Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e6404065800fe1acdfffd268329dffb2b55a39aba2e9d5d1d81daba4a8cf9b
+oid sha256:009f470510ee410ef165856a4831c7abd5523f1ff480925bf3123f0139124f77
 size 267832560

run-3/checkpoint-8552/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "vocab_size": 30522
+}

run-3/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009f470510ee410ef165856a4831c7abd5523f1ff480925bf3123f0139124f77
+size 267832560

run-3/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403b8ed48b448a2e51ef8cbe704f0cef8c16148f5b3096b16225fe1dc3c82b18
+size 535727290

run-3/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732c31857c7291dd1a9b9c4143214555b9728c092650c6ce6ce02f6130a3af9b
+size 14308

run-3/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda6bd1836bd96bd878ddd09e010be2235dac8400550af22c6ec07cf50681a46
+size 1064

run-3/checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 0.5108951669698317,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-8552",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 9.916498184204102,
+      "learning_rate": 1.0352460846585169e-05,
+      "loss": 0.588,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 2.0442557334899902,
+      "learning_rate": 9.709610570468354e-06,
+      "loss": 0.5642,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 25.158737182617188,
+      "learning_rate": 9.066760294351542e-06,
+      "loss": 0.5358,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 21.2142276763916,
+      "learning_rate": 8.423910018234727e-06,
+      "loss": 0.5288,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6297594904899597,
+      "eval_matthews_correlation": 0.4181278600904661,
+      "eval_runtime": 0.8372,
+      "eval_samples_per_second": 1245.804,
+      "eval_steps_per_second": 78.833,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 40.90157699584961,
+      "learning_rate": 7.781059742117914e-06,
+      "loss": 0.4866,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 0.11679931730031967,
+      "learning_rate": 7.138209466001099e-06,
+      "loss": 0.4601,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 9.670472145080566,
+      "learning_rate": 6.495359189884285e-06,
+      "loss": 0.4758,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 1.609247088432312,
+      "learning_rate": 5.852508913767472e-06,
+      "loss": 0.4517,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9118176102638245,
+      "eval_matthews_correlation": 0.4622674649892012,
+      "eval_runtime": 0.7476,
+      "eval_samples_per_second": 1395.206,
+      "eval_steps_per_second": 88.287,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1047708138447145,
+      "grad_norm": 0.1278693974018097,
+      "learning_rate": 5.209658637650659e-06,
+      "loss": 0.3716,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 0.046489011496305466,
+      "learning_rate": 4.566808361533844e-06,
+      "loss": 0.3199,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5724976613657624,
+      "grad_norm": 8.200950622558594,
+      "learning_rate": 3.923958085417031e-06,
+      "loss": 0.3667,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 0.06558237969875336,
+      "learning_rate": 3.281107809300217e-06,
+      "loss": 0.3323,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9285444021224976,
+      "eval_matthews_correlation": 0.5015847043424765,
+      "eval_runtime": 0.7214,
+      "eval_samples_per_second": 1445.788,
+      "eval_steps_per_second": 91.488,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0402245088868103,
+      "grad_norm": 0.10314546525478363,
+      "learning_rate": 2.6382575331834036e-06,
+      "loss": 0.325,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 0.09269363433122635,
+      "learning_rate": 1.99540725706659e-06,
+      "loss": 0.2483,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5079513564078577,
+      "grad_norm": 0.033062130212783813,
+      "learning_rate": 1.3525569809497761e-06,
+      "loss": 0.2065,
+      "step": 7500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 2.666268825531006,
+      "learning_rate": 7.097067048329624e-07,
+      "loss": 0.2449,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9756782039289056,
+      "grad_norm": 0.12107378989458084,
+      "learning_rate": 6.685642871614863e-08,
+      "loss": 0.2523,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.092543125152588,
+      "eval_matthews_correlation": 0.5108951669698317,
+      "eval_runtime": 0.8843,
+      "eval_samples_per_second": 1179.471,
+      "eval_steps_per_second": 74.636,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 138564521149608.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0995311122701982e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 21
+  }
+}

run-3/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34730fac82fbb430a2d34761a01c6cb30b23aa40dc0ad7758d1ffd45727f8d7
+size 5240

runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723863304.b5f02c58e851.301.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee8593f570ba6f91cc2c1af4203feec0041170725da246e3aca0df65fa411ac
-size 9067
+oid sha256:8375b447556bf9205c71f53102ad140db03ddf77509510cb868f0ae09c8f3b1c
+size 10178