Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f89282192773f18f6349fe3918f94025ce964d3f10d405820f90c8565c4aa68
+oid sha256:e0264745ed8cb93a9ba05fa315c92190f24a1e5993186e5f31190e5f0632d679
 size 267832560

run-1/checkpoint-4276/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": "4.39.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0264745ed8cb93a9ba05fa315c92190f24a1e5993186e5f31190e5f0632d679
+size 267832560

run-1/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67294183491af3b27fda7bdd5a394c7dfc0e2a1811af4b0da386470524f000f
+size 535727290

run-1/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792d7da015051b0f95daa7da21da56350a33a56efa48ffca82531ccffd0c139f
+size 14244

run-1/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5609cb438edc0031999bbe8386beebb8d04a14c92914cf8c924e33d4f11cfa2b
+size 1064

run-1/checkpoint-4276/special_tokens_map.json

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

run-1/checkpoint-4276/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-1/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.5011003042513985,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 7.5246806144714355,
+      "learning_rate": 1.1577749465690007e-05,
+      "loss": 0.5887,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 25.256967544555664,
+      "learning_rate": 1.0044678826695038e-05,
+      "loss": 0.5585,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 10.809298515319824,
+      "learning_rate": 8.511608187700069e-06,
+      "loss": 0.5535,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 55.36846160888672,
+      "learning_rate": 6.978537548705099e-06,
+      "loss": 0.5117,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6122316122055054,
+      "eval_matthews_correlation": 0.45831111658186324,
+      "eval_runtime": 0.8138,
+      "eval_samples_per_second": 1281.66,
+      "eval_steps_per_second": 81.102,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 71.29000854492188,
+      "learning_rate": 5.44546690971013e-06,
+      "loss": 0.4209,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.4101831912994385,
+      "learning_rate": 3.912396270715161e-06,
+      "loss": 0.4658,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 2.0748186111450195,
+      "learning_rate": 2.379325631720192e-06,
+      "loss": 0.4685,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 153.2447052001953,
+      "learning_rate": 8.46254992725223e-07,
+      "loss": 0.4715,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7943716645240784,
+      "eval_matthews_correlation": 0.5011003042513985,
+      "eval_runtime": 0.7454,
+      "eval_samples_per_second": 1399.229,
+      "eval_steps_per_second": 88.542,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 65361794770440.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3110820104684976e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 22
+  }
+}

run-1/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc31c849e6487c8907123e1d6a6f0f93bddeccd5c1dc35d3d931b06422622412
+size 5048

runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711160316.d179836e26c8.903.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdbb934ba1453d989f5840ea0b15cce345f88723bb7417563ffb9fab2d38ad42
-size 5785
+oid sha256:cf2f247e598ec214d9f1bd3cd58b98efc9526998b25763dbf0eab2d88f08acb0
+size 7318