Training in progress, epoch 1

logs/events.out.tfevents.1723127354.621b935b3e3f.593.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8d1477eefa0127670d0e873728e16fb6349f2dbe8ba2ef0599ae224d09acd3
-size 5986
+oid sha256:3d8c35f38c514888e76b66e68b13ef490456fb427adc9cb93665f3c1599c9ad4
+size 8476

logs/events.out.tfevents.1723128504.621b935b3e3f.593.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b248c1a94e6fb4122107674ee5d090bc9eb1f04cb0e001d27204e02af1c0f1c
+size 5452

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2de728810e04a7b9524a9a75ede5aa044e3cc2632f36a7135d3d3d47d8e8aff
+oid sha256:03fffd4916830b77cc5289e2fbf40d6777d4aab66e7cae5fbf83d4b178a5fcd9
 size 17549312

run-3/checkpoint-2635/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4adab2798d8566f6ba61c751bee2a4489fd6e213a3089cf435b765bef480fde
+size 17549312

run-3/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85fe78890947abf2ad3b220e64ceb6fa8e4497846a850e1db33db089b414ecc
+size 35123898

run-3/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5f82fd2fccfa1c0aeaf300c430a1e8a7f5356a548a23bb187c50e623fde970
+size 14308

run-3/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4622ed0bb9ca20b74d4c624e269311b072e155b762137239d9b69a0e2fab418d
+size 1064

run-3/checkpoint-2635/special_tokens_map.json

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

run-3/checkpoint-2635/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-3/checkpoint-2635/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.7855504587155964,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-2635",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2635,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.747544288635254,
+      "learning_rate": 8.421921303617797e-06,
+      "loss": 1.1824,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7259174311926605,
+      "eval_loss": 1.0221459865570068,
+      "eval_runtime": 2.6361,
+      "eval_samples_per_second": 330.793,
+      "eval_steps_per_second": 2.655,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.284089088439941,
+      "learning_rate": 6.737537042894237e-06,
+      "loss": 0.974,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 0.8609867095947266,
+      "eval_runtime": 2.6102,
+      "eval_samples_per_second": 334.074,
+      "eval_steps_per_second": 2.682,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 14.767024993896484,
+      "learning_rate": 5.053152782170678e-06,
+      "loss": 0.8451,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7809633027522935,
+      "eval_loss": 0.8180754780769348,
+      "eval_runtime": 2.6115,
+      "eval_samples_per_second": 333.903,
+      "eval_steps_per_second": 2.68,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 9.393446922302246,
+      "learning_rate": 3.3687685214471185e-06,
+      "loss": 0.7901,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 0.8021524548530579,
+      "eval_runtime": 2.5985,
+      "eval_samples_per_second": 335.573,
+      "eval_steps_per_second": 2.694,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.2117280960083,
+      "learning_rate": 1.6843842607235593e-06,
+      "loss": 0.7574,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7855504587155964,
+      "eval_loss": 0.7915852665901184,
+      "eval_runtime": 2.6137,
+      "eval_samples_per_second": 333.62,
+      "eval_steps_per_second": 2.678,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 40447180739880.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8183970243354497,
+    "learning_rate": 1.0106305564341356e-05,
+    "num_train_epochs": 6,
+    "temperature": 4
+  }
+}

run-3/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19b3d1ab98759ce4a3c2a3b1b6c08002a84c81483690b1cbe27bc016b13e374
+size 5176

run-3/checkpoint-3162/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-3162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c179672b9d00f71c868f9314c2d543e8baf1f1f2d75073067047c401f2a78f86
+size 17549312

run-3/checkpoint-3162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691a301f4a99a0f9a3989bd26736c18c1f92360b579cef41cf80c0428e7e2083
+size 35123898

run-3/checkpoint-3162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522b7aebc7f2d792dff3c51eedb9bc3afba88519f25125b03cb3295366cd0853
+size 14308

run-3/checkpoint-3162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c623efc268ce501ea36fca199a9e2cc8f50e10076222aa85a9499d5d7187395e
+size 1064

run-3/checkpoint-3162/special_tokens_map.json

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

run-3/checkpoint-3162/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-3/checkpoint-3162/trainer_state.json

@@ -0,0 +1,134 @@
+{
+  "best_metric": 0.7855504587155964,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-2635",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 3162,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.747544288635254,
+      "learning_rate": 8.421921303617797e-06,
+      "loss": 1.1824,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7259174311926605,
+      "eval_loss": 1.0221459865570068,
+      "eval_runtime": 2.6361,
+      "eval_samples_per_second": 330.793,
+      "eval_steps_per_second": 2.655,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.284089088439941,
+      "learning_rate": 6.737537042894237e-06,
+      "loss": 0.974,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 0.8609867095947266,
+      "eval_runtime": 2.6102,
+      "eval_samples_per_second": 334.074,
+      "eval_steps_per_second": 2.682,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 14.767024993896484,
+      "learning_rate": 5.053152782170678e-06,
+      "loss": 0.8451,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7809633027522935,
+      "eval_loss": 0.8180754780769348,
+      "eval_runtime": 2.6115,
+      "eval_samples_per_second": 333.903,
+      "eval_steps_per_second": 2.68,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 9.393446922302246,
+      "learning_rate": 3.3687685214471185e-06,
+      "loss": 0.7901,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 0.8021524548530579,
+      "eval_runtime": 2.5985,
+      "eval_samples_per_second": 335.573,
+      "eval_steps_per_second": 2.694,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.2117280960083,
+      "learning_rate": 1.6843842607235593e-06,
+      "loss": 0.7574,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7855504587155964,
+      "eval_loss": 0.7915852665901184,
+      "eval_runtime": 2.6137,
+      "eval_samples_per_second": 333.62,
+      "eval_steps_per_second": 2.678,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": Infinity,
+      "learning_rate": 3.1961750677866402e-09,
+      "loss": 0.7425,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7855504587155964,
+      "eval_loss": 0.7894423007965088,
+      "eval_runtime": 2.611,
+      "eval_samples_per_second": 333.971,
+      "eval_steps_per_second": 2.681,
+      "step": 3162
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 48527917525620.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8183970243354497,
+    "learning_rate": 1.0106305564341356e-05,
+    "num_train_epochs": 6,
+    "temperature": 4
+  }
+}

run-3/checkpoint-3162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19b3d1ab98759ce4a3c2a3b1b6c08002a84c81483690b1cbe27bc016b13e374
+size 5176

run-4/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fffd4916830b77cc5289e2fbf40d6777d4aab66e7cae5fbf83d4b178a5fcd9
+size 17549312

run-4/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827058ee036ab2f3574ad6bdfb4e8ac2bc6458afdc169881fecd3d67082391d5
+size 35123898

run-4/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
+size 14308

run-4/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f64880c063434f17eead5cb1fd93c9b8eae6f9baa2e047c591296b118d949ab
+size 1064

run-4/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-4/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-4/checkpoint-527/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.783256880733945,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/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,
+      "grad_norm": 16.52549171447754,
+      "learning_rate": 2.5580384769538956e-05,
+      "loss": 1.9115,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.783256880733945,
+      "eval_loss": 1.4265761375427246,
+      "eval_runtime": 2.6128,
+      "eval_samples_per_second": 333.747,
+      "eval_steps_per_second": 2.679,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1581,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5410636464880473,
+    "learning_rate": 3.8370577154308436e-05,
+    "num_train_epochs": 3,
+    "temperature": 7
+  }
+}

run-4/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87de9afbd2da70b736ad6a15d120f6fbc2602e77549aefd5eef18e7d1bf815f
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e19b3d1ab98759ce4a3c2a3b1b6c08002a84c81483690b1cbe27bc016b13e374
+oid sha256:e87de9afbd2da70b736ad6a15d120f6fbc2602e77549aefd5eef18e7d1bf815f
 size 5176