Training in progress, epoch 2

logs/events.out.tfevents.1713611777.a9446dbff3d4.7440.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d0e4c12ff6a9fa9a398f7a49cf791af94b4001df2563b336912cd69f17b98f8
-size 5482
+oid sha256:18e31b12edf6b61752f73e50281b40ca559b1d12db31ffb2121b16ebd99776cb
+size 6212

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a31a3503cac9a84d54a0282c9948ca9d722d936f72363ab63bcd49e423d4a4
+oid sha256:859be09bccaef0438439a701821e802dc5336dde9699992e7e4fbeb9e446a33b
 size 17549312

run-16/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-16/checkpoint-320/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859be09bccaef0438439a701821e802dc5336dde9699992e7e4fbeb9e446a33b
+size 17549312

run-16/checkpoint-320/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcb51f8778e7b50a48079156f53a3d8f5ca08d29757290917739c1146774ba3
+size 35123898

run-16/checkpoint-320/rng_state.pth

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

run-16/checkpoint-320/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609806a14de257d0e20c6bc8fb778846b39378dfb3a2117a71aab9e665803e6e
+size 1064

run-16/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-16/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-16/checkpoint-320/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.7137254901960784,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/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": 1.7216335535049438,
+      "learning_rate": 0.00033371467549721734,
+      "loss": 0.4146,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6870588235294117,
+      "eval_f1": 0.1971830985915493,
+      "eval_loss": 0.37955978512763977,
+      "eval_mcc": 0.18019685365777874,
+      "eval_precision": 0.6805555555555556,
+      "eval_recall": 0.11529411764705882,
+      "eval_runtime": 1.871,
+      "eval_samples_per_second": 681.446,
+      "eval_steps_per_second": 21.379,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9292495250701904,
+      "learning_rate": 0.00028604115042618627,
+      "loss": 0.3901,
+      "step": 320
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7137254901960784,
+      "eval_f1": 0.33515482695810567,
+      "eval_loss": 0.3745056092739105,
+      "eval_mcc": 0.2844985686324911,
+      "eval_precision": 0.7419354838709677,
+      "eval_recall": 0.2164705882352941,
+      "eval_runtime": 1.8722,
+      "eval_samples_per_second": 681.009,
+      "eval_steps_per_second": 21.365,
+      "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": 0.640212771663602,
+    "learning_rate": 0.0003813882005682484,
+    "num_train_epochs": 8,
+    "temperature": 30
+  }
+}

run-16/checkpoint-320/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432ab3e224fab3a9b71fffd7e885ba357c72ca9362e38c509caa0fc4e423675f
+size 5048