Training in progress, epoch 2

logs/events.out.tfevents.1709621162.404ecd1cf399.26000.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970b363e32ccb39a80e25899bd645e9e9dd48037e901a923b35238f797d73f28
-size 5314
+oid sha256:56446eacc9914ea8457a82ce9aaf576e70f8d2071b141fef01eb6d7cd2b07f70
+size 5997

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3735ea28e3d6cd1886c3e5c7b2785a2ab71ac55d4b90d7f42c9458c9b695f9ba
+oid sha256:8218b0b49358a4f2c91ebc8c843961cecc26366dde2821fd7b7fcdb07a6f52db
 size 17549312

run-10/checkpoint-192/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-10/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8218b0b49358a4f2c91ebc8c843961cecc26366dde2821fd7b7fcdb07a6f52db
+size 17549312

run-10/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60cc74a23a3dca814a6e6dc4b91f9d9e9e5f067c9b46395a12259a7a57ccf5fa
+size 35122746

run-10/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+size 14054

run-10/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289123c16907c5b1f306770de8e3858f3c794d2c2c173b5931335d4f72bfe74e
+size 1064

run-10/checkpoint-192/special_tokens_map.json

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

run-10/checkpoint-192/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-10/checkpoint-192/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.824853228962818,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-192",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9170680046081543,
+      "learning_rate": 0.0005212663608648181,
+      "loss": 0.5641,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.799412915851272,
+      "eval_f1": 0.8197009674582234,
+      "eval_loss": 0.47259676456451416,
+      "eval_precision": 0.744408945686901,
+      "eval_recall": 0.9119373776908023,
+      "eval_runtime": 30.8424,
+      "eval_samples_per_second": 33.136,
+      "eval_steps_per_second": 1.038,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.4848690032958984,
+      "learning_rate": 0.00026063318043240905,
+      "loss": 0.456,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.824853228962818,
+      "eval_f1": 0.8406055209260909,
+      "eval_loss": 0.4349122643470764,
+      "eval_precision": 0.7712418300653595,
+      "eval_recall": 0.923679060665362,
+      "eval_runtime": 31.1515,
+      "eval_samples_per_second": 32.807,
+      "eval_steps_per_second": 1.027,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 288,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9610512963031814,
+    "learning_rate": 0.0007818995412972273,
+    "num_train_epochs": 3,
+    "temperature": 24
+  }
+}

run-10/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c48cb920a64a7322ad1d6d741321a643be4ed10af970a24a154150a0def2990
+size 4920