Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0e48f30763fd0ec52154bdda6e91ed85ffc6fd3ed79f829fb02df5c50aa9fa
+oid sha256:6bc896c70d6094782d316ed4ff72f355a62338eb7a17610edb8898dde5fe8c59
 size 470641664

run-3/checkpoint-106/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

run-3/checkpoint-106/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0e48f30763fd0ec52154bdda6e91ed85ffc6fd3ed79f829fb02df5c50aa9fa
+size 470641664

run-3/checkpoint-106/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1066f156de9416ec408f6a47e725f9a0e00846fb791e971dd5474ef15ba7ab
+size 941404410

run-3/checkpoint-106/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9461ce57ca642305c3edafd8c0e0cfa746276df6556c74321702a8635b1ffc1
+size 14180

run-3/checkpoint-106/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e08949a8c9619e1178b5b8b3d8ff36b49af0be839f5c43e356640db1ae24bf2
+size 1064

run-3/checkpoint-106/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

run-3/checkpoint-106/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-106/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
+size 17098273

run-3/checkpoint-106/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-106/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.7993119266055045,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-3/checkpoint-106",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 106,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.4503490626811981,
+      "eval_runtime": 0.9477,
+      "eval_samples_per_second": 920.118,
+      "eval_steps_per_second": 58.035,
+      "step": 106
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 424,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3419555649158772e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-3/checkpoint-106/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae913b9d9917311801715473b973aed6b7064f0996bb6f6f0e3ab9ab897efb3e
+size 4984

run-3/checkpoint-212/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

run-3/checkpoint-212/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18dc7de4e55089ad012e0cbd4d5998b2e9d5ad8b1ebbacf65813fb3e3ba447e
+size 470641664

run-3/checkpoint-212/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c1491054c487e3608157f3ae9903823d0a16bc915479d65af9231c53a726fa
+size 941404410

run-3/checkpoint-212/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aad64024c239e0abbb01ad3997703e20fef94d4867ddbd3a89f17b07d74ce20
+size 14180

run-3/checkpoint-212/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00fa9134e8899ea0c6296021cb99f5036db8a95308bc03e8ab78743a7b8e3931
+size 1064

run-3/checkpoint-212/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

run-3/checkpoint-212/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-212/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
+size 17098273

run-3/checkpoint-212/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-212/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.8073394495412844,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-3/checkpoint-212",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 212,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.4503490626811981,
+      "eval_runtime": 0.9477,
+      "eval_samples_per_second": 920.118,
+      "eval_steps_per_second": 58.035,
+      "step": 106
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8073394495412844,
+      "eval_loss": 0.43257269263267517,
+      "eval_runtime": 1.0392,
+      "eval_samples_per_second": 839.146,
+      "eval_steps_per_second": 52.928,
+      "step": 212
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 424,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3419555649158772e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-3/checkpoint-212/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae913b9d9917311801715473b973aed6b7064f0996bb6f6f0e3ab9ab897efb3e
+size 4984

run-3/checkpoint-318/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

run-3/checkpoint-318/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b00986ec8e99ec9bfcd4ccdf742bdb4e2a30555988d621183287a83b45d2c73
+size 470641664

run-3/checkpoint-318/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ab24a7117e8e6a90bcff53709902d9e3ed43c0d72105ff7537f850458bbef8
+size 941404410

run-3/checkpoint-318/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16d62d9a350bce2c01b07772d36050731efc5c4f5f31285fef551875e7831a0
+size 14180

run-3/checkpoint-318/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8898f534b95e18f98550bf2084744a1bc461a6981327828253dbbb1ebe6ee9fa
+size 1064

run-3/checkpoint-318/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

run-3/checkpoint-318/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-318/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
+size 17098273

run-3/checkpoint-318/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-318/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.8337155963302753,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-3/checkpoint-318",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 318,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.4503490626811981,
+      "eval_runtime": 0.9477,
+      "eval_samples_per_second": 920.118,
+      "eval_steps_per_second": 58.035,
+      "step": 106
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8073394495412844,
+      "eval_loss": 0.43257269263267517,
+      "eval_runtime": 1.0392,
+      "eval_samples_per_second": 839.146,
+      "eval_steps_per_second": 52.928,
+      "step": 212
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 0.40033113956451416,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 848.263,
+      "eval_steps_per_second": 53.503,
+      "step": 318
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 424,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3419555649158772e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-3/checkpoint-318/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae913b9d9917311801715473b973aed6b7064f0996bb6f6f0e3ab9ab897efb3e
+size 4984

run-3/checkpoint-424/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

run-3/checkpoint-424/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f94b9f076b895c457be18902125e8ff79d84c0baf6e46a1668e5ca3d2a31c1c
+size 470641664

run-3/checkpoint-424/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4711cddda48f5d9ebde562a702e2b08e5941687c545a60992c5f5dcc4e6f7a
+size 941404410

run-3/checkpoint-424/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a57c760827965bd0c415b117690931ee01b7b4021094d1f430b5c8361d6467
+size 14180

run-3/checkpoint-424/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964e8e0e3bf7dd21a33ba2eb4569d1ffee98f70360217372207afc2c1d1d5018
+size 1064

run-3/checkpoint-424/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

run-3/checkpoint-424/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-424/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
+size 17098273

run-3/checkpoint-424/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-424/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.8348623853211009,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-3/checkpoint-424",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 424,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.4503490626811981,
+      "eval_runtime": 0.9477,
+      "eval_samples_per_second": 920.118,
+      "eval_steps_per_second": 58.035,
+      "step": 106
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8073394495412844,
+      "eval_loss": 0.43257269263267517,
+      "eval_runtime": 1.0392,
+      "eval_samples_per_second": 839.146,
+      "eval_steps_per_second": 52.928,
+      "step": 212
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 0.40033113956451416,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 848.263,
+      "eval_steps_per_second": 53.503,
+      "step": 318
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8348623853211009,
+      "eval_loss": 0.4028107821941376,
+      "eval_runtime": 1.2011,
+      "eval_samples_per_second": 726.009,
+      "eval_steps_per_second": 45.792,
+      "step": 424
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 424,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3419555649158772e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-3/checkpoint-424/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae913b9d9917311801715473b973aed6b7064f0996bb6f6f0e3ab9ab897efb3e
+size 4984

run-4/checkpoint-1684/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

run-4/checkpoint-1684/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc39d2132b33b4c6c39547e89bcf3368c78de7a7ace0433c0327aebd9b89887
+size 470641664

run-4/checkpoint-1684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f9e06421817aecd4158d12cdc51bfd3528093b145fd8ae22a448057c2201e4
+size 941404410

run-4/checkpoint-1684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1ce78359f243cfa7302f5705f7e3ff4001b624a0e229968654129955cf4636
+size 14244

run-4/checkpoint-1684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36aa2b6b43cb7c4d638205aa6941a4bfdc273c2bfa008f9ac5ff98124d0e026a
+size 1064