Training in progress, epoch 2

logs/events.out.tfevents.1713611625.a9446dbff3d4.7440.15

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4894eab0be15b8aacf0f737e36e510a7070b526e465056e4403e27737056df4c
-size 5481
+oid sha256:06983d2ad03d21b35010f689a27c474f7ad7bf3dbc5783a05ba2461586a91e2e
+size 6211

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc0ae4816f22b66a592a170fd26111dc44a68e5570bb669c882dc48701f796e
+oid sha256:92c9f6092ec70603457429477d4808f8093c435713e779bb0e2b655287caa418
 size 17549312

run-13/checkpoint-320/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-13/checkpoint-320/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c9f6092ec70603457429477d4808f8093c435713e779bb0e2b655287caa418
+size 17549312

run-13/checkpoint-320/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98940dee3a93b07620c09a19d88237872b38e1c262be5f360596b9de5d34f7cd
+size 35123898

run-13/checkpoint-320/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce5941012578d026c76372190ed75bc3a1c59455c429a4fd246677d1bfc3594
+size 14308

run-13/checkpoint-320/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a6c3639c9c6390f084f0894e4fe6cee132e964586270af18ea63c6a4d2f10ca
+size 1064

run-13/checkpoint-320/special_tokens_map.json

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

run-13/checkpoint-320/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-13/checkpoint-320/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.7184313725490196,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-320",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 320,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6348164081573486,
+      "learning_rate": 0.00028293467755282096,
+      "loss": 0.4646,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.668235294117647,
+      "eval_f1": 0.018561484918793503,
+      "eval_loss": 0.43796491622924805,
+      "eval_mcc": 0.04862166383263152,
+      "eval_precision": 0.6666666666666666,
+      "eval_recall": 0.009411764705882352,
+      "eval_runtime": 1.8631,
+      "eval_samples_per_second": 684.329,
+      "eval_steps_per_second": 21.469,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2706644535064697,
+      "learning_rate": 0.000242515437902418,
+      "loss": 0.4357,
+      "step": 320
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7184313725490196,
+      "eval_f1": 0.37565217391304345,
+      "eval_loss": 0.4178254306316376,
+      "eval_mcc": 0.2995107121067069,
+      "eval_precision": 0.72,
+      "eval_recall": 0.2541176470588235,
+      "eval_runtime": 1.8716,
+      "eval_samples_per_second": 681.232,
+      "eval_steps_per_second": 21.372,
+      "step": 320
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 583510875840.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7266899336949371,
+    "learning_rate": 0.000323353917203224,
+    "num_train_epochs": 8,
+    "temperature": 24
+  }
+}

run-13/checkpoint-320/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75d1a13345b1b7409ffa5572fa151259b0166dcbee52e95898829d69dc6b9cd
+size 5048