Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9875bdaf5d0e86f4ce39972d6a4cac083c5b31595a40bc92023279223db9105f
+oid sha256:f6468ddc026d6f5c77fa6b29fa967ea0ee566ea47dd573771098aef804f37aee
 size 267832560

run-1/checkpoint-10690/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": "4.40.0",
+  "vocab_size": 30522
+}

run-1/checkpoint-10690/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6468ddc026d6f5c77fa6b29fa967ea0ee566ea47dd573771098aef804f37aee
+size 267832560

run-1/checkpoint-10690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dce64fcf151df9da70fa75c5e2c8aeead4603d9cdbf23ddf65f99fa8c638b439
+size 535724410

run-1/checkpoint-10690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69bad382a3a0a9fc10738888dd829cd4399ab13dfb5599c4ba1dee48abe195b3
+size 13990

run-1/checkpoint-10690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce09bdbd61da4db064f2473164783f0ac4a74958bd447e76b509f9ad15afc70
+size 1064

run-1/checkpoint-10690/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-10690/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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-10690/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.4496664370323995,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-10690",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 10690,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 3.146369218826294,
+      "learning_rate": 1.653715321124928e-06,
+      "loss": 0.6079,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 5.078900337219238,
+      "learning_rate": 1.5725712916291023e-06,
+      "loss": 0.6126,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 7.2771897315979,
+      "learning_rate": 1.4914272621332766e-06,
+      "loss": 0.5551,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 22.494115829467773,
+      "learning_rate": 1.4102832326374508e-06,
+      "loss": 0.523,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5956234335899353,
+      "eval_matthews_correlation": 0.3084289905217366,
+      "eval_runtime": 31.6888,
+      "eval_samples_per_second": 32.914,
+      "eval_steps_per_second": 2.083,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 14.600356101989746,
+      "learning_rate": 1.329139203141625e-06,
+      "loss": 0.501,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 20.79261589050293,
+      "learning_rate": 1.2479951736457994e-06,
+      "loss": 0.5081,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 26.76811981201172,
+      "learning_rate": 1.1668511441499738e-06,
+      "loss": 0.4969,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 24.809595108032227,
+      "learning_rate": 1.0857071146541479e-06,
+      "loss": 0.5316,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5633124113082886,
+      "eval_matthews_correlation": 0.4209858842371305,
+      "eval_runtime": 30.8324,
+      "eval_samples_per_second": 33.828,
+      "eval_steps_per_second": 2.141,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1047708138447145,
+      "grad_norm": 35.22346878051758,
+      "learning_rate": 1.0045630851583222e-06,
+      "loss": 0.4832,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 57.915016174316406,
+      "learning_rate": 9.234190556624964e-07,
+      "loss": 0.5068,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5724976613657624,
+      "grad_norm": 72.93724822998047,
+      "learning_rate": 8.422750261666709e-07,
+      "loss": 0.4365,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 41.979488372802734,
+      "learning_rate": 7.611309966708451e-07,
+      "loss": 0.4986,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6376824378967285,
+      "eval_matthews_correlation": 0.42676403064167506,
+      "eval_runtime": 29.8373,
+      "eval_samples_per_second": 34.956,
+      "eval_steps_per_second": 2.212,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0402245088868103,
+      "grad_norm": 1.3610893487930298,
+      "learning_rate": 6.799869671750195e-07,
+      "loss": 0.5347,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 57.98234558105469,
+      "learning_rate": 5.988429376791937e-07,
+      "loss": 0.4583,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5079513564078577,
+      "grad_norm": 68.71504974365234,
+      "learning_rate": 5.17698908183368e-07,
+      "loss": 0.4624,
+      "step": 7500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 8.295002937316895,
+      "learning_rate": 4.3655487868754235e-07,
+      "loss": 0.4819,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9756782039289056,
+      "grad_norm": 54.670257568359375,
+      "learning_rate": 3.554108491917166e-07,
+      "loss": 0.5088,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6887398958206177,
+      "eval_matthews_correlation": 0.44441091037773406,
+      "eval_runtime": 32.0864,
+      "eval_samples_per_second": 32.506,
+      "eval_steps_per_second": 2.057,
+      "step": 8552
+    },
+    {
+      "epoch": 4.209541627689429,
+      "grad_norm": 0.6164466738700867,
+      "learning_rate": 2.7426681969589086e-07,
+      "loss": 0.4787,
+      "step": 9000
+    },
+    {
+      "epoch": 4.443405051449953,
+      "grad_norm": 56.68175506591797,
+      "learning_rate": 1.9312279020006517e-07,
+      "loss": 0.4801,
+      "step": 9500
+    },
+    {
+      "epoch": 4.677268475210477,
+      "grad_norm": 82.50342559814453,
+      "learning_rate": 1.1197876070423949e-07,
+      "loss": 0.487,
+      "step": 10000
+    },
+    {
+      "epoch": 4.911131898971001,
+      "grad_norm": 88.25664520263672,
+      "learning_rate": 3.083473120841377e-08,
+      "loss": 0.4887,
+      "step": 10500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7118309736251831,
+      "eval_matthews_correlation": 0.4496664370323995,
+      "eval_runtime": 30.9154,
+      "eval_samples_per_second": 33.737,
+      "eval_steps_per_second": 2.135,
+      "step": 10690
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 171558476254308.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7348593506207536e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 22
+  }
+}

run-1/checkpoint-10690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b505570bfabe2b3954b5c415db50fe70c16c7616859b303999126f730738b08
+size 5048

runs/Apr23_21-08-52_949a71f95aca/events.out.tfevents.1713915632.949a71f95aca.1272.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de9c3a12d273fa0155fdc78cdae20cfe539cdfe5aab293026958a177f117764a
-size 9577
+oid sha256:399e608090fe1b84c706ff2e54f87e5e5840f558d4b460202ff2e65046b083ef
+size 11110