Training in progress, epoch 3

logs/events.out.tfevents.1713440327.ec9626078864.14834.38

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7433452ffa2082321bd4aece9dfd48d77cde22717ea2dfc0610ecc199ae5fadb
-size 6137
+oid sha256:412015406d49cf868c8058aa946105cc830cb5f7a68ccf28addf3904a432ab62
+size 6867

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78755fd6ba9fbc5bee6f89e5b087ba50948fc788e8ea8ddfe5120d6836728191
+oid sha256:1f4e8dd6e42e5d17c85c55249da1555e408e6d6ac8c5a6a26d95f27aece03058
 size 17549312

run-37/checkpoint-1935/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-37/checkpoint-1935/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4e8dd6e42e5d17c85c55249da1555e408e6d6ac8c5a6a26d95f27aece03058
+size 17549312

run-37/checkpoint-1935/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd8358d50a76f6ebf1e1078dfe3e1d6a523ede40cf6b1ab22235677e659c6d8
+size 35123898

run-37/checkpoint-1935/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52accd942491f2dc7d4a75134a3eb6fb2aad787ad955e2de73fb9398b7a6277c
+size 14308

run-37/checkpoint-1935/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64dd6d2f840cf4c2356d8e4a6bfca7a7936cc6b600a4b2408d57883d5de5848a
+size 1064

run-37/checkpoint-1935/special_tokens_map.json

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

run-37/checkpoint-1935/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-37/checkpoint-1935/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.8978286157425359,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-37/checkpoint-1935",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1935,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3864041566848755,
+      "learning_rate": 0.00016868362667848253,
+      "loss": 0.2983,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8949205118262893,
+      "eval_f1": 0.2322946175637394,
+      "eval_loss": 0.2774158716201782,
+      "eval_mcc": 0.257425944719354,
+      "eval_precision": 0.5985401459854015,
+      "eval_recall": 0.14411247803163443,
+      "eval_runtime": 9.9039,
+      "eval_samples_per_second": 520.804,
+      "eval_steps_per_second": 16.357,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.49007099866867065,
+      "learning_rate": 0.0001499410014919845,
+      "loss": 0.2764,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8960837533927879,
+      "eval_f1": 0.1518987341772152,
+      "eval_loss": 0.27505719661712646,
+      "eval_mcc": 0.23128061022537116,
+      "eval_precision": 0.7619047619047619,
+      "eval_recall": 0.0843585237258348,
+      "eval_runtime": 9.9176,
+      "eval_samples_per_second": 520.084,
+      "eval_steps_per_second": 16.335,
+      "step": 1290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7594336867332458,
+      "learning_rate": 0.0001311983763054864,
+      "loss": 0.2709,
+      "step": 1935
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8978286157425359,
+      "eval_f1": 0.1700787401574803,
+      "eval_loss": 0.2664003074169159,
+      "eval_mcc": 0.2572444823436495,
+      "eval_precision": 0.8181818181818182,
+      "eval_recall": 0.09490333919156414,
+      "eval_runtime": 9.9289,
+      "eval_samples_per_second": 519.496,
+      "eval_steps_per_second": 16.316,
+      "step": 1935
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 4760827597800.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8497931576459636,
+    "learning_rate": 0.0001874262518649806,
+    "num_train_epochs": 10,
+    "temperature": 17
+  }
+}

run-37/checkpoint-1935/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09573e66bd1616796d5c7cf2c8e806aea231a9366717caf7c85276193ae906a9
+size 4984