Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef6b9771f3c13f2303540fa2811b4e8590cc9513c682268f854fd15b77e521de
+oid sha256:1d19514171d74e45e9016d7a4f5f0c9e83dd62ba9cbefc17987d0ea94269f672
 size 267832560

run-0/checkpoint-12630/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": "4.40.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-12630/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d19514171d74e45e9016d7a4f5f0c9e83dd62ba9cbefc17987d0ea94269f672
+size 267832560

run-0/checkpoint-12630/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653c3f411d377c5763af09f174241ec0765de3d584ec4c2e49ffaed3e11a0b4f
+size 535727290

run-0/checkpoint-12630/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb96d62a1991846e695eb246470d9b86ed7778be04f0fd4ebe4c19b11127ff71
+size 14244

run-0/checkpoint-12630/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e705f33267b58e5495f5615adf4b8c9fa395d84111e0e29abb3038984c1f6da1
+size 1064

run-0/checkpoint-12630/special_tokens_map.json

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

run-0/checkpoint-12630/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-0/checkpoint-12630/trainer_state.json

@@ -0,0 +1,228 @@
+{
+  "best_metric": 0.9036697247706422,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-sst2/run-0/checkpoint-4210",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 12630,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1187648456057007,
+      "grad_norm": 9.763530731201172,
+      "learning_rate": 2.4130303407723998e-05,
+      "loss": 0.3459,
+      "step": 500
+    },
+    {
+      "epoch": 0.2375296912114014,
+      "grad_norm": 7.90731954574585,
+      "learning_rate": 2.3543191402669885e-05,
+      "loss": 0.2557,
+      "step": 1000
+    },
+    {
+      "epoch": 0.35629453681710216,
+      "grad_norm": 7.188111305236816,
+      "learning_rate": 2.2956079397615776e-05,
+      "loss": 0.2242,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4750593824228028,
+      "grad_norm": 9.416199684143066,
+      "learning_rate": 2.2368967392561663e-05,
+      "loss": 0.2281,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5938242280285035,
+      "grad_norm": 6.982799053192139,
+      "learning_rate": 2.1781855387507554e-05,
+      "loss": 0.2196,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7125890736342043,
+      "grad_norm": 3.475909948348999,
+      "learning_rate": 2.1194743382453438e-05,
+      "loss": 0.199,
+      "step": 3000
+    },
+    {
+      "epoch": 0.831353919239905,
+      "grad_norm": 18.930234909057617,
+      "learning_rate": 2.0607631377399328e-05,
+      "loss": 0.1988,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9501187648456056,
+      "grad_norm": 21.44248390197754,
+      "learning_rate": 2.0020519372345215e-05,
+      "loss": 0.1964,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9036697247706422,
+      "eval_loss": 0.279630184173584,
+      "eval_runtime": 1.1981,
+      "eval_samples_per_second": 727.831,
+      "eval_steps_per_second": 45.907,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0688836104513064,
+      "grad_norm": 6.991998672485352,
+      "learning_rate": 1.9433407367291103e-05,
+      "loss": 0.1449,
+      "step": 4500
+    },
+    {
+      "epoch": 1.187648456057007,
+      "grad_norm": 1.0682291984558105,
+      "learning_rate": 1.8846295362236993e-05,
+      "loss": 0.1307,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3064133016627077,
+      "grad_norm": 1.4475390911102295,
+      "learning_rate": 1.825918335718288e-05,
+      "loss": 0.1248,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4251781472684084,
+      "grad_norm": 0.4122050702571869,
+      "learning_rate": 1.767207135212877e-05,
+      "loss": 0.1288,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5439429928741093,
+      "grad_norm": 0.35570672154426575,
+      "learning_rate": 1.7084959347074655e-05,
+      "loss": 0.1353,
+      "step": 6500
+    },
+    {
+      "epoch": 1.66270783847981,
+      "grad_norm": 0.9978006482124329,
+      "learning_rate": 1.6497847342020545e-05,
+      "loss": 0.1316,
+      "step": 7000
+    },
+    {
+      "epoch": 1.7814726840855108,
+      "grad_norm": 7.568444728851318,
+      "learning_rate": 1.5910735336966433e-05,
+      "loss": 0.1363,
+      "step": 7500
+    },
+    {
+      "epoch": 1.9002375296912115,
+      "grad_norm": 0.1252310872077942,
+      "learning_rate": 1.532362333191232e-05,
+      "loss": 0.1271,
+      "step": 8000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8887614678899083,
+      "eval_loss": 0.37789419293403625,
+      "eval_runtime": 1.2,
+      "eval_samples_per_second": 726.651,
+      "eval_steps_per_second": 45.832,
+      "step": 8420
+    },
+    {
+      "epoch": 2.019002375296912,
+      "grad_norm": 0.2641623616218567,
+      "learning_rate": 1.4736511326858209e-05,
+      "loss": 0.114,
+      "step": 8500
+    },
+    {
+      "epoch": 2.137767220902613,
+      "grad_norm": 16.91781234741211,
+      "learning_rate": 1.4149399321804098e-05,
+      "loss": 0.0814,
+      "step": 9000
+    },
+    {
+      "epoch": 2.2565320665083135,
+      "grad_norm": 0.13691911101341248,
+      "learning_rate": 1.3562287316749987e-05,
+      "loss": 0.0807,
+      "step": 9500
+    },
+    {
+      "epoch": 2.375296912114014,
+      "grad_norm": 14.652079582214355,
+      "learning_rate": 1.2975175311695872e-05,
+      "loss": 0.0909,
+      "step": 10000
+    },
+    {
+      "epoch": 2.494061757719715,
+      "grad_norm": 0.23481616377830505,
+      "learning_rate": 1.2388063306641761e-05,
+      "loss": 0.0823,
+      "step": 10500
+    },
+    {
+      "epoch": 2.6128266033254155,
+      "grad_norm": 0.16778022050857544,
+      "learning_rate": 1.1800951301587648e-05,
+      "loss": 0.0866,
+      "step": 11000
+    },
+    {
+      "epoch": 2.731591448931116,
+      "grad_norm": 22.94564437866211,
+      "learning_rate": 1.1213839296533537e-05,
+      "loss": 0.0894,
+      "step": 11500
+    },
+    {
+      "epoch": 2.850356294536817,
+      "grad_norm": 4.668305397033691,
+      "learning_rate": 1.0626727291479424e-05,
+      "loss": 0.0969,
+      "step": 12000
+    },
+    {
+      "epoch": 2.969121140142518,
+      "grad_norm": 0.056590911000967026,
+      "learning_rate": 1.0039615286425313e-05,
+      "loss": 0.0932,
+      "step": 12500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8990825688073395,
+      "eval_loss": 0.4282897412776947,
+      "eval_runtime": 1.1944,
+      "eval_samples_per_second": 730.051,
+      "eval_steps_per_second": 46.047,
+      "step": 12630
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 21050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1821393097219560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.471741541277811e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 27
+  }
+}

run-0/checkpoint-12630/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ec7297f5c06e907634b65b0c3c004d7bc361b158c4a0a3f342fbd4132ec430
+size 5048

runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715696155.d0b6fd4b0e89.396.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edee2eebb5344295f5010280acc0b81272b1a26d7d27fd8fbd662477b9d2c967
-size 8871
+oid sha256:5a5a08db032e190c8c5b18dfec2d00955fbb7bea9c1227c6229bf8275feeb089
+size 10882