Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f5c629441e431c292478817904a48fc60bd6a25aaec9fae7c494ea780a6941
+oid sha256:86f87cf2bf59060d3a0048c5a8c89d46ad6fbbda7e7277d36534ba5b40602188
 size 267829484

run-4/checkpoint-144/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b96031aac114c6e35186c47bedb6093c9b1d8d7a35080d4af0e5427b7c0e7a
+oid sha256:c73a5225f6f8ff5decc155d3d351f83dfcf0ce9aaf6c45a279ae41fb4449ee24
 size 267829484

run-4/checkpoint-144/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35cac1bb27bfb5fff6849dd603b20c0df6498f36f3c3399382e82c90dbfd99
+oid sha256:9ad524efcad3a6ddbfb63ab93577f87e0d7f7b4e402ca5f9057e542f22055002
 size 535721146

run-4/checkpoint-144/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba4ef1c5e753a9401f18db6dd0e9badc9fb4e3e4956aafa5bbed209ec8cba9e0
+oid sha256:0f6b60aad452bff3447ffca2a36beeee0343938e34ba314a3008c1ede5f8c3f6
 size 14244

run-4/checkpoint-144/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78e4fab71e71f8cfdac39d3ebd41054aafb6de39f3ccc727afec93c8a6994f8
+oid sha256:24cb08a5f47f3b09c6191ca27ce63f964273a32bc35b3de399ba3391421dc493
 size 1064

run-4/checkpoint-144/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8072119226154155,
+  "best_metric": 0.8221827565737537,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-144",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,37 +10,37 @@
   "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,
+      "eval_loss": 0.8611708283424377,
+      "eval_pearson": 0.7953877953260705,
+      "eval_runtime": 0.8553,
+      "eval_samples_per_second": 1753.857,
+      "eval_spearmanr": 0.7996594648437907,
+      "eval_steps_per_second": 109.908,
       "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,
+      "eval_loss": 0.7928332686424255,
+      "eval_pearson": 0.8221827565737537,
+      "eval_runtime": 0.8614,
+      "eval_samples_per_second": 1741.283,
+      "eval_spearmanr": 0.8208920009900285,
+      "eval_steps_per_second": 109.12,
       "step": 144
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 216,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.5574276250903696e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 8.502777165949994e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 8,
-    "seed": 40
+    "seed": 19
   }
 }

run-4/checkpoint-144/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
+oid sha256:99e809e9199816ee8172204222af345fed40c54314e26cb4383f4a491343c532
 size 4920

run-4/checkpoint-216/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e7ed4567edaf8cafd3b04aab5b2c4357198ecc55e0a732fb05e92389af23be
+oid sha256:c9cc46d46871c720e6e25d063fe577e0b47a56ed46be3e82e1851ee8cf48303c
 size 267829484

run-4/checkpoint-216/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445fbf7678428da33cc6ef3dab5c6183654679f7828b6489a42b3512166af7e3
+oid sha256:5dd36370b0b1ed1879223c5e6383d42bcb9e59580277c5bb8ebe64db5f757c8a
 size 535721146

run-4/checkpoint-216/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038e71594f5547a63cb7e467f33b50c0377a188cf2dc5dbbab756833f58c85c4
+oid sha256:dea1e3237b5de73b8d4f4afa8a389d9785cb7e1f3d1738843f3cd66c39f997fb
 size 14244

run-4/checkpoint-216/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a286dc983477a9eeb41942ec56313b71758475c64c11b6678337da3196238271
+oid sha256:23c54cb0947a5fd07e5fe04185ac1939bfe0e5cdb73f4d9f05a3f00c8c151940
 size 1064

run-4/checkpoint-216/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.811708722217708,
+  "best_metric": 0.8338559298590572,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-216",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,47 +10,47 @@
   "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,
+      "eval_loss": 0.8611708283424377,
+      "eval_pearson": 0.7953877953260705,
+      "eval_runtime": 0.8553,
+      "eval_samples_per_second": 1753.857,
+      "eval_spearmanr": 0.7996594648437907,
+      "eval_steps_per_second": 109.908,
       "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,
+      "eval_loss": 0.7928332686424255,
+      "eval_pearson": 0.8221827565737537,
+      "eval_runtime": 0.8614,
+      "eval_samples_per_second": 1741.283,
+      "eval_spearmanr": 0.8208920009900285,
+      "eval_steps_per_second": 109.12,
       "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,
+      "eval_loss": 0.6891829967498779,
+      "eval_pearson": 0.8338559298590572,
+      "eval_runtime": 0.8695,
+      "eval_samples_per_second": 1725.217,
+      "eval_spearmanr": 0.8309150363589644,
+      "eval_steps_per_second": 108.114,
       "step": 216
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 216,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.5574276250903696e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 8.502777165949994e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 8,
-    "seed": 40
+    "seed": 19
   }
 }

run-4/checkpoint-216/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
+oid sha256:99e809e9199816ee8172204222af345fed40c54314e26cb4383f4a491343c532
 size 4920

run-8/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-8/checkpoint-36/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f87cf2bf59060d3a0048c5a8c89d46ad6fbbda7e7277d36534ba5b40602188
+size 267829484

run-8/checkpoint-36/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b767f45412f2c684679b9fb33446783175c7043516dbb87b80745203bbc4c7b
+size 535721146

run-8/checkpoint-36/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f663ac3d6fdee92e133d3c7c5493cc1047112c0b2c69cb8a334baa59a84a22
+size 14308

run-8/checkpoint-36/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d4eb5f7f97d88d3219be58a8a19533f283f48ba8461d527bb29a342bde9aff
+size 1064

run-8/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-8/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-8/checkpoint-36/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.7318354585295763,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-8/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": 1.3752338886260986,
+      "eval_pearson": 0.7318354585295763,
+      "eval_runtime": 0.8667,
+      "eval_samples_per_second": 1730.617,
+      "eval_spearmanr": 0.7352649171390578,
+      "eval_steps_per_second": 108.452,
+      "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": 8.023427611654661e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 32
+  }
+}

run-8/checkpoint-36/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc9ff8b6111b24f8c33c7c89aa6bd61df59ec50315b654becfc206c361b6086
+size 4920

runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774166.6dcd98e81284.961.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ac276f06255b427f86bab200ea2d5b880735b99ec593b3e2dd681354ec62d5
+size 4980

runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774171.6dcd98e81284.961.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662f7c59c314eaf00d2e990ce52aea4d59beabfc2f12e875a1523b059564f064
+size 4981

runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774177.6dcd98e81284.961.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8146cffc8f448ba257a85fbaa9355d32aad63b8184785963ad81f741abbfa72
+size 4975

runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774180.6dcd98e81284.961.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e1b69cc854fd7fc04664067af54f5d73a66debde355560221338249f51df65
+size 6059

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99e809e9199816ee8172204222af345fed40c54314e26cb4383f4a491343c532
+oid sha256:bbc9ff8b6111b24f8c33c7c89aa6bd61df59ec50315b654becfc206c361b6086
 size 4920