Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a1eb309bec98e4c0bf7dfee033a0074f1dde2d1f2ad466a0454ff6be9c67fd
+oid sha256:0c72c160ce745efa2a168ba3065831c2eb692ce9297265e22265b0352f137ee9
 size 267829484

run-2/checkpoint-288/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-2/checkpoint-288/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614189b65fba102d06159359331ffeb1953e2f7125e11bcc69949ffcb747a48d
+size 267829484

run-2/checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b03782bfc350f9945c8e16d1e1b6a773cc80197d8703db9782c28b4b3e912b
+size 535721146

run-2/checkpoint-288/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7059eec0255ffdc912f70633c83c9764bf6fc16919990e7ab44548a90030087c
+size 14244

run-2/checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db95cbff936e71fa082f1cfce602ec54cea6f6ee7a160fd818b0eefc21767602
+size 1064

run-2/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-2/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-2/checkpoint-288/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.8661005085464799,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-288",
+  "epoch": 2.0,
+  "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": 0.9578061699867249,
+      "eval_pearson": 0.8355986744784069,
+      "eval_runtime": 0.7883,
+      "eval_samples_per_second": 1902.903,
+      "eval_spearmanr": 0.8478883362984728,
+      "eval_steps_per_second": 119.249,
+      "step": 144
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5721424221992493,
+      "eval_pearson": 0.8661005085464799,
+      "eval_runtime": 0.8164,
+      "eval_samples_per_second": 1837.328,
+      "eval_spearmanr": 0.862146981344484,
+      "eval_steps_per_second": 115.139,
+      "step": 288
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 288,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.552203664807529e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 5
+  }
+}

run-2/checkpoint-288/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246413bd9d1435f6c7c69c70d1a2f8591cfec05c6bb21beef22e1bd41910e74b
+size 4920

run-3/checkpoint-18/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-3/checkpoint-18/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f670a7bc2e85b36d63192f0d128ca6f674d4cb95702f386cdd32b99e598fa2f9
+oid sha256:0c72c160ce745efa2a168ba3065831c2eb692ce9297265e22265b0352f137ee9
 size 267829484

run-3/checkpoint-18/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5163a1827246a3df71f6f6739c8028fe0195075ca2294f8781ae566c7f5eef5c
+oid sha256:2f3756abeafbc8fb8b516c48dd4cbad4eeb6f69ae6f8b83a4baa8248f6850f2c
 size 535721146

run-3/checkpoint-18/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd3b20d13cc947d3fe8837480a28641637ef12d62750314c6901be85133cb70
-size 14180
+oid sha256:31fb11d3e165a3b516cbc59429a49c849c1bd3fe6ee9d654f1fbf083b2fddab2
+size 14308

run-3/checkpoint-18/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51ba4afa0d8569a56a97e7f179262890d3b642b3394523af8148fdb6fcb3d28
+oid sha256:840046423a728241bc609475b779796bd125f6e74e3b919f8c4cf98b300055cc
 size 1064

run-3/checkpoint-18/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.0470495796010619,
+  "best_metric": 0.8640876954461902,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-18",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 18,
   "is_hyper_param_search": true,
@@ -10,37 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 7.199407577514648,
-      "eval_pearson": 0.024278120881494558,
-      "eval_runtime": 0.9268,
-      "eval_samples_per_second": 1618.438,
-      "eval_spearmanr": 0.025433044219399577,
-      "eval_steps_per_second": 101.422,
-      "step": 9
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 6.31046724319458,
-      "eval_pearson": 0.0470495796010619,
-      "eval_runtime": 0.9557,
-      "eval_samples_per_second": 1569.521,
-      "eval_spearmanr": 0.048936574609921006,
-      "eval_steps_per_second": 98.357,
+      "eval_loss": 0.6028859615325928,
+      "eval_pearson": 0.8640876954461902,
+      "eval_runtime": 0.7957,
+      "eval_samples_per_second": 1885.175,
+      "eval_spearmanr": 0.8614938677816929,
+      "eval_steps_per_second": 118.138,
       "step": 18
     }
   ],
   "logging_steps": 500,
-  "max_steps": 45,
+  "max_steps": 90,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.243560941114439e-06,
+    "learning_rate": 5.304193372992487e-05,
     "num_train_epochs": 5,
-    "per_device_train_batch_size": 64,
-    "seed": 10
+    "per_device_train_batch_size": 32,
+    "seed": 31
   }
 }

run-3/checkpoint-18/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
+oid sha256:39e6105fbde8ff9149ae2a4bbcd7a8dac84eb9cecad379f5bd1a4200bdc1f6ea
 size 4920

runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110384.0f0a24039c15.273.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e825ecbdbf00da1a52f3680848612270825feac9c2eb9b6149b758ba58b4dc
+size 6898

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:246413bd9d1435f6c7c69c70d1a2f8591cfec05c6bb21beef22e1bd41910e74b
+oid sha256:39e6105fbde8ff9149ae2a4bbcd7a8dac84eb9cecad379f5bd1a4200bdc1f6ea
 size 4920