Training in progress, epoch 1

logs/events.out.tfevents.1702286155.joseph_legion.22340.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d780c1e596f6950266700a47a7a3099743cb175d2ef5ff74890db59f944a7dcd
-size 5406
+oid sha256:ebdf790d0254346f996b2dfddde1d51edd39a0ef5e70df3786d3d52ceb146765
+size 6240

logs/events.out.tfevents.1702287558.joseph_legion.22340.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a241ee5aceee463d93548be0d5544c5033a0b701a04c244e49beb4b30ca15fbf
+size 4926

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b23aedd0e49c2c041178a7ff5bee4f3a8ec6412a728426f7ec9fc26bde988632
+oid sha256:d2e18c6daab22eac242f7cbb7bdd5d61a65337092b43e12d101695f0ef7204ea
 size 44692608

run-8/checkpoint-591/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-591/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c8864946db017e8c393c4e50c0e24c47cde04ebd318faa34ca62e2bb09303a
+size 44692608

run-8/checkpoint-591/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2361f232a80d8ec85b5849768e8c1bad409f63f9b810f885412551708719b7e
+size 89430010

run-8/checkpoint-591/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70141f0acfe75a3d2817bbed9f14bb13efceb08fee84dae3818267566941c957
+size 14308

run-8/checkpoint-591/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e834352ba05d39a205e93c2bcfccc6dcd9c0bc034aa2831fcc4ceebf5fbe56ef
+size 1064

run-8/checkpoint-591/special_tokens_map.json

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

run-8/checkpoint-591/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-8/checkpoint-591/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.7840466926070039,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-8\\checkpoint-591",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 591,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.45388964676361e-06,
+      "loss": 0.275,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7752918287937743,
+      "eval_loss": 0.26254990696907043,
+      "eval_runtime": 125.5427,
+      "eval_samples_per_second": 57.319,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.726944823381805e-06,
+      "loss": 0.2662,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.783212896053363,
+      "eval_loss": 0.25981640815734863,
+      "eval_runtime": 125.4546,
+      "eval_samples_per_second": 57.359,
+      "eval_steps_per_second": 0.454,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2633,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7840466926070039,
+      "eval_loss": 0.259382039308548,
+      "eval_runtime": 125.4964,
+      "eval_samples_per_second": 57.34,
+      "eval_steps_per_second": 0.454,
+      "step": 591
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 591,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 133009215775884.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.43662764362367845,
+    "learning_rate": 1.4180834470145417e-05,
+    "num_train_epochs": 3,
+    "temperature": 19
+  }
+}

run-8/checkpoint-591/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3748f4fdacf1ee097e552e18bffbdfb276f83c94eb1a87d1aba98a3482f9c8
+size 4792

run-9/checkpoint-197/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-9/checkpoint-197/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e18c6daab22eac242f7cbb7bdd5d61a65337092b43e12d101695f0ef7204ea
+size 44692608

run-9/checkpoint-197/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8b774b373a4094dd9006e4acebd40cc0ad0b33ac72247f8bae29783f9d8b53
+size 89430010

run-9/checkpoint-197/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfce427b13a79881b8dd7c1ca79db1eca136c641f9f35f4f0773c5f01a793672
+size 14308

run-9/checkpoint-197/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd18678b38529ef44a83c63a81adc73e63f677222b8f4888b771acb1f66180b
+size 1064

run-9/checkpoint-197/special_tokens_map.json

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

run-9/checkpoint-197/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-9/checkpoint-197/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.7761256253474152,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-9\\checkpoint-197",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 197,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.1884492449582221e-05,
+      "loss": 0.3771,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7761256253474152,
+      "eval_loss": 0.35103824734687805,
+      "eval_runtime": 125.0972,
+      "eval_samples_per_second": 57.523,
+      "eval_steps_per_second": 0.456,
+      "step": 197
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 44298765947484.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.625656755680376,
+    "learning_rate": 1.3582277085236825e-05,
+    "num_train_epochs": 8,
+    "temperature": 10
+  }
+}

run-9/checkpoint-197/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c910c119accf4bbf865cec75218ffcb177b5dd17c6f67c36518b8f592afcb473
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3748f4fdacf1ee097e552e18bffbdfb276f83c94eb1a87d1aba98a3482f9c8
+oid sha256:c910c119accf4bbf865cec75218ffcb177b5dd17c6f67c36518b8f592afcb473
 size 4792