Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b38855305b8b377679c744001ad4e541cd22ed140e581d3752d0eff5f726f5
+oid sha256:fa7bcacfef2f532d8fee281c266e272a024c4d7d34ddf907105caa1561621a62
 size 267832560

run-1/checkpoint-6414/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": "4.35.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7bcacfef2f532d8fee281c266e272a024c4d7d34ddf907105caa1561621a62
+size 267832560

run-1/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58d64526e87b949e5dcbe6f84cb6a6a92a2758eaa0ba92927dcada4b9e3a539
+size 535727290

run-1/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad2a20760e242235fbdf1287df7f93bec6cfe0b0a8aa29c1f1a8756fb491051
+size 14244

run-1/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4e32042a2237a42b53866ee789f007952bce14a4d9cc66a8286b913c5720fc
+size 1064

run-1/checkpoint-6414/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-6414/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-6414/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": 0.39150252536899116,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.3464482832056169e-06,
+      "loss": 0.6152,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2326126150279351e-06,
+      "loss": 0.5757,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1187769468502538e-06,
+      "loss": 0.5878,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0049412786725722e-06,
+      "loss": 0.5571,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5580433011054993,
+      "eval_matthews_correlation": 0.20334509429779915,
+      "eval_runtime": 0.5344,
+      "eval_samples_per_second": 1951.85,
+      "eval_steps_per_second": 123.511,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 8.911056104948908e-07,
+      "loss": 0.5247,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 7.772699423172092e-07,
+      "loss": 0.516,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 6.634342741395277e-07,
+      "loss": 0.518,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.495986059618463e-07,
+      "loss": 0.4983,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5595452189445496,
+      "eval_matthews_correlation": 0.39150252536899116,
+      "eval_runtime": 0.5424,
+      "eval_samples_per_second": 1922.955,
+      "eval_steps_per_second": 121.683,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.357629377841647e-07,
+      "loss": 0.4985,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 3.219272696064833e-07,
+      "loss": 0.4795,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.080916014288018e-07,
+      "loss": 0.4954,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 9.425593325112028e-08,
+      "loss": 0.4859,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5893857479095459,
+      "eval_matthews_correlation": 0.3883727168442722,
+      "eval_runtime": 0.5651,
+      "eval_samples_per_second": 1845.532,
+      "eval_steps_per_second": 116.783,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 97693154156472.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4602839513832982e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 39
+  }
+}

run-1/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe22a8f836acb47a4fe883a7c62be708f1d34133b3d1e899a381776f9420739d
+size 4664

runs/Jan08_03-19-08_fe6f5592002e/events.out.tfevents.1704685074.fe6f5592002e.4919.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7d30ea936546f9edcbe07988f7862f50d387208134bcce069d5ef581fbb265
-size 6273
+oid sha256:8d190d683bf700ad4c8858c1e79c446f84438278966f5e4bdba82e5a6f7b85d5
+size 7433