Training in progress, epoch 2

logs/events.out.tfevents.1714704854.e992b94a7c88.3982.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f930bc5f3cab42d33c05b98502016720af4d323e42577367630bbbc6d4adc789
-size 5482
+oid sha256:041b5d745fea6844be8c5fb8a59b5deb3043944a46483b9f9dcb5d5d073596e9
+size 6212

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cccce3106e071ca3fb957d79db0964f0891a006781fc805ec2c65f644737c446
+oid sha256:7f87289a7237bfc91c1456da63559491ad4577df7eb4dd3b2472d289804896fc
 size 17549312

run-12/checkpoint-3176/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-12/checkpoint-3176/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f87289a7237bfc91c1456da63559491ad4577df7eb4dd3b2472d289804896fc
+size 17549312

run-12/checkpoint-3176/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f4e293b6aa8e3b0f6d0444dc5b99d042039dc2dc017ca54479c6eea387331b
+size 35123898

run-12/checkpoint-3176/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a5639c0ad118ba9a8c782a537e44e599d8a964db5e9d2de1ad5a8f5134ec48
+size 14308

run-12/checkpoint-3176/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22108c35d88f2b0e383a5328b135b416b21d199ab7a91ef51919828b791f4e0
+size 1064

run-12/checkpoint-3176/special_tokens_map.json

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

run-12/checkpoint-3176/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-12/checkpoint-3176/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6833779316858177,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-3176",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3176,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9882927536964417,
+      "learning_rate": 7.410798334450794e-05,
+      "loss": 0.6034,
+      "step": 1588
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6725956241145915,
+      "eval_f1": 0.37966000596480765,
+      "eval_loss": 0.5911920070648193,
+      "eval_mcc": 0.1895683346876405,
+      "eval_precision": 0.5151760420882234,
+      "eval_recall": 0.30059031877213693,
+      "eval_runtime": 23.3666,
+      "eval_samples_per_second": 543.767,
+      "eval_steps_per_second": 17.033,
+      "step": 1588
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.495981216430664,
+      "learning_rate": 6.175665278708995e-05,
+      "loss": 0.5856,
+      "step": 3176
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6833779316858177,
+      "eval_f1": 0.22768285659435594,
+      "eval_loss": 0.5804989337921143,
+      "eval_mcc": 0.1684089921769426,
+      "eval_precision": 0.608829568788501,
+      "eval_recall": 0.14002361275088548,
+      "eval_runtime": 23.4973,
+      "eval_samples_per_second": 540.742,
+      "eval_steps_per_second": 16.938,
+      "step": 3176
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 7817788152600.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.971233252957219,
+    "learning_rate": 8.645931390192593e-05,
+    "num_train_epochs": 7,
+    "temperature": 16
+  }
+}

run-12/checkpoint-3176/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee1795c6c064e30b93b61f7db5815153fa9a2685024f5a88af44cf5291be307
+size 4984