Training in progress, epoch 1

logs/events.out.tfevents.1713588088.1376c752d37a.9760.13

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b03971f71764aef8d9e2272ffb001c7ef594cc71186036ef161d1dd866983b11
-size 6214
+oid sha256:1ab2c088c1a77b8a9e850fbf9dcb9688ea336b6e5bdf39d76bb17b7934b999de
+size 11324

logs/events.out.tfevents.1713588236.1376c752d37a.9760.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fcf86b97c94672f7f394431a0bf6dd87262bca74991e0e86b325cdaa8be15ad
+size 5482

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6e8180408bf79edc472d05a9309353297d7248ccaf4cf1833779de73e7a37be
+oid sha256:f755ff6559590f70dd60b4ffbb2384922811a13ff87015f5c38d21ef3718aa32
 size 17549312

run-13/checkpoint-1498/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-13/checkpoint-1498/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa84c3116167386d80a4a76ef3b823c5974cf58ef02996221e527cf7c705e2e0
+size 17549312

run-13/checkpoint-1498/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16499707aebbf0665dd459651b897cd68afa36f3979ec748c41f0e1237b7e17
+size 35123898

run-13/checkpoint-1498/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec7baa77763623ab6f5c0a3afb24b20f15950a2841a41419e9c31b1269a80a7
+size 14308

run-13/checkpoint-1498/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8012d44af1232392ec4e1a5815505e9b30177a74d77396958ecc6d6caff76d3a
+size 1064

run-13/checkpoint-1498/special_tokens_map.json

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

run-13/checkpoint-1498/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-13/checkpoint-1498/trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": 0.7633274751025191,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-1284",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1498,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.252918720245361,
+      "learning_rate": 0.00015581725710675,
+      "loss": 0.4793,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6994727592267135,
+      "eval_f1": 0.2982216142270862,
+      "eval_loss": 0.45286598801612854,
+      "eval_mcc": 0.23321001518594284,
+      "eval_precision": 0.6728395061728395,
+      "eval_recall": 0.19156414762741653,
+      "eval_runtime": 3.1418,
+      "eval_samples_per_second": 543.327,
+      "eval_steps_per_second": 17.188,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6013866662979126,
+      "learning_rate": 0.00013850422853933333,
+      "loss": 0.4377,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7393087287639133,
+      "eval_f1": 0.44165621079046424,
+      "eval_loss": 0.4278346300125122,
+      "eval_mcc": 0.36530426808949645,
+      "eval_precision": 0.7719298245614035,
+      "eval_recall": 0.3093145869947276,
+      "eval_runtime": 3.129,
+      "eval_samples_per_second": 545.542,
+      "eval_steps_per_second": 17.258,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.8795703649520874,
+      "learning_rate": 0.00012119119997191666,
+      "loss": 0.4198,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7410661980082015,
+      "eval_f1": 0.45566502463054187,
+      "eval_loss": 0.4231508672237396,
+      "eval_mcc": 0.36988431980614395,
+      "eval_precision": 0.7613168724279835,
+      "eval_recall": 0.3251318101933216,
+      "eval_runtime": 3.1432,
+      "eval_samples_per_second": 543.083,
+      "eval_steps_per_second": 17.18,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.028773784637451,
+      "learning_rate": 0.00010387817140449999,
+      "loss": 0.4158,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7492677211482133,
+      "eval_f1": 0.48681055155875297,
+      "eval_loss": 0.41446971893310547,
+      "eval_mcc": 0.3934937852291293,
+      "eval_precision": 0.7660377358490567,
+      "eval_recall": 0.35676625659050965,
+      "eval_runtime": 3.1319,
+      "eval_samples_per_second": 545.042,
+      "eval_steps_per_second": 17.242,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.238177537918091,
+      "learning_rate": 8.656514283708333e-05,
+      "loss": 0.4093,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7545401288810779,
+      "eval_f1": 0.5144843568945539,
+      "eval_loss": 0.41232869029045105,
+      "eval_mcc": 0.40811560014590953,
+      "eval_precision": 0.7551020408163265,
+      "eval_recall": 0.39015817223198596,
+      "eval_runtime": 3.1304,
+      "eval_samples_per_second": 545.304,
+      "eval_steps_per_second": 17.25,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.982135772705078,
+      "learning_rate": 6.925211426966667e-05,
+      "loss": 0.406,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7633274751025191,
+      "eval_f1": 0.5817805383022774,
+      "eval_loss": 0.4112951457500458,
+      "eval_mcc": 0.4373095480521575,
+      "eval_precision": 0.707808564231738,
+      "eval_recall": 0.4938488576449912,
+      "eval_runtime": 3.1421,
+      "eval_samples_per_second": 543.275,
+      "eval_steps_per_second": 17.186,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.224627494812012,
+      "learning_rate": 5.1939085702249996e-05,
+      "loss": 0.4012,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.760398359695372,
+      "eval_f1": 0.5193889541715628,
+      "eval_loss": 0.40900105237960815,
+      "eval_mcc": 0.4249892956955117,
+      "eval_precision": 0.7836879432624113,
+      "eval_recall": 0.3884007029876977,
+      "eval_runtime": 3.1417,
+      "eval_samples_per_second": 543.33,
+      "eval_steps_per_second": 17.188,
+      "step": 1498
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 3673429651080.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7600265334081553,
+    "learning_rate": 0.00017313028567416666,
+    "num_train_epochs": 10,
+    "temperature": 20
+  }
+}

run-13/checkpoint-1498/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337ae105471fec8ffb5d52423139a5e61882546739f2232fd2c523f2c7731651
+size 5048

run-13/checkpoint-1712/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-13/checkpoint-1712/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2103f25d21fdb549ab7a5447b1216c3d84eae1206a7610e274eee74e33f8407b
+size 17549312

run-13/checkpoint-1712/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1768f9219dfabb03280e931352c5e7bc129665cfa19e57df9cdd1e7e44d9765a
+size 35123898

run-13/checkpoint-1712/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4989482a5a75709b5c8ca6795f7ae67e4569d30e28e8e6fcdef7d2324018c9b4
+size 14308

run-13/checkpoint-1712/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b5eb76c7317b74ce9663086a926664499fdaafc7e3c9d8a5935c47ff344e27
+size 1064

run-13/checkpoint-1712/special_tokens_map.json

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

run-13/checkpoint-1712/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-13/checkpoint-1712/trainer_state.json

@@ -0,0 +1,186 @@
+{
+  "best_metric": 0.7703573520796719,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-1712",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1712,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.252918720245361,
+      "learning_rate": 0.00015581725710675,
+      "loss": 0.4793,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6994727592267135,
+      "eval_f1": 0.2982216142270862,
+      "eval_loss": 0.45286598801612854,
+      "eval_mcc": 0.23321001518594284,
+      "eval_precision": 0.6728395061728395,
+      "eval_recall": 0.19156414762741653,
+      "eval_runtime": 3.1418,
+      "eval_samples_per_second": 543.327,
+      "eval_steps_per_second": 17.188,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6013866662979126,
+      "learning_rate": 0.00013850422853933333,
+      "loss": 0.4377,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7393087287639133,
+      "eval_f1": 0.44165621079046424,
+      "eval_loss": 0.4278346300125122,
+      "eval_mcc": 0.36530426808949645,
+      "eval_precision": 0.7719298245614035,
+      "eval_recall": 0.3093145869947276,
+      "eval_runtime": 3.129,
+      "eval_samples_per_second": 545.542,
+      "eval_steps_per_second": 17.258,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.8795703649520874,
+      "learning_rate": 0.00012119119997191666,
+      "loss": 0.4198,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7410661980082015,
+      "eval_f1": 0.45566502463054187,
+      "eval_loss": 0.4231508672237396,
+      "eval_mcc": 0.36988431980614395,
+      "eval_precision": 0.7613168724279835,
+      "eval_recall": 0.3251318101933216,
+      "eval_runtime": 3.1432,
+      "eval_samples_per_second": 543.083,
+      "eval_steps_per_second": 17.18,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.028773784637451,
+      "learning_rate": 0.00010387817140449999,
+      "loss": 0.4158,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7492677211482133,
+      "eval_f1": 0.48681055155875297,
+      "eval_loss": 0.41446971893310547,
+      "eval_mcc": 0.3934937852291293,
+      "eval_precision": 0.7660377358490567,
+      "eval_recall": 0.35676625659050965,
+      "eval_runtime": 3.1319,
+      "eval_samples_per_second": 545.042,
+      "eval_steps_per_second": 17.242,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.238177537918091,
+      "learning_rate": 8.656514283708333e-05,
+      "loss": 0.4093,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7545401288810779,
+      "eval_f1": 0.5144843568945539,
+      "eval_loss": 0.41232869029045105,
+      "eval_mcc": 0.40811560014590953,
+      "eval_precision": 0.7551020408163265,
+      "eval_recall": 0.39015817223198596,
+      "eval_runtime": 3.1304,
+      "eval_samples_per_second": 545.304,
+      "eval_steps_per_second": 17.25,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.982135772705078,
+      "learning_rate": 6.925211426966667e-05,
+      "loss": 0.406,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7633274751025191,
+      "eval_f1": 0.5817805383022774,
+      "eval_loss": 0.4112951457500458,
+      "eval_mcc": 0.4373095480521575,
+      "eval_precision": 0.707808564231738,
+      "eval_recall": 0.4938488576449912,
+      "eval_runtime": 3.1421,
+      "eval_samples_per_second": 543.275,
+      "eval_steps_per_second": 17.186,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.224627494812012,
+      "learning_rate": 5.1939085702249996e-05,
+      "loss": 0.4012,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.760398359695372,
+      "eval_f1": 0.5193889541715628,
+      "eval_loss": 0.40900105237960815,
+      "eval_mcc": 0.4249892956955117,
+      "eval_precision": 0.7836879432624113,
+      "eval_recall": 0.3884007029876977,
+      "eval_runtime": 3.1417,
+      "eval_samples_per_second": 543.33,
+      "eval_steps_per_second": 17.188,
+      "step": 1498
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.8839030265808105,
+      "learning_rate": 3.462605713483333e-05,
+      "loss": 0.3966,
+      "step": 1712
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7703573520796719,
+      "eval_f1": 0.5634743875278397,
+      "eval_loss": 0.4091112017631531,
+      "eval_mcc": 0.45157604955258585,
+      "eval_precision": 0.7689969604863222,
+      "eval_recall": 0.4446397188049209,
+      "eval_runtime": 3.1342,
+      "eval_samples_per_second": 544.632,
+      "eval_steps_per_second": 17.229,
+      "step": 1712
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 4198205315520.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7600265334081553,
+    "learning_rate": 0.00017313028567416666,
+    "num_train_epochs": 10,
+    "temperature": 20
+  }
+}

run-13/checkpoint-1712/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337ae105471fec8ffb5d52423139a5e61882546739f2232fd2c523f2c7731651
+size 5048

run-14/checkpoint-214/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-14/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f755ff6559590f70dd60b4ffbb2384922811a13ff87015f5c38d21ef3718aa32
+size 17549312

run-14/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cfb0d8c08fd74068eb6567eeba1bce00cbb13d462a214904652176445e66b99
+size 35123898

run-14/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
+size 14308

run-14/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5b053550b6e32cce0e89713383b5b60d0c19066ce6860238faf99d5062f59e
+size 1064

run-14/checkpoint-214/special_tokens_map.json

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

run-14/checkpoint-214/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-14/checkpoint-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6865846514352666,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.930738925933838,
+      "learning_rate": 5.414014250397772e-05,
+      "loss": 0.6091,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6865846514352666,
+      "eval_f1": 0.37572928821470253,
+      "eval_loss": 0.564587414264679,
+      "eval_mcc": 0.2156910734882714,
+      "eval_precision": 0.5590277777777778,
+      "eval_recall": 0.28295254833040423,
+      "eval_runtime": 3.1483,
+      "eval_samples_per_second": 542.201,
+      "eval_steps_per_second": 17.152,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9740992948842065,
+    "learning_rate": 6.187444857597454e-05,
+    "num_train_epochs": 8,
+    "temperature": 3
+  }
+}

run-14/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7957c24fcc5f109d1242da58460e07cf4b6b3343538fd03977a240662bdcface
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337ae105471fec8ffb5d52423139a5e61882546739f2232fd2c523f2c7731651
+oid sha256:7957c24fcc5f109d1242da58460e07cf4b6b3343538fd03977a240662bdcface
 size 5048