Training in progress, epoch 2

logs/events.out.tfevents.1713437232.ec9626078864.14834.15

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd6ff3f5c0959c502361b6e153fdf9d9e0f23f8e6f05413e1f0b87cf520fdb7
-size 5406
+oid sha256:77cd57f26ba2bf71b6339ddc9113f30f55b418c7411a87f1ccb2fc483af216a1
+size 6136

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09640bd0a4c4890df1f44b2f3010a82d69229c89425f4c3efe67921255c1d335
+oid sha256:254d6bc2c35cdaee340edf24d21bdafa1db6398c1bad0dad264664a76309220b
 size 17549312

run-14/checkpoint-1290/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-14/checkpoint-1290/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254d6bc2c35cdaee340edf24d21bdafa1db6398c1bad0dad264664a76309220b
+size 17549312

run-14/checkpoint-1290/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ae147fc2d35773ef0b604a26f9358fdbd0f37b0451c61df5fbba97dac1ea8b
+size 35123898

run-14/checkpoint-1290/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7f2a5e16989d9df1a9f119f3a022ead0c31636524de5ea431eca109ab65358
+size 14308

run-14/checkpoint-1290/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce21b28f22c1d446b4d0d3ff3e82b91def68124a80e5d3bf12c27dc85c00d6ce
+size 1064

run-14/checkpoint-1290/special_tokens_map.json

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

run-14/checkpoint-1290/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-14/checkpoint-1290/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.8914307871267934,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-1290",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1290,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9803465604782104,
+      "learning_rate": 0.00027230837357094026,
+      "loss": 0.327,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8887165568049632,
+      "eval_f1": 0.19154929577464788,
+      "eval_loss": 0.3063199520111084,
+      "eval_mcc": 0.1990419339488759,
+      "eval_precision": 0.48226950354609927,
+      "eval_recall": 0.1195079086115993,
+      "eval_runtime": 9.9261,
+      "eval_samples_per_second": 519.642,
+      "eval_steps_per_second": 16.321,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0405207872390747,
+      "learning_rate": 0.00023340717734652024,
+      "loss": 0.3025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8914307871267934,
+      "eval_f1": 0.14893617021276595,
+      "eval_loss": 0.3057989478111267,
+      "eval_mcc": 0.18620749231762276,
+      "eval_precision": 0.550561797752809,
+      "eval_recall": 0.08611599297012303,
+      "eval_runtime": 9.9284,
+      "eval_samples_per_second": 519.521,
+      "eval_steps_per_second": 16.317,
+      "step": 1290
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 3173885065200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9932188265495786,
+    "learning_rate": 0.0003112095697953603,
+    "num_train_epochs": 8,
+    "temperature": 21
+  }
+}

run-14/checkpoint-1290/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477fc5e0a8a4f66ce89d996de5d48a66ce5157517c69b38a9deeba1e7b63e8ee
+size 4984