Training in progress, epoch 3

logs/events.out.tfevents.1713589993.1376c752d37a.9760.37

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5d18a2b95b5bfe7513fed13aed9e185d71cc7d3af32bb120085e8657d99efba
-size 5482
+oid sha256:d2c87df54970850a7de0907f9e131c768dd8648b12c3042d49fe5783610b3fd7
+size 6942

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:808ceec946b8bd1be03680ef884102644e10a559c8d3c3824fb64bf797e2d525
+oid sha256:ab59aa5a270b0431e0338fde0ae9b47db938899f8e8941067329f6a3b6977467
 size 17549312

run-37/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-37/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d73cfe77193e0053943749d534c2607a76dbe802e49abb3c36b8047a3409f9
+size 17549312

run-37/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a1c9abb7dd8bfda6bf166cc3a22ea6a23d7b51d497956b7ea99b293248aba3
+size 35123898

run-37/checkpoint-428/rng_state.pth

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

run-37/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f34a6a9e2ae4c1dfa67055277a1c8b060e14cdf44a9202971066f58e1b62870d
+size 1064

run-37/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-37/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-37/checkpoint-428/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.7305213825424721,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-37/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": 2.5660171508789062,
+      "learning_rate": 0.0005426960660121868,
+      "loss": 0.3936,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7065026362038664,
+      "eval_f1": 0.3275167785234899,
+      "eval_loss": 0.3753478229045868,
+      "eval_mcc": 0.2588181173815382,
+      "eval_precision": 0.6931818181818182,
+      "eval_recall": 0.21441124780316345,
+      "eval_runtime": 3.1566,
+      "eval_samples_per_second": 540.772,
+      "eval_steps_per_second": 17.107,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.099513530731201,
+      "learning_rate": 0.00040702204950914005,
+      "loss": 0.372,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7305213825424721,
+      "eval_f1": 0.3994778067885118,
+      "eval_loss": 0.366894006729126,
+      "eval_mcc": 0.33967587808797833,
+      "eval_precision": 0.7766497461928934,
+      "eval_recall": 0.2688927943760984,
+      "eval_runtime": 3.769,
+      "eval_samples_per_second": 452.906,
+      "eval_steps_per_second": 14.327,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1049551328880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6249127121707758,
+    "learning_rate": 0.0006783700825152334,
+    "num_train_epochs": 5,
+    "temperature": 13
+  }
+}

run-37/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01f7cb1930ef4d58db7e82c9c5d393875a675c9066fdbc6e65a97862326c7e8
+size 5048

run-37/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-37/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab59aa5a270b0431e0338fde0ae9b47db938899f8e8941067329f6a3b6977467
+size 17549312

run-37/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27d021c810ae65582ad6fff13a24cb7059e94357a0aaa1c37955670c3f5e2e7
+size 35123898

run-37/checkpoint-642/rng_state.pth

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

run-37/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664d45393359027559f61115ea3d4ef77c2642d40dce331c91399beac224f64b
+size 1064

run-37/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-37/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-37/checkpoint-642/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.7305213825424721,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-37/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": 2.5660171508789062,
+      "learning_rate": 0.0005426960660121868,
+      "loss": 0.3936,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7065026362038664,
+      "eval_f1": 0.3275167785234899,
+      "eval_loss": 0.3753478229045868,
+      "eval_mcc": 0.2588181173815382,
+      "eval_precision": 0.6931818181818182,
+      "eval_recall": 0.21441124780316345,
+      "eval_runtime": 3.1566,
+      "eval_samples_per_second": 540.772,
+      "eval_steps_per_second": 17.107,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.099513530731201,
+      "learning_rate": 0.00040702204950914005,
+      "loss": 0.372,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7305213825424721,
+      "eval_f1": 0.3994778067885118,
+      "eval_loss": 0.366894006729126,
+      "eval_mcc": 0.33967587808797833,
+      "eval_precision": 0.7766497461928934,
+      "eval_recall": 0.2688927943760984,
+      "eval_runtime": 3.769,
+      "eval_samples_per_second": 452.906,
+      "eval_steps_per_second": 14.327,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2766120433807373,
+      "learning_rate": 0.0002713480330060934,
+      "loss": 0.3619,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7024018746338606,
+      "eval_f1": 0.21604938271604937,
+      "eval_loss": 0.3670775592327118,
+      "eval_mcc": 0.258294733907354,
+      "eval_precision": 0.8860759493670886,
+      "eval_recall": 0.12302284710017575,
+      "eval_runtime": 3.1357,
+      "eval_samples_per_second": 544.372,
+      "eval_steps_per_second": 17.221,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1574326993320.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6249127121707758,
+    "learning_rate": 0.0006783700825152334,
+    "num_train_epochs": 5,
+    "temperature": 13
+  }
+}

run-37/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01f7cb1930ef4d58db7e82c9c5d393875a675c9066fdbc6e65a97862326c7e8
+size 5048