Training in progress, epoch 1

logs/events.out.tfevents.1713589558.1376c752d37a.9760.32

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27b9c5c8e727afa4b94fc2d10cdcae8c18602267188ad24050985b2259f92c2
-size 7673
+oid sha256:dab7053150c7f3316766a67941c1a868afc37e8b3863098470763db526fc17f3
+size 9133

logs/events.out.tfevents.1713589659.1376c752d37a.9760.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc76d571c70b21d4454d1bf21802089cd390d283f273dd96b8d4041f797fc28e
+size 5482

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2ad175fc036ef461d8be376547158cebf8e1336231653cd0fc155bc7081cf3
+oid sha256:84164f2953052592d2835d09047ceee0142ed79126af704101498f75f68714d9
 size 17549312

run-32/checkpoint-1070/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-32/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e258f0750097071aa9f0cdb40c2eab4b42056896d09d8e64c58c99cab9d989
+size 17549312

run-32/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592b1389092724bc3af53e294a2d060263fb5bd5c0b950e3f89ad1bfcc07d2b9
+size 35123898

run-32/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8889b20d89ae20d68b3b1e02c508fe878c92c2f33b24682cc4f66bd3af9eea6
+size 14308

run-32/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9d8e1286238678148089e6fdd8cb94cb5dd72c30ef1da44fd9f5d668bf21e1
+size 1064

run-32/checkpoint-1070/special_tokens_map.json

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

run-32/checkpoint-1070/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-32/checkpoint-1070/trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.7580550673696543,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-1070",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.148311614990234,
+      "learning_rate": 0.00021207436837213607,
+      "loss": 0.5606,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7129466900995899,
+      "eval_f1": 0.5040485829959513,
+      "eval_loss": 0.5154260396957397,
+      "eval_mcc": 0.3157140452463625,
+      "eval_precision": 0.594272076372315,
+      "eval_recall": 0.437609841827768,
+      "eval_runtime": 3.126,
+      "eval_samples_per_second": 546.06,
+      "eval_steps_per_second": 17.274,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.1550638675689697,
+      "learning_rate": 0.0001817780300332595,
+      "loss": 0.4995,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7393087287639133,
+      "eval_f1": 0.5071982281284606,
+      "eval_loss": 0.4903852641582489,
+      "eval_mcc": 0.36859649869532995,
+      "eval_precision": 0.6856287425149701,
+      "eval_recall": 0.4024604569420035,
+      "eval_runtime": 3.1521,
+      "eval_samples_per_second": 541.536,
+      "eval_steps_per_second": 17.131,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.5803661346435547,
+      "learning_rate": 0.00015148169169438292,
+      "loss": 0.479,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7574692442882249,
+      "eval_f1": 0.541019955654102,
+      "eval_loss": 0.48610907793045044,
+      "eval_mcc": 0.41710213681200975,
+      "eval_precision": 0.7327327327327328,
+      "eval_recall": 0.4288224956063269,
+      "eval_runtime": 3.1361,
+      "eval_samples_per_second": 544.307,
+      "eval_steps_per_second": 17.219,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.8908817768096924,
+      "learning_rate": 0.00012118535335550633,
+      "loss": 0.4702,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7527826596367897,
+      "eval_f1": 0.5193621867881549,
+      "eval_loss": 0.4752483069896698,
+      "eval_mcc": 0.4034441704043775,
+      "eval_precision": 0.7378640776699029,
+      "eval_recall": 0.4007029876977153,
+      "eval_runtime": 3.1566,
+      "eval_samples_per_second": 540.775,
+      "eval_steps_per_second": 17.107,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 6.063438415527344,
+      "learning_rate": 9.088901501662975e-05,
+      "loss": 0.4592,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7580550673696543,
+      "eval_f1": 0.565720294426919,
+      "eval_loss": 0.4738541543483734,
+      "eval_mcc": 0.42241011732814765,
+      "eval_precision": 0.7041884816753927,
+      "eval_recall": 0.4727592267135325,
+      "eval_runtime": 3.1379,
+      "eval_samples_per_second": 544.002,
+      "eval_steps_per_second": 17.209,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 2623878322200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9251938490023766,
+    "learning_rate": 0.00024237070671101265,
+    "num_train_epochs": 8,
+    "temperature": 22
+  }
+}

run-32/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0211643bf748d7e4241acbd1423a0a1eddceec49ca8d870c57f42d37dfe7bbe8
+size 5048

run-33/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-33/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84164f2953052592d2835d09047ceee0142ed79126af704101498f75f68714d9
+size 17549312

run-33/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690389741a770858e2995d2c68cfbdd92b663d43595617b83548d120c41db90e
+size 35123898

run-33/checkpoint-214/rng_state.pth

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

run-33/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153ed27d647f7b31045d10a5b8c53f308a8665c2c8f4240203561bef684f304f
+size 1064

run-33/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-33/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-33/checkpoint-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6924428822495606,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-33/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": 6.1991143226623535,
+      "learning_rate": 6.724081136915917e-05,
+      "loss": 0.5853,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6924428822495606,
+      "eval_f1": 0.46373850868232896,
+      "eval_loss": 0.5429773330688477,
+      "eval_mcc": 0.26278004135127175,
+      "eval_precision": 0.5536585365853659,
+      "eval_recall": 0.3989455184534271,
+      "eval_runtime": 3.1406,
+      "eval_samples_per_second": 543.53,
+      "eval_steps_per_second": 17.194,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1926,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9360715938313949,
+    "learning_rate": 7.564591279030407e-05,
+    "num_train_epochs": 9,
+    "temperature": 28
+  }
+}

run-33/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c639803f3f95121766bce4b0b8c45655fd41650358eae72e2f53e8b3c3ab6ba2
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0211643bf748d7e4241acbd1423a0a1eddceec49ca8d870c57f42d37dfe7bbe8
+oid sha256:c639803f3f95121766bce4b0b8c45655fd41650358eae72e2f53e8b3c3ab6ba2
 size 5048