Training in progress, epoch 6

logs/events.out.tfevents.1713441879.ec9626078864.14834.44

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822435bb367a7a34f5ce4f2f0b872683017c06d3c694e09704231e5e799a47b2
-size 8327
+oid sha256:ecd37eb526ffd4ea94610e02a5035a7209bd6a3cb91d8ecd2d4badd757100e00
+size 9057

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b7eb4647590a55b7c959190a1b5fad9b12f75b84b676398c4acbe0f3b31324
+oid sha256:f9dc2d5f6ef880b55cf1bb572263a0d7b637feff9bfb9659dd3245a1a8eb388b
 size 17549312

run-43/checkpoint-3870/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-43/checkpoint-3870/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dc2d5f6ef880b55cf1bb572263a0d7b637feff9bfb9659dd3245a1a8eb388b
+size 17549312

run-43/checkpoint-3870/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36f8ffbbf49ebc1c117042e97686f2eb66d381db523b21132f9cbf8722b40a4
+size 35123898

run-43/checkpoint-3870/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd3594daca53cebdd7cbf0d80846211d0eafca218895f209b5494269a0d240f
+size 14308

run-43/checkpoint-3870/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3399e1ed83c572d15b47d854aeb9fa7a728d3dbadac0cd24aa40fb39f8a7031e
+size 1064

run-43/checkpoint-3870/special_tokens_map.json

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

run-43/checkpoint-3870/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-43/checkpoint-3870/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 0.9020938348196975,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-43/checkpoint-3225",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 3870,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1614691019058228,
+      "learning_rate": 0.00013740809545058623,
+      "loss": 0.2838,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8960837533927879,
+      "eval_f1": 0.1878787878787879,
+      "eval_loss": 0.26379355788230896,
+      "eval_mcc": 0.24425925679105032,
+      "eval_precision": 0.6813186813186813,
+      "eval_recall": 0.10896309314586995,
+      "eval_runtime": 9.9542,
+      "eval_samples_per_second": 518.172,
+      "eval_steps_per_second": 16.274,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5016854405403137,
+      "learning_rate": 0.00011450674620882187,
+      "loss": 0.2634,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8982163629313688,
+      "eval_f1": 0.18856259659969088,
+      "eval_loss": 0.26019662618637085,
+      "eval_mcc": 0.2656935582466473,
+      "eval_precision": 0.782051282051282,
+      "eval_recall": 0.10720562390158173,
+      "eval_runtime": 9.9403,
+      "eval_samples_per_second": 518.897,
+      "eval_steps_per_second": 16.297,
+      "step": 1290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7783706784248352,
+      "learning_rate": 9.16053969670575e-05,
+      "loss": 0.2592,
+      "step": 1935
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8989918573090345,
+      "eval_f1": 0.187207488299532,
+      "eval_loss": 0.2548668682575226,
+      "eval_mcc": 0.2745959396731611,
+      "eval_precision": 0.8333333333333334,
+      "eval_recall": 0.1054481546572935,
+      "eval_runtime": 9.9225,
+      "eval_samples_per_second": 519.829,
+      "eval_steps_per_second": 16.327,
+      "step": 1935
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.8894814252853394,
+      "learning_rate": 6.870404772529312e-05,
+      "loss": 0.2553,
+      "step": 2580
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9011244668476154,
+      "eval_f1": 0.2994505494505495,
+      "eval_loss": 0.2551569938659668,
+      "eval_mcc": 0.327459456642367,
+      "eval_precision": 0.6855345911949685,
+      "eval_recall": 0.19156414762741653,
+      "eval_runtime": 9.9192,
+      "eval_samples_per_second": 520.001,
+      "eval_steps_per_second": 16.332,
+      "step": 2580
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.9782265424728394,
+      "learning_rate": 4.580269848352875e-05,
+      "loss": 0.253,
+      "step": 3225
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9020938348196975,
+      "eval_f1": 0.3346508563899868,
+      "eval_loss": 0.2522221505641937,
+      "eval_mcc": 0.3483931718687521,
+      "eval_precision": 0.6684210526315789,
+      "eval_recall": 0.22319859402460457,
+      "eval_runtime": 9.9132,
+      "eval_samples_per_second": 520.318,
+      "eval_steps_per_second": 16.342,
+      "step": 3225
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.8605930209159851,
+      "learning_rate": 2.2901349241764373e-05,
+      "loss": 0.2505,
+      "step": 3870
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.898797983714618,
+      "eval_f1": 0.275,
+      "eval_loss": 0.25063198804855347,
+      "eval_mcc": 0.30228273888271523,
+      "eval_precision": 0.6556291390728477,
+      "eval_recall": 0.17398945518453426,
+      "eval_runtime": 9.9201,
+      "eval_samples_per_second": 519.955,
+      "eval_steps_per_second": 16.33,
+      "step": 3870
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4515,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 9521655195600.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7868511609350549,
+    "learning_rate": 0.00016030944469235062,
+    "num_train_epochs": 7,
+    "temperature": 12
+  }
+}

run-43/checkpoint-3870/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08828bcd5b32baf8358042cd0b0d31aa8b726101d471f32c4aacac638c8d4236
+size 4984