Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfe9fdecb135d017f748d4f62411a239f87748cf415d9d549bd29842518983d
+oid sha256:e069d094ca8a574d13321febd2ccfb587e994a68106882f97744acb3998cc3ac
 size 267832560

run-1/checkpoint-16840/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-16840/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e069d094ca8a574d13321febd2ccfb587e994a68106882f97744acb3998cc3ac
+size 267832560

run-1/checkpoint-16840/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a48e1e5eb51255dfafc7a944fc6d322136e491ba829e2296b49eb5548511a3
+size 535727290

run-1/checkpoint-16840/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d28b6671c6edf25c3dab818fe68a70ab22ed85572a7869f1ed35d58a2474ae
+size 14244

run-1/checkpoint-16840/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb1e963b81d5f0ccd8f36c764204f06a4f2c7880f60130196072acb7c4aa822
+size 1064

run-1/checkpoint-16840/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-16840/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-16840/trainer_state.json

@@ -0,0 +1,293 @@
+{
+  "best_metric": 0.9048165137614679,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-sst2/run-1/checkpoint-16840",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 16840,
+  "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
+    },
+    {
+      "epoch": 2.019002375296912,
+      "grad_norm": 8.27688217163086,
+      "learning_rate": 1.7170096723236659e-06,
+      "loss": 0.1744,
+      "step": 8500
+    },
+    {
+      "epoch": 2.137767220902613,
+      "grad_norm": 14.900986671447754,
+      "learning_rate": 1.6140714425680505e-06,
+      "loss": 0.1697,
+      "step": 9000
+    },
+    {
+      "epoch": 2.2565320665083135,
+      "grad_norm": 19.000568389892578,
+      "learning_rate": 1.511133212812435e-06,
+      "loss": 0.1609,
+      "step": 9500
+    },
+    {
+      "epoch": 2.375296912114014,
+      "grad_norm": 20.799606323242188,
+      "learning_rate": 1.4081949830568196e-06,
+      "loss": 0.167,
+      "step": 10000
+    },
+    {
+      "epoch": 2.494061757719715,
+      "grad_norm": 5.071231842041016,
+      "learning_rate": 1.305256753301204e-06,
+      "loss": 0.1618,
+      "step": 10500
+    },
+    {
+      "epoch": 2.6128266033254155,
+      "grad_norm": 10.71907901763916,
+      "learning_rate": 1.2023185235455886e-06,
+      "loss": 0.1622,
+      "step": 11000
+    },
+    {
+      "epoch": 2.731591448931116,
+      "grad_norm": 11.408883094787598,
+      "learning_rate": 1.0993802937899732e-06,
+      "loss": 0.1611,
+      "step": 11500
+    },
+    {
+      "epoch": 2.850356294536817,
+      "grad_norm": 0.14033222198486328,
+      "learning_rate": 9.964420640343578e-07,
+      "loss": 0.1682,
+      "step": 12000
+    },
+    {
+      "epoch": 2.969121140142518,
+      "grad_norm": 47.36281967163086,
+      "learning_rate": 8.935038342787424e-07,
+      "loss": 0.1664,
+      "step": 12500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9002293577981652,
+      "eval_loss": 0.36717090010643005,
+      "eval_runtime": 1.2257,
+      "eval_samples_per_second": 711.438,
+      "eval_steps_per_second": 44.873,
+      "step": 12630
+    },
+    {
+      "epoch": 3.0878859857482186,
+      "grad_norm": 9.310757637023926,
+      "learning_rate": 7.905656045231268e-07,
+      "loss": 0.1501,
+      "step": 13000
+    },
+    {
+      "epoch": 3.2066508313539193,
+      "grad_norm": 4.144458293914795,
+      "learning_rate": 6.876273747675112e-07,
+      "loss": 0.1637,
+      "step": 13500
+    },
+    {
+      "epoch": 3.32541567695962,
+      "grad_norm": 0.40117746591567993,
+      "learning_rate": 5.846891450118958e-07,
+      "loss": 0.1538,
+      "step": 14000
+    },
+    {
+      "epoch": 3.4441805225653206,
+      "grad_norm": 24.535791397094727,
+      "learning_rate": 4.817509152562803e-07,
+      "loss": 0.1395,
+      "step": 14500
+    },
+    {
+      "epoch": 3.5629453681710213,
+      "grad_norm": 0.5985422730445862,
+      "learning_rate": 3.788126855006649e-07,
+      "loss": 0.1695,
+      "step": 15000
+    },
+    {
+      "epoch": 3.6817102137767224,
+      "grad_norm": 24.767759323120117,
+      "learning_rate": 2.7587445574504945e-07,
+      "loss": 0.1594,
+      "step": 15500
+    },
+    {
+      "epoch": 3.800475059382423,
+      "grad_norm": 40.31415557861328,
+      "learning_rate": 1.7293622598943399e-07,
+      "loss": 0.1453,
+      "step": 16000
+    },
+    {
+      "epoch": 3.9192399049881237,
+      "grad_norm": 14.257155418395996,
+      "learning_rate": 6.999799623381852e-08,
+      "loss": 0.1437,
+      "step": 16500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9048165137614679,
+      "eval_loss": 0.3792918920516968,
+      "eval_runtime": 1.2318,
+      "eval_samples_per_second": 707.887,
+      "eval_steps_per_second": 44.649,
+      "step": 16840
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 2401835225985144.0,
+  "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-16840/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:c7bb2ecfa53ff1e92d2e2a8cf886feeaefdf6897a98e3f01f1e7ca3330bad158
-size 11093
+oid sha256:2e053d4eb45c21f89810510350ddd62b01b444861d77381d5d5576cc2bde3747
+size 13263