Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc5cd6dec7b8aa6b1d96e463c001641cb3a4305ef4c0df23191e20a9092c43f
+oid sha256:db29bc550c29b67ba33bf1510fd686d89e76b51a529616e9aa34a2a915e64a4c
 size 267832560

run-1/checkpoint-8420/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-1/checkpoint-8420/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db29bc550c29b67ba33bf1510fd686d89e76b51a529616e9aa34a2a915e64a4c
+size 267832560

run-1/checkpoint-8420/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ce9238c96e271814fdff7c51f0afee37172bd996c80410687342418a4d7254
+size 535727290

run-1/checkpoint-8420/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6072e5519a25699c8c433f90cc84698ada8682ef972a22565664f18d6e9bcd
+size 14244

run-1/checkpoint-8420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53c888981a56087762bc71d7ed3f200f7bfc191894d3ea4ca4aaff670f228f5
+size 1064

run-1/checkpoint-8420/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-8420/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-8420/trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": 0.8979357798165137,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-sst2/run-1/checkpoint-8420",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 8420,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1187648456057007,
+      "grad_norm": 10.556523323059082,
+      "learning_rate": 3.3640213484135133e-06,
+      "loss": 0.4628,
+      "step": 500
+    },
+    {
+      "epoch": 0.2375296912114014,
+      "grad_norm": 27.427276611328125,
+      "learning_rate": 3.261083118657898e-06,
+      "loss": 0.3038,
+      "step": 1000
+    },
+    {
+      "epoch": 0.35629453681710216,
+      "grad_norm": 10.17439079284668,
+      "learning_rate": 3.1581448889022824e-06,
+      "loss": 0.2837,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4750593824228028,
+      "grad_norm": 13.1768159866333,
+      "learning_rate": 3.0552066591466673e-06,
+      "loss": 0.2588,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5938242280285035,
+      "grad_norm": 7.38680362701416,
+      "learning_rate": 2.952268429391051e-06,
+      "loss": 0.2554,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7125890736342043,
+      "grad_norm": 13.285799980163574,
+      "learning_rate": 2.849330199635436e-06,
+      "loss": 0.2433,
+      "step": 3000
+    },
+    {
+      "epoch": 0.831353919239905,
+      "grad_norm": 10.867403984069824,
+      "learning_rate": 2.7463919698798204e-06,
+      "loss": 0.2491,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9501187648456056,
+      "grad_norm": 8.815483093261719,
+      "learning_rate": 2.643453740124205e-06,
+      "loss": 0.232,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8944954128440367,
+      "eval_loss": 0.2890743613243103,
+      "eval_runtime": 1.2151,
+      "eval_samples_per_second": 717.616,
+      "eval_steps_per_second": 45.262,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0688836104513064,
+      "grad_norm": 16.8696231842041,
+      "learning_rate": 2.5405155103685896e-06,
+      "loss": 0.2066,
+      "step": 4500
+    },
+    {
+      "epoch": 1.187648456057007,
+      "grad_norm": 6.819976329803467,
+      "learning_rate": 2.4375772806129744e-06,
+      "loss": 0.1874,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3064133016627077,
+      "grad_norm": 4.169142246246338,
+      "learning_rate": 2.3346390508573587e-06,
+      "loss": 0.1915,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4251781472684084,
+      "grad_norm": 18.407304763793945,
+      "learning_rate": 2.2317008211017436e-06,
+      "loss": 0.2073,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5439429928741093,
+      "grad_norm": 7.375812530517578,
+      "learning_rate": 2.128762591346128e-06,
+      "loss": 0.2011,
+      "step": 6500
+    },
+    {
+      "epoch": 1.66270783847981,
+      "grad_norm": 5.930243968963623,
+      "learning_rate": 2.0258243615905123e-06,
+      "loss": 0.2006,
+      "step": 7000
+    },
+    {
+      "epoch": 1.7814726840855108,
+      "grad_norm": 4.470451831817627,
+      "learning_rate": 1.9228861318348967e-06,
+      "loss": 0.1969,
+      "step": 7500
+    },
+    {
+      "epoch": 1.9002375296912115,
+      "grad_norm": 11.651495933532715,
+      "learning_rate": 1.8199479020792813e-06,
+      "loss": 0.1855,
+      "step": 8000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8979357798165137,
+      "eval_loss": 0.321312814950943,
+      "eval_runtime": 1.2118,
+      "eval_samples_per_second": 719.61,
+      "eval_steps_per_second": 45.388,
+      "step": 8420
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1163165956727940.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.466959578169129e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 22
+  }
+}

run-1/checkpoint-8420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4981b833ec6213c008f66b30a316660ab04fb07a2c3971bfc74c2eb43819a780
+size 5048

runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715697677.d0b6fd4b0e89.396.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bb535545918758a5dcb388e4850973acb51c61fc0f81ac84ddb8b9422869aa
-size 6860
+oid sha256:242e3fea628da28431b1f75611a6c8062e8868b0c23bc93c486fae1e8f979378
+size 8871