Training in progress, epoch 1

logs/events.out.tfevents.1709618554.404ecd1cf399.26000.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b5f68ed168481cd4315211b214b75b831b747c2033531f5d7d9f1fd81af289
-size 5998
+oid sha256:441b1a93ec46c320899b8d39867f4e411fa1ca7c78aa62a436db106c9410e8ef
+size 7035

logs/events.out.tfevents.1709618909.404ecd1cf399.26000.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ce86560b9f6c2172042d693125bfb09ff03191b2cd98a022ad745096d2242b9
+size 5313

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3ae2fa78db1d16939496673fe96513e6285b61d2f7edfaba98bf3bfef765fa
+oid sha256:af020de10a78437284341857ed456069cddcba5115cd9cf73bbd880c668987f4
 size 17549312

run-2/checkpoint-288/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-288/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d58e82edd574294986a35234cf1dbc56efe12c5d5a6e0be3eca262b7775d2f1
+size 17549312

run-2/checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9037368495d761f57d2ffc11701c075f08d6f343f53608fea5afd5d00f5b533b
+size 35122746

run-2/checkpoint-288/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3c2bb1d96a39a28ae1b66f234e351e3c13c700fc97347efd6308798b151790
+size 14054

run-2/checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0746c2ae52ef13e6783595120e8b1aa980117eee52abf4fd526c80260c0fb9f1
+size 1064

run-2/checkpoint-288/special_tokens_map.json

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

run-2/checkpoint-288/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-2/checkpoint-288/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.8101761252446184,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-288",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 288,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.613167643547058,
+      "learning_rate": 0.00027081825418014463,
+      "loss": 0.516,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7837573385518591,
+      "eval_f1": 0.8073234524847429,
+      "eval_loss": 0.44109782576560974,
+      "eval_precision": 0.7279874213836478,
+      "eval_recall": 0.9060665362035225,
+      "eval_runtime": 31.7637,
+      "eval_samples_per_second": 32.175,
+      "eval_steps_per_second": 1.007,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.826476812362671,
+      "learning_rate": 0.00013540912709007232,
+      "loss": 0.4436,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7964774951076321,
+      "eval_f1": 0.820069204152249,
+      "eval_loss": 0.42240670323371887,
+      "eval_precision": 0.7348837209302326,
+      "eval_recall": 0.9275929549902152,
+      "eval_runtime": 30.3967,
+      "eval_samples_per_second": 33.622,
+      "eval_steps_per_second": 1.053,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.404919147491455,
+      "learning_rate": 0.0,
+      "loss": 0.4233,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8101761252446184,
+      "eval_f1": 0.8264758497316635,
+      "eval_loss": 0.41113388538360596,
+      "eval_precision": 0.7611202635914333,
+      "eval_recall": 0.9041095890410958,
+      "eval_runtime": 30.8837,
+      "eval_samples_per_second": 33.092,
+      "eval_steps_per_second": 1.036,
+      "step": 288
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 288,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 707085591840.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7853139256228429,
+    "learning_rate": 0.00040622738127021695,
+    "num_train_epochs": 3,
+    "temperature": 5
+  }
+}

run-2/checkpoint-288/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0762669f3cc0b738504b8520ffeb23dad59a4047901db16223a1552e162134
+size 4920

run-3/checkpoint-96/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af020de10a78437284341857ed456069cddcba5115cd9cf73bbd880c668987f4
+size 17549312

run-3/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1e62db45f26fc9aceaafe4cfd47f298fe6070cc9e9df068869a51b06a179fb
+size 35122746

run-3/checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
+size 14054

run-3/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d0eae126ade6de0e19f38bc7c732485cd14e2a7620ccdfba356009a97cdf22
+size 1064

run-3/checkpoint-96/special_tokens_map.json

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

run-3/checkpoint-96/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-3/checkpoint-96/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.786692759295499,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-96",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2690824270248413,
+      "learning_rate": 0.00018636956997148543,
+      "loss": 0.4818,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.786692759295499,
+      "eval_f1": 0.8039568345323741,
+      "eval_loss": 0.4252791106700897,
+      "eval_precision": 0.7437603993344426,
+      "eval_recall": 0.8747553816046967,
+      "eval_runtime": 31.9977,
+      "eval_samples_per_second": 31.94,
+      "eval_steps_per_second": 1.0,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 672,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6895915406036343,
+    "learning_rate": 0.000217431164966733,
+    "num_train_epochs": 7,
+    "temperature": 20
+  }
+}

run-3/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d383e461806a90d203afa329c2e34418d5e578d8a577a59888ecbd6bee4250c7
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db0762669f3cc0b738504b8520ffeb23dad59a4047901db16223a1552e162134
+oid sha256:d383e461806a90d203afa329c2e34418d5e578d8a577a59888ecbd6bee4250c7
 size 4920