Training in progress, epoch 2

logs/events.out.tfevents.1711307073.73e3a81c01ef.4225.48

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdff036c57e9f6ce9d02f83bf240b36b627203f0a5200c6d715fcdd37315e15a
-size 5407
+oid sha256:96989755d2843cc9f97a600ead7406bf7b42b92167261941e6a92323949e7ee9
+size 6491

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c35a5546d0fc73fcc3adc887eb853063ffaeb94d98f331a01d1750a610afe8c1
+oid sha256:aa6f0fd02064c89050e3a50279e3f40f1ed994929a60afc296554ac1847518b0
 size 17549312

run-48/checkpoint-384/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-48/checkpoint-384/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6f0fd02064c89050e3a50279e3f40f1ed994929a60afc296554ac1847518b0
+size 17549312

run-48/checkpoint-384/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1972414e137151041ad44de750f7c583872ef3d199163d38d9ba0a7c3037c21c
+size 35122746

run-48/checkpoint-384/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2558f72cda987826e5e7caf54cc6282fe335ebecbddfed7bb83f0184d1f54cc
+size 14054

run-48/checkpoint-384/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33067a2cec107a73a7dfb83715379ea3d03722fbfab77cb2bf704909aaaa9ea
+size 1064

run-48/checkpoint-384/special_tokens_map.json

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

run-48/checkpoint-384/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-48/checkpoint-384/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.8101761252446184,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-48/checkpoint-384",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 384,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.156297206878662,
+      "learning_rate": 6.847131652416489e-05,
+      "loss": 0.5617,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7984344422700587,
+      "eval_f1": 0.8186619718309858,
+      "eval_loss": 0.4545396566390991,
+      "eval_mcc": 0.6123004481387646,
+      "eval_precision": 0.744,
+      "eval_recall": 0.9099804305283757,
+      "eval_runtime": 66.7324,
+      "eval_samples_per_second": 15.315,
+      "eval_steps_per_second": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.695183277130127,
+      "learning_rate": 0.0,
+      "loss": 0.4646,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8101761252446184,
+      "eval_f1": 0.8245931283905967,
+      "eval_loss": 0.43737441301345825,
+      "eval_mcc": 0.6289075983671709,
+      "eval_precision": 0.7663865546218488,
+      "eval_recall": 0.8923679060665362,
+      "eval_runtime": 66.9568,
+      "eval_samples_per_second": 15.264,
+      "eval_steps_per_second": 0.478,
+      "step": 384
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 384,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8915947606865525,
+    "learning_rate": 0.00013694263304832977,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "temperature": 24
+  }
+}

run-48/checkpoint-384/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d30e5b21f83d87a77503fd594b335990baf967de194f9e146aac9cf831a4555
+size 4984