Training in progress, epoch 1

logs/events.out.tfevents.1709699817.a2333cf40ebd.21010.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae777abbdf7a5d754696fbf31b20722f9af071ae847d4a1e3c41ade546551d2a
-size 5314
+oid sha256:289cc40b57a99bf3ecf71cc08a171d9c6f878306fe93b6a85d5b3e57df259b9e
+size 6351

logs/events.out.tfevents.1709700065.a2333cf40ebd.21010.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2b73214d470cae4ab0be0e1751e817bf9009ec5f0f9913db97f622fea661bc
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:341ad4d50cbe58d1b314de03a4658dee0efe3524aa61e3749df2b3f270cbd9de
+oid sha256:b5a1669a0ccd6b5bd97bc24add7d61050d74aa8351771f1cc6847eeb50ba096c
 size 17549312

run-11/checkpoint-192/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-11/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de23d2cedae4958efe60248e8338ab58ce8571f49aa7e111838779e574258cd9
+size 17549312

run-11/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b6a898431dcbcdbba5f39830a6aa09bde9420adfda571675afd353db3569591
+size 35122746

run-11/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+size 14054

run-11/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53bc242a1c53c5d1389b134bb22523c02bd39246b127f05cf3867e83db9ae5f
+size 1064

run-11/checkpoint-192/special_tokens_map.json

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

run-11/checkpoint-192/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-11/checkpoint-192/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.8023483365949119,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-192",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.867341995239258,
+      "learning_rate": 0.00047267095070335774,
+      "loss": 0.5752,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7514677103718199,
+      "eval_f1": 0.765249537892791,
+      "eval_loss": 0.501445472240448,
+      "eval_precision": 0.7250437828371279,
+      "eval_recall": 0.8101761252446184,
+      "eval_runtime": 30.0696,
+      "eval_samples_per_second": 33.988,
+      "eval_steps_per_second": 1.064,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.714812755584717,
+      "learning_rate": 0.0,
+      "loss": 0.4797,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8023483365949119,
+      "eval_f1": 0.8246527777777778,
+      "eval_loss": 0.4407924711704254,
+      "eval_precision": 0.7410296411856474,
+      "eval_recall": 0.9295499021526419,
+      "eval_runtime": 29.5981,
+      "eval_samples_per_second": 34.529,
+      "eval_steps_per_second": 1.081,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9981740599737018,
+    "learning_rate": 0.0009453419014067155,
+    "num_train_epochs": 2,
+    "temperature": 30
+  }
+}

run-11/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ad2a3b631ed3da14471b5ac8c719b5c11baabf1e37c311322e42839c08f1d3
+size 4920

run-12/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-12/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a1669a0ccd6b5bd97bc24add7d61050d74aa8351771f1cc6847eeb50ba096c
+size 17549312

run-12/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4557a4d5ec84c48678f38fc252bde90fe44084a2e924402d7e74a289197e6b4
+size 35122746

run-12/checkpoint-96/rng_state.pth

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

run-12/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a080dda77cb2dbbfadc47cfa7d5175f1d7685c4fd0fb579b4d4601b2a0174a4c
+size 1064

run-12/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-12/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-12/checkpoint-96/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7671232876712328,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/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": 1.4721163511276245,
+      "learning_rate": 0.0005951476674473283,
+      "loss": 0.4971,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7671232876712328,
+      "eval_f1": 0.7989864864864864,
+      "eval_loss": 0.4431186616420746,
+      "eval_precision": 0.7028231797919762,
+      "eval_recall": 0.9256360078277887,
+      "eval_runtime": 28.4119,
+      "eval_samples_per_second": 35.971,
+      "eval_steps_per_second": 1.126,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 288,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7419170223133877,
+    "learning_rate": 0.0008927215011709925,
+    "num_train_epochs": 3,
+    "temperature": 30
+  }
+}

run-12/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9494b45a46d7299cfdd740382df8282ceb4e98494c56a4025a5a8636cf28c5
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eca285e074f5751b46e77605d55ec46cae8a3b205f294ab4811aec331d54f279
+oid sha256:2d9494b45a46d7299cfdd740382df8282ceb4e98494c56a4025a5a8636cf28c5
 size 4920