Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475be2c7e113d40683406e8823d7389e3567d12d4398a875869febd179abda22
+oid sha256:628e81c9d1cd28e94fd2c0528b29c2450ff4003f56c032e01547e58616527956
 size 267829484

run-2/checkpoint-18/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f91234e83dbce56155401ad1d694d158623c6dbcb479b1db268fcce8bb17a34
+oid sha256:e3bd9289f6d13dfb86bf6d6c5ea2fc8272397af0ae0983f98a2e95ce54ff6c87
 size 267829484

run-2/checkpoint-18/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d7dfcd85bbe095a7319684aa46db30a3c31c331bf0d626069d29ca390da693
+oid sha256:290209986adc4145147597ae9f00174c08b322ff434765f5343dc28c4c50bea9
 size 535721146

run-2/checkpoint-18/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ffbb71a78626d320e0c7e109df0deaee9a942aef8d9d09deef70e0bfd7c11c
-size 14244
+oid sha256:2278d47bd604800f774ab03ae4190531fb4f0bb9ade998d2253395fb7fc7a062
+size 14308

run-2/checkpoint-18/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e42290e228d418923069eab3d6144e284e05546d2e53f8e66ffe83b7fd46d65
+oid sha256:0daca37ead5c3454bd7b82bc2ba88d4ad343140ccb779d04e2bfa88439b40fea
 size 1064

run-2/checkpoint-18/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.3111201117407732,
+  "best_metric": 0.2841659960070816,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-18",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 18,
   "is_hyper_param_search": true,
@@ -10,27 +10,37 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.5358598232269287,
-      "eval_pearson": 0.3111201117407732,
-      "eval_runtime": 0.9088,
-      "eval_samples_per_second": 1650.59,
-      "eval_spearmanr": 0.30189341919396323,
-      "eval_steps_per_second": 103.437,
+      "eval_loss": 4.423223495483398,
+      "eval_pearson": 0.17909300472522865,
+      "eval_runtime": 0.8624,
+      "eval_samples_per_second": 1739.427,
+      "eval_spearmanr": 0.1740721288711004,
+      "eval_steps_per_second": 109.004,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.390650987625122,
+      "eval_pearson": 0.2841659960070816,
+      "eval_runtime": 0.8895,
+      "eval_samples_per_second": 1686.303,
+      "eval_spearmanr": 0.32493796565837335,
+      "eval_steps_per_second": 105.675,
       "step": 18
     }
   ],
   "logging_steps": 500,
-  "max_steps": 72,
+  "max_steps": 36,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.9708935486543325e-05,
+    "learning_rate": 2.6680721367432187e-05,
     "num_train_epochs": 4,
-    "per_device_train_batch_size": 32,
-    "seed": 27
+    "per_device_train_batch_size": 64,
+    "seed": 29
   }
 }

run-2/checkpoint-18/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a58e573bd94f8beb9db88df304942d0e9c8bc04406d12b1190de70c7fae2b2b
+oid sha256:10030bf67bebf9712be4aee13e4eb2bc3bd722e9da638f545180055dd9d691b8
 size 4920

run-2/checkpoint-27/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-2/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2585a91a160915792ac68da62718015090f9979e10f55c61b2c7f242b180ea
+size 267829484

run-2/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5e9229a912b577743d0bc96305ef0ad812f22077c33bfe0cae938f2d2bf21e
+size 535721146

run-2/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18212658bc6abf57a7b3b876c2db102461910a9ecc7699b5fd646bfb5015c263
+size 14308

run-2/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a56a7631c2cc7c6f0e675edb161ea7fc33df616f3ef3940733b1988c0cea6ee
+size 1064

run-2/checkpoint-27/special_tokens_map.json

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

run-2/checkpoint-27/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-2/checkpoint-27/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.30476307824800447,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-27",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.423223495483398,
+      "eval_pearson": 0.17909300472522865,
+      "eval_runtime": 0.8624,
+      "eval_samples_per_second": 1739.427,
+      "eval_spearmanr": 0.1740721288711004,
+      "eval_steps_per_second": 109.004,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.390650987625122,
+      "eval_pearson": 0.2841659960070816,
+      "eval_runtime": 0.8895,
+      "eval_samples_per_second": 1686.303,
+      "eval_spearmanr": 0.32493796565837335,
+      "eval_steps_per_second": 105.675,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.221266746520996,
+      "eval_pearson": 0.30476307824800447,
+      "eval_runtime": 0.8761,
+      "eval_samples_per_second": 1712.204,
+      "eval_spearmanr": 0.32409413348965677,
+      "eval_steps_per_second": 107.298,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 36,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.6680721367432187e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 29
+  }
+}

run-2/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10030bf67bebf9712be4aee13e4eb2bc3bd722e9da638f545180055dd9d691b8
+size 4920

run-2/checkpoint-36/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f930b8e96467ee59dea52bcf8712dae91677530f12e1f7ea5a39a7a4572f96e9
+oid sha256:569bbe56c4f6402c0da1d737655763630777779fa1fd831d3eeecdcfdb0ce5cc
 size 267829484

run-2/checkpoint-36/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb506fecce1fb0b394149d81f89c829a9f59f5e9b82210e2b4a2581d50a25010
+oid sha256:76e649ef690cf4032595a982b8f2c8846e01840db57b5c1d46e7acb894238ab2
 size 535721146

run-2/checkpoint-36/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e301dfdefa0bdcaf96abb4785d80c44201447f4b6cd7ecb8a0638b8d695f8a09
-size 14244
+oid sha256:120b265081defe782dd089076117c7ba9160d0e705e276032b793732a324ec6b
+size 14308

run-2/checkpoint-36/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c8286a4eb3ca2b934455ad2ce9ed451db18e27aab2aa7fe20c57a9ac5c9294
+oid sha256:645db668f6b8180ecbe45335051022b20e24a308d9373fde921c514362069146
 size 1064

run-2/checkpoint-36/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.6951648539564048,
+  "best_metric": 0.4586603784701155,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-36",
-  "epoch": 2.0,
+  "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 36,
   "is_hyper_param_search": true,
@@ -10,37 +10,57 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.5358598232269287,
-      "eval_pearson": 0.3111201117407732,
-      "eval_runtime": 0.9088,
-      "eval_samples_per_second": 1650.59,
-      "eval_spearmanr": 0.30189341919396323,
-      "eval_steps_per_second": 103.437,
-      "step": 18
+      "eval_loss": 4.423223495483398,
+      "eval_pearson": 0.17909300472522865,
+      "eval_runtime": 0.8624,
+      "eval_samples_per_second": 1739.427,
+      "eval_spearmanr": 0.1740721288711004,
+      "eval_steps_per_second": 109.004,
+      "step": 9
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.8630882501602173,
-      "eval_pearson": 0.6951648539564048,
-      "eval_runtime": 1.1428,
-      "eval_samples_per_second": 1312.613,
-      "eval_spearmanr": 0.6897209166518194,
-      "eval_steps_per_second": 82.257,
+      "eval_loss": 2.390650987625122,
+      "eval_pearson": 0.2841659960070816,
+      "eval_runtime": 0.8895,
+      "eval_samples_per_second": 1686.303,
+      "eval_spearmanr": 0.32493796565837335,
+      "eval_steps_per_second": 105.675,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.221266746520996,
+      "eval_pearson": 0.30476307824800447,
+      "eval_runtime": 0.8761,
+      "eval_samples_per_second": 1712.204,
+      "eval_spearmanr": 0.32409413348965677,
+      "eval_steps_per_second": 107.298,
+      "step": 27
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.2502002716064453,
+      "eval_pearson": 0.4586603784701155,
+      "eval_runtime": 0.8808,
+      "eval_samples_per_second": 1702.946,
+      "eval_spearmanr": 0.4929584589747905,
+      "eval_steps_per_second": 106.718,
       "step": 36
     }
   ],
   "logging_steps": 500,
-  "max_steps": 72,
+  "max_steps": 36,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.9708935486543325e-05,
+    "learning_rate": 2.6680721367432187e-05,
     "num_train_epochs": 4,
-    "per_device_train_batch_size": 32,
-    "seed": 27
+    "per_device_train_batch_size": 64,
+    "seed": 29
   }
 }

run-2/checkpoint-36/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a58e573bd94f8beb9db88df304942d0e9c8bc04406d12b1190de70c7fae2b2b
+oid sha256:10030bf67bebf9712be4aee13e4eb2bc3bd722e9da638f545180055dd9d691b8
 size 4920

run-3/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-3/checkpoint-72/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:628e81c9d1cd28e94fd2c0528b29c2450ff4003f56c032e01547e58616527956
+size 267829484

run-3/checkpoint-72/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2efe5398abd461fcafd62df5d68501cdf7326c5d01c05bfb382b1f855d199173
+size 535721146

run-3/checkpoint-72/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dda7584660763f72c41c754dd6523df6f1c049b2a56e83473d0e06cc32bb35d
+size 14308

run-3/checkpoint-72/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525313aa68006057abc2527656e139e39e304df0fae14edc96d58c8a10f35d43
+size 1064

run-3/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-3/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-3/checkpoint-72/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.3488998094346536,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/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": 2.188309907913208,
+      "eval_pearson": 0.3488998094346536,
+      "eval_runtime": 0.8689,
+      "eval_samples_per_second": 1726.372,
+      "eval_spearmanr": 0.3841984779795825,
+      "eval_steps_per_second": 108.186,
+      "step": 72
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 72,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2281778565394951e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 24
+  }
+}

run-3/checkpoint-72/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a97181d28e1b7189cab54251a7b430fd73528c8be0f04e2930aea21ed4e946
+size 4920

runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774024.6dcd98e81284.961.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cee97ac540578c3df21b9b8dc3092bf2cd45b9b1706e1bbc863071a79f4a9ca
+size 5323

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10030bf67bebf9712be4aee13e4eb2bc3bd722e9da638f545180055dd9d691b8
+oid sha256:94a97181d28e1b7189cab54251a7b430fd73528c8be0f04e2930aea21ed4e946
 size 4920