Training in progress, epoch 2

logs/events.out.tfevents.1713611051.a9446dbff3d4.7440.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb4caa4114346721637152eca8745caa49e03a0bf2d5290fa035397d9128fcaa
-size 5483
+oid sha256:499dd9567b37484ea8a54de97aa807e5f9909baa48bac00b49ed48d9af58203f
+size 6213

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632299b5f4d481f8202af64f601ce4157a83d4d85a033490c325c22ec79f4eb2
+oid sha256:e693767afb1b214fc1ad02f50396e43ea5e9eb74a5a6421d4c2c1981719db98c
 size 17549312

run-0/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-0/checkpoint-320/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e693767afb1b214fc1ad02f50396e43ea5e9eb74a5a6421d4c2c1981719db98c
+size 17549312

run-0/checkpoint-320/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e552b2b220e1b4d104ca14c2321e5b1fc325e98b7a0039bae1b35319aab6570e
+size 35123898

run-0/checkpoint-320/rng_state.pth

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

run-0/checkpoint-320/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2828698693545c85a5d2f854e847c4911918e3cc7aa46ce3bf266668443e27
+size 1064

run-0/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-0/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-0/checkpoint-320/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6666666666666666,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-160",
+  "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": 0.8234807848930359,
+      "learning_rate": 6.749457389390413e-05,
+      "loss": 0.0587,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_f1": 0.0,
+      "eval_loss": 0.0437474325299263,
+      "eval_mcc": 0.0,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 1.868,
+      "eval_samples_per_second": 682.566,
+      "eval_steps_per_second": 21.414,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.42042386531829834,
+      "learning_rate": 3.374728694695207e-05,
+      "loss": 0.0451,
+      "step": 320
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6650980392156862,
+      "eval_f1": 0.04044943820224719,
+      "eval_loss": 0.042260926216840744,
+      "eval_mcc": 0.031242528987421626,
+      "eval_precision": 0.45,
+      "eval_recall": 0.021176470588235293,
+      "eval_runtime": 1.9237,
+      "eval_samples_per_second": 662.79,
+      "eval_steps_per_second": 20.793,
+      "step": 320
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 583510875840.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.04540173695128236,
+    "learning_rate": 0.00010124186084085621,
+    "num_train_epochs": 3,
+    "temperature": 16
+  }
+}

run-0/checkpoint-320/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d83889cb9e45c619a65dc3c74d6c27442b46e57ca94aa59069f14a234d3140e
+size 5048