Training in progress, epoch 2

logs/events.out.tfevents.1713434952.ec9626078864.14834.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f90b5f67fbd204c9a5ee02f8b151be9d93e643f078403f8dc81a2876e08f2b0
-size 5407
+oid sha256:c17566112939021221ead35c829ff6eb88c11c65eed9be656860397679375e12
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0e971c84178afa0367579195fe2a956b5bdee252e19a3465e4f42c6959df97
+oid sha256:41fdcf897dd6f19339f3c726f5fdcb514dae7efe2b0dbedf9eb0798444f4d649
 size 17549312

run-0/checkpoint-1290/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": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1290/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fdcf897dd6f19339f3c726f5fdcb514dae7efe2b0dbedf9eb0798444f4d649
+size 17549312

run-0/checkpoint-1290/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27d97d739e11b9354720106f7ddbd123f5ec55a58a8cb42eabec9c50aa24dba
+size 35123898

run-0/checkpoint-1290/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7f2a5e16989d9df1a9f119f3a022ead0c31636524de5ea431eca109ab65358
+size 14308

run-0/checkpoint-1290/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33215b5310077db8069cc44d297bd55aee6cdf30bf0c3350043c608c2db7b010
+size 1064

run-0/checkpoint-1290/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-1290/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-1290/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.8898797983714618,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-645",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1290,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.770919680595398,
+      "learning_rate": 0.00045575725544182215,
+      "loss": 0.2361,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8898797983714618,
+      "eval_f1": 0.003508771929824561,
+      "eval_loss": 0.22947192192077637,
+      "eval_mcc": 0.039546160983878816,
+      "eval_precision": 1.0,
+      "eval_recall": 0.0017574692442882249,
+      "eval_runtime": 9.9701,
+      "eval_samples_per_second": 517.345,
+      "eval_steps_per_second": 16.249,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8797195553779602,
+      "learning_rate": 0.00040511756039273084,
+      "loss": 0.2287,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8896859247770453,
+      "eval_f1": 0.0,
+      "eval_loss": 0.22863532602787018,
+      "eval_mcc": 0.0,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 10.133,
+      "eval_samples_per_second": 509.028,
+      "eval_steps_per_second": 15.987,
+      "step": 1290
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 3173885065200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6185480031675171,
+    "learning_rate": 0.0005063969504909135,
+    "num_train_epochs": 10,
+    "temperature": 26
+  }
+}

run-0/checkpoint-1290/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00b6308354fcc4fbffa0d77653d8e9ff2f79de3d1452d8a8cbff61d75d82cfc
+size 4984