500,
-  "max_steps": 36,
+  "max_steps": 54,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.463445057905012e-06,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 64,
-    "seed": 5
+    "learning_rate": 9.914291118758786e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 10
   }
 }

run-4/checkpoint-36/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf3f62aadffc261f72a51d4b7c87acc76e6bc2705585514f61113a84b0e34fd3
+oid sha256:a0fb3669a562055766866e71b54806bb7235c4677b6cb8f825acdf2c31236bf5
 size 4920

run-4/checkpoint-54/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
+  "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-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe9007611f884e116c02af1450a6ea7a4cca0d81efdc65c004a05c6068dd98d
+size 267829484

run-4/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5356380fd3cb58cb7788d39f619ed30d551db8078949ef0e3be3df07ea01645b
+size 535721146

run-4/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e75092925b793a7e14690b52acc499966fcbf55d1d06b60e264fc46fdeb79e2
+size 14180

run-4/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab0a8c83eeb1b42d77610423156308d391ce4b7ebb7414a69c163eb17ad2200
+size 1064

run-4/checkpoint-54/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-54/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-54/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8701155553176486,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-54",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5605268478393555,
+      "eval_pearson": 0.8698177849938507,
+      "eval_runtime": 0.7833,
+      "eval_samples_per_second": 1914.894,
+      "eval_spearmanr": 0.8653376248792928,
+      "eval_steps_per_second": 120.0,
+      "step": 18
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5489152073860168,
+      "eval_pearson": 0.8696541826078176,
+      "eval_runtime": 0.7851,
+      "eval_samples_per_second": 1910.528,
+      "eval_spearmanr": 0.8655096971822834,
+      "eval_steps_per_second": 119.726,
+      "step": 36
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.549419105052948,
+      "eval_pearson": 0.8701155553176486,
+      "eval_runtime": 0.8019,
+      "eval_samples_per_second": 1870.6,
+      "eval_spearmanr": 0.8658778646954919,
+      "eval_steps_per_second": 117.224,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 54,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.914291118758786e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 10
+  }
+}

run-4/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fb3669a562055766866e71b54806bb7235c4677b6cb8f825acdf2c31236bf5
+size 4920

run-5/checkpoint-144/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
+  "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-5/checkpoint-144/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b8c78fe5026c94af7a8215ef418f077d1b268ab1a05d9f5b3ae585fa964aa3
+size 267829484

run-5/checkpoint-144/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e898b213865cdbafdc40d4f32a7a60c49225d80a2a137a76c66b042daf74a5
+size 535721146

run-5/checkpoint-144/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0847bf7b0d2d1b12819a366eeb9e1b4ebb44345cc05a157292c4374c504256
+size 14308

run-5/checkpoint-144/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a84ac9d8ad12c2f54714f2acbd2618b49e7bb05812cded36a7af97954492e9
+size 1064

run-5/checkpoint-144/special_tokens_map.json

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

run-5/checkpoint-144/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-5/checkpoint-144/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.8704356686123957,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-5/checkpoint-144",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 144,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5534277558326721,
+      "eval_pearson": 0.8704356686123957,
+      "eval_runtime": 0.7898,
+      "eval_samples_per_second": 1899.33,
+      "eval_spearmanr": 0.8659393895289175,
+      "eval_steps_per_second": 119.025,
+      "step": 144
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 432,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.532250940931899e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 33
+  }
+}

run-5/checkpoint-144/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d063450f94a7ab133a59ea26cf4a1835754e836fb09e39b3319de7656bcf4f60
+size 4920

runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110580.0f0a24039c15.273.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ebf3153777d46dd7a35a2207cfad0c837c51383d5a75bbad83121822e5728c1
+size 6188

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0fb3669a562055766866e71b54806bb7235c4677b6cb8f825acdf2c31236bf5
+oid sha256:d063450f94a7ab133a59ea26cf4a1835754e836fb09e39b3319de7656bcf4f60
 size 4920