Training in progress, epoch 6

logs/events.out.tfevents.1702277265.joseph_legion.22340.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d971f34a17188a90f33332eaaff310eac82a96cab088bc2f72d5a06934c8d7
-size 6366
+oid sha256:617af0d0886d3afd4ff3cd38b1b6fffa6a90d9121388c9f65939a469babf63cd
+size 7326

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5750d27525e32c5a53e301db202b2ef1c356243e137f2537a9026aeb55309bd
+oid sha256:c263ed7680053b0c6647f5947ff43e2263f33c30e7eaea33b614362bff78d60f
 size 44692608

run-5/checkpoint-1182/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-5/checkpoint-1182/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c263ed7680053b0c6647f5947ff43e2263f33c30e7eaea33b614362bff78d60f
+size 44692608

run-5/checkpoint-1182/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2c99178b7f45793d3299e29dd53c6c136838b60c7ab7676cbf4eb7b886c629
+size 89430010

run-5/checkpoint-1182/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9511e5e4163d669edd4526e0777794d8936c52493f7e77dc7be042cfeed886
+size 14308

run-5/checkpoint-1182/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5176f4f412082e1bd1dc832d4064246bccb85b06aad9da1101efbf7633f0d14d
+size 1064

run-5/checkpoint-1182/special_tokens_map.json

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

run-5/checkpoint-1182/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-5/checkpoint-1182/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.7864091161756531,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-5\\checkpoint-1182",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1182,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.941433573951871e-06,
+      "loss": 0.3472,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7540300166759311,
+      "eval_loss": 0.3264233469963074,
+      "eval_runtime": 125.6102,
+      "eval_samples_per_second": 57.288,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.117861311626559e-06,
+      "loss": 0.3304,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7727904391328516,
+      "eval_loss": 0.3193582594394684,
+      "eval_runtime": 125.5179,
+      "eval_samples_per_second": 57.33,
+      "eval_steps_per_second": 0.454,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.2942890493012468e-06,
+      "loss": 0.3247,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7782101167315175,
+      "eval_loss": 0.31648218631744385,
+      "eval_runtime": 125.7064,
+      "eval_samples_per_second": 57.244,
+      "eval_steps_per_second": 0.453,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.4707167869759353e-06,
+      "loss": 0.3224,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7812673707615342,
+      "eval_loss": 0.31448855996131897,
+      "eval_runtime": 125.4689,
+      "eval_samples_per_second": 57.353,
+      "eval_steps_per_second": 0.454,
+      "step": 788
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.6471445246506234e-06,
+      "loss": 0.3204,
+      "step": 985
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7847415230683713,
+      "eval_loss": 0.31334513425827026,
+      "eval_runtime": 125.4012,
+      "eval_samples_per_second": 57.384,
+      "eval_steps_per_second": 0.455,
+      "step": 985
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.235722623253117e-07,
+      "loss": 0.3185,
+      "step": 1182
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7864091161756531,
+      "eval_loss": 0.3128955364227295,
+      "eval_runtime": 125.3008,
+      "eval_samples_per_second": 57.43,
+      "eval_steps_per_second": 0.455,
+      "step": 1182
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1379,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 265501203931764.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5501861057464915,
+    "learning_rate": 5.7650058362771825e-06,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-5/checkpoint-1182/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28cc7611006f792e9dd8ff296313a535b356cc6a1bb6db2c1180dd69535d0c93
+size 4792

run-5/checkpoint-985/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-5/checkpoint-985/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d270fdbbabf2fbd367d466c6cbd5336529bba192e9daaab8ba8cfe92ac34f7f9
+size 44692608

run-5/checkpoint-985/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48158fe0e3a193e948eea320ea03866903eb018bc715ae20e34fc75de80da7a
+size 89430010

run-5/checkpoint-985/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a364bebceef36329237a96faee9e2da941c96eff10dae0acfc327c86066983
+size 14308

run-5/checkpoint-985/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad11861df1a4d9db5d5850fc8954e5e32534eedeba515db07d92d844029e2205
+size 1064

run-5/checkpoint-985/special_tokens_map.json

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

run-5/checkpoint-985/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-5/checkpoint-985/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.7847415230683713,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-5\\checkpoint-985",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 985,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.941433573951871e-06,
+      "loss": 0.3472,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7540300166759311,
+      "eval_loss": 0.3264233469963074,
+      "eval_runtime": 125.6102,
+      "eval_samples_per_second": 57.288,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.117861311626559e-06,
+      "loss": 0.3304,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7727904391328516,
+      "eval_loss": 0.3193582594394684,
+      "eval_runtime": 125.5179,
+      "eval_samples_per_second": 57.33,
+      "eval_steps_per_second": 0.454,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.2942890493012468e-06,
+      "loss": 0.3247,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7782101167315175,
+      "eval_loss": 0.31648218631744385,
+      "eval_runtime": 125.7064,
+      "eval_samples_per_second": 57.244,
+      "eval_steps_per_second": 0.453,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.4707167869759353e-06,
+      "loss": 0.3224,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7812673707615342,
+      "eval_loss": 0.31448855996131897,
+      "eval_runtime": 125.4689,
+      "eval_samples_per_second": 57.353,
+      "eval_steps_per_second": 0.454,
+      "step": 788
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.6471445246506234e-06,
+      "loss": 0.3204,
+      "step": 985
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7847415230683713,
+      "eval_loss": 0.31334513425827026,
+      "eval_runtime": 125.4012,
+      "eval_samples_per_second": 57.384,
+      "eval_steps_per_second": 0.455,
+      "step": 985
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1379,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 221342066021952.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5501861057464915,
+    "learning_rate": 5.7650058362771825e-06,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-5/checkpoint-985/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28cc7611006f792e9dd8ff296313a535b356cc6a1bb6db2c1180dd69535d0c93
+size 4792