Training in progress, epoch 1

logs/events.out.tfevents.1711297789.8cc2eef2edb7.2942.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840c5ed09f997acfa3b3fdae656cf411d1856ae539d940f83ba82e27f46af715
-size 6136
+oid sha256:94a9f3cc531d88be6825586ad2249493114e18a8efa76cc03bc29ec2d6b80d22
+size 8680

logs/events.out.tfevents.1711297887.8cc2eef2edb7.2942.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d4707e4a108340b458e9c065ee982aa198c039b2e79dac056e2b30742df83c
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d22607b84750171b6c241a03468803316ee141125bf04405d4ba757799fbce
+oid sha256:1e1e22070765ff0aae78098bc646393701ac3b48dd5560933121577d54f049be
 size 17549312

run-12/checkpoint-1485/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-12/checkpoint-1485/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e834c6835cd1a05ca60e908da6143e84dce41114f4209ce8734ddd5079c332
+size 17549312

run-12/checkpoint-1485/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a355745f0bd9e4af042569cf48b6d3fe59d51f7dcf98be9409627e9ed82dc7
+size 35123898

run-12/checkpoint-1485/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c532b5f010242990de7c2dd8b4cd2d14624b3c168e0dbeb7940a12d466a7dc
+size 14308

run-12/checkpoint-1485/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f227bf08eb3123ded5a5ee117d777fcd4ca9b5e5515f1670e8837bde91b2cbd7
+size 1064

run-12/checkpoint-1485/special_tokens_map.json

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

run-12/checkpoint-1485/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-12/checkpoint-1485/trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.6514851485148515,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-594",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1485,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.2921676635742188,
+      "learning_rate": 0.0002222584415009539,
+      "loss": 0.686,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5702970297029702,
+      "eval_f1": 0.44501278772378516,
+      "eval_loss": 0.6809988617897034,
+      "eval_mcc": 0.15639504109088162,
+      "eval_precision": 0.6258992805755396,
+      "eval_recall": 0.34523809523809523,
+      "eval_runtime": 0.9404,
+      "eval_samples_per_second": 537.021,
+      "eval_steps_per_second": 17.015,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.4260432720184326,
+      "learning_rate": 0.0001666938311257154,
+      "loss": 0.6423,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6514851485148515,
+      "eval_f1": 0.7095709570957095,
+      "eval_loss": 0.6317262053489685,
+      "eval_mcc": 0.33175059993848016,
+      "eval_precision": 0.6073446327683616,
+      "eval_recall": 0.8531746031746031,
+      "eval_runtime": 0.9481,
+      "eval_samples_per_second": 532.626,
+      "eval_steps_per_second": 16.875,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.5611865520477295,
+      "learning_rate": 0.00011112922075047695,
+      "loss": 0.6124,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6316831683168317,
+      "eval_f1": 0.7056962025316456,
+      "eval_loss": 0.6464924216270447,
+      "eval_mcc": 0.3062819624263322,
+      "eval_precision": 0.5868421052631579,
+      "eval_recall": 0.8849206349206349,
+      "eval_runtime": 0.9328,
+      "eval_samples_per_second": 541.37,
+      "eval_steps_per_second": 17.152,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.205620288848877,
+      "learning_rate": 5.5564610375238476e-05,
+      "loss": 0.5982,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6475247524752475,
+      "eval_f1": 0.7062706270627062,
+      "eval_loss": 0.6347035765647888,
+      "eval_mcc": 0.3231001092600616,
+      "eval_precision": 0.6045197740112994,
+      "eval_recall": 0.8492063492063492,
+      "eval_runtime": 0.9417,
+      "eval_samples_per_second": 536.25,
+      "eval_steps_per_second": 16.99,
+      "step": 1188
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.662528038024902,
+      "learning_rate": 0.0,
+      "loss": 0.5829,
+      "step": 1485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6514851485148515,
+      "eval_f1": 0.6912280701754385,
+      "eval_loss": 0.6265904307365417,
+      "eval_mcc": 0.31424156599226655,
+      "eval_precision": 0.6194968553459119,
+      "eval_recall": 0.7817460317460317,
+      "eval_runtime": 0.9503,
+      "eval_samples_per_second": 531.404,
+      "eval_steps_per_second": 16.837,
+      "step": 1485
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1485,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3653506329900.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9940046606774494,
+    "learning_rate": 0.0002778230518761924,
+    "num_train_epochs": 5,
+    "temperature": 40
+  }
+}

run-12/checkpoint-1485/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02632af8f846fd2ddd1b29b2be9bc83617b20d72b5cbcd9b8e75794dad0a1456
+size 4920

run-13/checkpoint-297/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-13/checkpoint-297/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1e22070765ff0aae78098bc646393701ac3b48dd5560933121577d54f049be
+size 17549312

run-13/checkpoint-297/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1264ade46a86c6469402d7abfd887311033cef8b3d79e135706436c64b2f16d
+size 35123898

run-13/checkpoint-297/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f5e396c574b9b2ecc40d3f9e87d628a8f4be69caef81905a47fcf8895067e6
+size 14308

run-13/checkpoint-297/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03bccdd93f662acf2c85bae6b03ce094ecdf04d0e1fade1c8dd8b1178a86c19
+size 1064

run-13/checkpoint-297/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-297/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-297/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.594059405940594,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-297",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 297,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.4399616718292236,
+      "learning_rate": 0.0002339700851227397,
+      "loss": 0.6863,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.594059405940594,
+      "eval_f1": 0.5514223194748358,
+      "eval_loss": 0.6703811287879944,
+      "eval_mcc": 0.19115957730889413,
+      "eval_precision": 0.6146341463414634,
+      "eval_recall": 0.5,
+      "eval_runtime": 0.945,
+      "eval_samples_per_second": 534.396,
+      "eval_steps_per_second": 16.931,
+      "step": 297
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1485,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 730701265980.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9967012331264692,
+    "learning_rate": 0.0002924626064034246,
+    "num_train_epochs": 5,
+    "temperature": 49
+  }
+}

run-13/checkpoint-297/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaacb850aeaacff1cb907a263d6c86e2703f0a0edb30636425add5371e86654a
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02632af8f846fd2ddd1b29b2be9bc83617b20d72b5cbcd9b8e75794dad0a1456
+oid sha256:eaacb850aeaacff1cb907a263d6c86e2703f0a0edb30636425add5371e86654a
 size 4920