Training in progress, epoch 3

logs/events.out.tfevents.1713589374.1376c752d37a.9760.30

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18436bc35e1516cf562c5a2ed2d64f9cdb5346087422069c20af492bbc99586
-size 5482
+oid sha256:d4efecce7b3d6f9bfc6bfcc9089464d9913cf23db105c1eafd3ca35621f5e4aa
+size 6942

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e055eaa4180a5dd2ffea1b3dbe87c44481cfc77da37ac68f686329241dad5d72
+oid sha256:1c8bbe35980c714a3659b7061f45bc2d7622ba2f5885b488333855b742d7a9b9
 size 17549312

run-30/checkpoint-428/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-30/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f811ec39a6b4d0a020c9bb71082e7c5a0a13072652171c0c5561a14054a74777
+size 17549312

run-30/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824788270089643206c0fe90b7efe183f4e71f20dddf035b7fb2b3e1ab613cd8
+size 35123898

run-30/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0c3b463a8fb08b95f5c77916114776bad3339b633df010e4ffd9b5ddabab1e
+size 14308

run-30/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d7151fd806d6aef11c6a9bfa6b1e3239b8d4dbdf8db2600684829bd256eafc
+size 1064

run-30/checkpoint-428/special_tokens_map.json

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

run-30/checkpoint-428/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-30/checkpoint-428/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.7299355594610427,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.404624938964844,
+      "learning_rate": 0.0006827366491550371,
+      "loss": 0.5674,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.70298769771529,
+      "eval_f1": 0.47461139896373056,
+      "eval_loss": 0.5547006130218506,
+      "eval_mcc": 0.28558083057134703,
+      "eval_precision": 0.5782828282828283,
+      "eval_recall": 0.4024604569420035,
+      "eval_runtime": 3.121,
+      "eval_samples_per_second": 546.936,
+      "eval_steps_per_second": 17.302,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9503083229064941,
+      "learning_rate": 0.0005973945680106575,
+      "loss": 0.518,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7299355594610427,
+      "eval_f1": 0.5252317198764161,
+      "eval_loss": 0.5166522860527039,
+      "eval_mcc": 0.35438337904683964,
+      "eval_precision": 0.6343283582089553,
+      "eval_recall": 0.44815465729349735,
+      "eval_runtime": 3.144,
+      "eval_samples_per_second": 542.932,
+      "eval_steps_per_second": 17.175,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1926,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 1049551328880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9213962687632572,
+    "learning_rate": 0.0007680787302994168,
+    "num_train_epochs": 9,
+    "temperature": 25
+  }
+}

run-30/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c21d2a5115c4ec711667a681f6c70624e61496610806db95b0db67741a26789
+size 5048

run-30/checkpoint-642/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-30/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8bbe35980c714a3659b7061f45bc2d7622ba2f5885b488333855b742d7a9b9
+size 17549312

run-30/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233e90e8f24f0a9e399adbf04ee915100e5613ee287194ed62765c73b776f779
+size 35123898

run-30/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b0c3fe82ed8fc0c5e4a46035e8c4191c362f7c18bb672613fb7c69885d7960
+size 14308

run-30/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de3b4d9db711aa395ea43d9eaf41ccdd0c9adaa1957d6aa74e3f428e11b6672
+size 1064

run-30/checkpoint-642/special_tokens_map.json

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

run-30/checkpoint-642/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-30/checkpoint-642/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.7299355594610427,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-428",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 642,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.404624938964844,
+      "learning_rate": 0.0006827366491550371,
+      "loss": 0.5674,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.70298769771529,
+      "eval_f1": 0.47461139896373056,
+      "eval_loss": 0.5547006130218506,
+      "eval_mcc": 0.28558083057134703,
+      "eval_precision": 0.5782828282828283,
+      "eval_recall": 0.4024604569420035,
+      "eval_runtime": 3.121,
+      "eval_samples_per_second": 546.936,
+      "eval_steps_per_second": 17.302,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9503083229064941,
+      "learning_rate": 0.0005973945680106575,
+      "loss": 0.518,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7299355594610427,
+      "eval_f1": 0.5252317198764161,
+      "eval_loss": 0.5166522860527039,
+      "eval_mcc": 0.35438337904683964,
+      "eval_precision": 0.6343283582089553,
+      "eval_recall": 0.44815465729349735,
+      "eval_runtime": 3.144,
+      "eval_samples_per_second": 542.932,
+      "eval_steps_per_second": 17.175,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.8388092517852783,
+      "learning_rate": 0.0005120524868662778,
+      "loss": 0.5125,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7076742823667252,
+      "eval_f1": 0.30014025245441794,
+      "eval_loss": 0.5383661985397339,
+      "eval_mcc": 0.2638138145109301,
+      "eval_precision": 0.7430555555555556,
+      "eval_recall": 0.18804920913884007,
+      "eval_runtime": 3.146,
+      "eval_samples_per_second": 542.599,
+      "eval_steps_per_second": 17.165,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1926,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 1574326993320.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9213962687632572,
+    "learning_rate": 0.0007680787302994168,
+    "num_train_epochs": 9,
+    "temperature": 25
+  }
+}

run-30/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c21d2a5115c4ec711667a681f6c70624e61496610806db95b0db67741a26789
+size 5048