Training in progress, epoch 1

logs/events.out.tfevents.1700280752.bdba95a6283e.570.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1d93a3c658df598f1f7b587c00718c1d688d01bbf52ac7c75faccf7dddfa4c
-size 5289
+oid sha256:03181edd19ce8e493e359c5c8eb7f991a750c57a53ad86daf515f24815af67fd
+size 9003

logs/events.out.tfevents.1700282528.bdba95a6283e.570.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b12ebb967aa57b2922ae1c2166b647391a0f3c574e16183e8ba563e71fae66b
+size 4809

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75cd593ab5e11de31991ca4e16324de4a078d8c45b4e384eefb608b0b9d4a3d3
+oid sha256:11bea40de792991a451d039d9713ca197f40fa5ca4fe929d63c6414f0b17763a
 size 17549312

run-1/checkpoint-2108/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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-2108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f32ede5b52ced919f9528fda4b2b4480e1964f720b9354beafcdf1b48891acb
+size 17549312

run-1/checkpoint-2108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6eb3cafec29b3f0d967f7311820785b6de26cd6e017be093d2d4d36ca00458
+size 35123898

run-1/checkpoint-2108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4b79bc2790e25d83b1f8898fdb436203335dc092b6b6672ca5039268209a63
+size 14308

run-1/checkpoint-2108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7247196b285fd77b593b444ee54a122f9d85c443a82e8eac59648c72cca016bd
+size 1064

run-1/checkpoint-2108/special_tokens_map.json

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

run-1/checkpoint-2108/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-1/checkpoint-2108/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.8142201834862385,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-1/checkpoint-2108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0007547350931851784,
+      "loss": 0.9577,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.4108219146728516,
+      "eval_runtime": 2.7423,
+      "eval_samples_per_second": 317.978,
+      "eval_steps_per_second": 2.553,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0006604155783384654,
+      "loss": 0.4355,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 1.51547372341156,
+      "eval_runtime": 2.7032,
+      "eval_samples_per_second": 322.583,
+      "eval_steps_per_second": 2.59,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0005660960634917523,
+      "loss": 0.2942,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 1.830112099647522,
+      "eval_runtime": 2.7315,
+      "eval_samples_per_second": 319.24,
+      "eval_steps_per_second": 2.563,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0004717765486450392,
+      "loss": 0.224,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8142201834862385,
+      "eval_loss": 1.54564368724823,
+      "eval_runtime": 2.6867,
+      "eval_samples_per_second": 324.567,
+      "eval_steps_per_second": 2.605,
+      "step": 2108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 32320254802260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5406219777379293,
+    "learning_rate": 0.0008488756336204177,
+    "num_train_epochs": 9,
+    "temperature": 24
+  }
+}

run-1/checkpoint-2108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fee1b02c10753a236e23df3915f51d15a4d89231b69375404c9fbf68c5317b
+size 4664

run-1/checkpoint-4743/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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-4743/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1cd6e64ea9d2b428d741c432a125a64d9425a96cc4d9709bf0c889b2fc4029
+size 17549312

run-1/checkpoint-4743/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e2283a4ee247efc308e36898d685e6276cae908e8ddff7c68001b745188c12
+size 35123898

run-1/checkpoint-4743/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c57ce5e6b2e9f61341a63c012a7ceeecd2734f8a396f51216cd4c12a9112a1
+size 14308

run-1/checkpoint-4743/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a854182f0cead760dbdac875713840774b47d87c1af242e614a71c57dc8735f
+size 1064

run-1/checkpoint-4743/special_tokens_map.json

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

run-1/checkpoint-4743/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-1/checkpoint-4743/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": 0.8142201834862385,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-1/checkpoint-2108",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 4743,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0007547350931851784,
+      "loss": 0.9577,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.4108219146728516,
+      "eval_runtime": 2.7423,
+      "eval_samples_per_second": 317.978,
+      "eval_steps_per_second": 2.553,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0006604155783384654,
+      "loss": 0.4355,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 1.51547372341156,
+      "eval_runtime": 2.7032,
+      "eval_samples_per_second": 322.583,
+      "eval_steps_per_second": 2.59,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0005660960634917523,
+      "loss": 0.2942,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 1.830112099647522,
+      "eval_runtime": 2.7315,
+      "eval_samples_per_second": 319.24,
+      "eval_steps_per_second": 2.563,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0004717765486450392,
+      "loss": 0.224,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8142201834862385,
+      "eval_loss": 1.54564368724823,
+      "eval_runtime": 2.6867,
+      "eval_samples_per_second": 324.567,
+      "eval_steps_per_second": 2.605,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0003774570337983261,
+      "loss": 0.1749,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 1.5634032487869263,
+      "eval_runtime": 2.6947,
+      "eval_samples_per_second": 323.597,
+      "eval_steps_per_second": 2.598,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0002833164933630869,
+      "loss": 0.1426,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 1.5573338270187378,
+      "eval_runtime": 2.6974,
+      "eval_samples_per_second": 323.271,
+      "eval_steps_per_second": 2.595,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00018899697851637384,
+      "loss": 0.1174,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8004587155963303,
+      "eval_loss": 1.5826865434646606,
+      "eval_runtime": 2.7055,
+      "eval_samples_per_second": 322.303,
+      "eval_steps_per_second": 2.587,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 9.467746366966076e-05,
+      "loss": 0.0994,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.601122260093689,
+      "eval_runtime": 2.7009,
+      "eval_samples_per_second": 322.85,
+      "eval_steps_per_second": 2.592,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3.579488229476777e-07,
+      "loss": 0.0844,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.5418086051940918,
+      "eval_runtime": 2.7055,
+      "eval_samples_per_second": 322.306,
+      "eval_steps_per_second": 2.587,
+      "step": 4743
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 72756683549280.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5406219777379293,
+    "learning_rate": 0.0008488756336204177,
+    "num_train_epochs": 9,
+    "temperature": 24
+  }
+}

run-1/checkpoint-4743/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fee1b02c10753a236e23df3915f51d15a4d89231b69375404c9fbf68c5317b
+size 4664

run-2/checkpoint-527/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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11bea40de792991a451d039d9713ca197f40fa5ca4fe929d63c6414f0b17763a
+size 17549312

run-2/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa55d5c6540707ca2d82076a6f660baf046a35d774e2be949e91eb8829c0209
+size 35123898

run-2/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df95bce5c5c16e60e49eb22753b34dbfa7966d22f239bd4ae61a5f9a0e6ccf0d
+size 14308

run-2/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2910ad171cfd5c788c00414bd967205a52c2d10a595b04ab9daffafb75dad6ea
+size 1064

run-2/checkpoint-527/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-527/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-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.7626146788990825,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-2/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.7859230398937433e-05,
+      "loss": 3.7946,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7626146788990825,
+      "eval_loss": 2.703794479370117,
+      "eval_runtime": 2.6906,
+      "eval_samples_per_second": 324.093,
+      "eval_steps_per_second": 2.602,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.15431079596404795,
+    "learning_rate": 2.008686976100551e-05,
+    "num_train_epochs": 9,
+    "temperature": 26
+  }
+}

run-2/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fef526ef3e659c6023033ec75dbddda78d254aee60cff3f8cb777637c56032
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fee1b02c10753a236e23df3915f51d15a4d89231b69375404c9fbf68c5317b
+oid sha256:35fef526ef3e659c6023033ec75dbddda78d254aee60cff3f8cb777637c56032
 size 4664