Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a4e3a61c5a6819d9bd9ba23fcdad4d09bf568b77df4a37cbcd3bed482949b91
+oid sha256:4f8ec01152500593829ff0f0c7a3be8665dc76acbde1ff542cbd5ec4be62d9ca
 size 470641664

run-0/checkpoint-1263/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-0/checkpoint-1263/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4987a425ece4f97ebe2a570e48267111ee2e5f8555f34b22192ce05ee5b28475
+size 470641664

run-0/checkpoint-1263/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c259aa99cb87a38d42083d7f39a4d829ba52d2cfe4b7e86e6872f24b073cc6a
+size 941404410

run-0/checkpoint-1263/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3280fcfac134eaf29462f4ce7a21396d7df8855c1378766cbb68faab277b0305
+size 14308

run-0/checkpoint-1263/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221737016b1b6dc7abbc95f0bd7e97af0f963544cad8ce359faa9e1ac3d0b1aa
+size 1064

run-0/checkpoint-1263/sentencepiece.bpe.model

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

run-0/checkpoint-1263/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-0/checkpoint-1263/tokenizer.json

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

run-0/checkpoint-1263/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-0/checkpoint-1263/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.8337155963302753,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-0/checkpoint-1263",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1263,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 0.4295983910560608,
+      "eval_runtime": 1.0076,
+      "eval_samples_per_second": 865.424,
+      "eval_steps_per_second": 54.585,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 8.123950004577637,
+      "learning_rate": 1.3357804670815412e-05,
+      "loss": 0.4991,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.39807233214378357,
+      "eval_runtime": 1.0042,
+      "eval_samples_per_second": 868.388,
+      "eval_steps_per_second": 54.772,
+      "step": 842
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 5.427116870880127,
+      "learning_rate": 9.196494804517776e-06,
+      "loss": 0.3654,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 0.40886953473091125,
+      "eval_runtime": 0.9135,
+      "eval_samples_per_second": 954.617,
+      "eval_steps_per_second": 60.211,
+      "step": 1263
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2105,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 85626186396660.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.751911453711305e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 24
+  }
+}

run-0/checkpoint-1263/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3aa54e4b5eb040628e4ef793b06ccd6e1dd48fa8ded6edc38a1248d8d9cd9f
+size 4984

run-0/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-0/checkpoint-1684/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0995598b12d9b4e71a35fc146a0ccb4cca76512ee74492ae8bc6a414279e4315
+size 470641664

run-0/checkpoint-1684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a6770a177be40542b9ec042db1c4a9c45fc29c4547822c8291a2e114ad7df9
+size 941404410

run-0/checkpoint-1684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a97183ff237de4ad9b87e4c307aae93f175896bded4b871fa77c0ae10a367ce
+size 14308

run-0/checkpoint-1684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8840b82fde56318f170d55f6783322ff533f0a993f62f256e7c6300fef09ea
+size 1064

run-0/checkpoint-1684/sentencepiece.bpe.model

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

run-0/checkpoint-1684/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-0/checkpoint-1684/tokenizer.json

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

run-0/checkpoint-1684/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-0/checkpoint-1684/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.8405963302752294,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-0/checkpoint-1684",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1684,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 0.4295983910560608,
+      "eval_runtime": 1.0076,
+      "eval_samples_per_second": 865.424,
+      "eval_steps_per_second": 54.585,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 8.123950004577637,
+      "learning_rate": 1.3357804670815412e-05,
+      "loss": 0.4991,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.39807233214378357,
+      "eval_runtime": 1.0042,
+      "eval_samples_per_second": 868.388,
+      "eval_steps_per_second": 54.772,
+      "step": 842
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 5.427116870880127,
+      "learning_rate": 9.196494804517776e-06,
+      "loss": 0.3654,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 0.40886953473091125,
+      "eval_runtime": 0.9135,
+      "eval_samples_per_second": 954.617,
+      "eval_steps_per_second": 60.211,
+      "step": 1263
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 1.0015597343444824,
+      "learning_rate": 5.03518493822014e-06,
+      "loss": 0.2923,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8405963302752294,
+      "eval_loss": 0.43070515990257263,
+      "eval_runtime": 0.931,
+      "eval_samples_per_second": 936.614,
+      "eval_steps_per_second": 59.075,
+      "step": 1684
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2105,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 128448478618824.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.751911453711305e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 24
+  }
+}

run-0/checkpoint-1684/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3aa54e4b5eb040628e4ef793b06ccd6e1dd48fa8ded6edc38a1248d8d9cd9f
+size 4984

run-0/checkpoint-2105/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-0/checkpoint-2105/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e618eba8adb30ccfca463c545bc511bd3bace5da4e44ed575b8ee43d53af2136
+size 470641664

run-0/checkpoint-2105/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d6536d428f2bef3d905316338197e405c6f15425a772986a454d02d396dc35
+size 941404410

run-0/checkpoint-2105/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ca3d173a2b65c0f89032545475725e910966bcf5e20d10b6d50bb64da7be7b
+size 14308

run-0/checkpoint-2105/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f58125482936324bdc3202e3664981e3b85dd6760eeb8e339fd6a5450bc072
+size 1064

run-0/checkpoint-2105/sentencepiece.bpe.model

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

run-0/checkpoint-2105/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-0/checkpoint-2105/tokenizer.json

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

run-0/checkpoint-2105/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-0/checkpoint-2105/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.8405963302752294,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-0/checkpoint-1684",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2105,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 0.4295983910560608,
+      "eval_runtime": 1.0076,
+      "eval_samples_per_second": 865.424,
+      "eval_steps_per_second": 54.585,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 8.123950004577637,
+      "learning_rate": 1.3357804670815412e-05,
+      "loss": 0.4991,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.39807233214378357,
+      "eval_runtime": 1.0042,
+      "eval_samples_per_second": 868.388,
+      "eval_steps_per_second": 54.772,
+      "step": 842
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 5.427116870880127,
+      "learning_rate": 9.196494804517776e-06,
+      "loss": 0.3654,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 0.40886953473091125,
+      "eval_runtime": 0.9135,
+      "eval_samples_per_second": 954.617,
+      "eval_steps_per_second": 60.211,
+      "step": 1263
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 1.0015597343444824,
+      "learning_rate": 5.03518493822014e-06,
+      "loss": 0.2923,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8405963302752294,
+      "eval_loss": 0.43070515990257263,
+      "eval_runtime": 0.931,
+      "eval_samples_per_second": 936.614,
+      "eval_steps_per_second": 59.075,
+      "step": 1684
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 18.156158447265625,
+      "learning_rate": 8.738750719225037e-07,
+      "loss": 0.2538,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.838302752293578,
+      "eval_loss": 0.4588472545146942,
+      "eval_runtime": 1.0148,
+      "eval_samples_per_second": 859.266,
+      "eval_steps_per_second": 54.197,
+      "step": 2105
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2105,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 170928927395856.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.751911453711305e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 24
+  }
+}

run-0/checkpoint-2105/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3aa54e4b5eb040628e4ef793b06ccd6e1dd48fa8ded6edc38a1248d8d9cd9f
+size 4984

run-0/checkpoint-842/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-0/checkpoint-842/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4784ca084b0a43fa198b34ad925d28939eba9788418a3ddf34f133c630a2cbcb
+size 470641664

run-0/checkpoint-842/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11d804e4cc145d31d9061e9c8182f4c440fb41ba9e2d9cf8c4e608b320c7233
+size 941404410

run-0/checkpoint-842/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec272268295ea8bc34374cc8be110ac45ec65a2e0880d4c3c9f585375c05a34d
+size 14308

run-0/checkpoint-842/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8c99c2d52c113ff19a3c5d4eeb160106bd8dbbdb7f488b071fc32090c8a214
+size 1064

run-0/checkpoint-842/sentencepiece.bpe.model

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

run-0/checkpoint-842/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-0/checkpoint-842/tokenizer.json

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

run-0/checkpoint-842/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-0/checkpoint-842/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.823394495412844,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-0/checkpoint-842",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 842,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 0.4295983910560608,
+      "eval_runtime": 1.0076,
+      "eval_samples_per_second": 865.424,
+      "eval_steps_per_second": 54.585,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 8.123950004577637,
+      "learning_rate": 1.3357804670815412e-05,
+      "loss": 0.4991,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.39807233214378357,
+      "eval_runtime": 1.0042,
+      "eval_samples_per_second": 868.388,
+      "eval_steps_per_second": 54.772,
+      "step": 842
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2105,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 42505408366176.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.751911453711305e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 24
+  }
+}

run-0/checkpoint-842/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3aa54e4b5eb040628e4ef793b06ccd6e1dd48fa8ded6edc38a1248d8d9cd9f
+size 4984

run-1/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-1/checkpoint-1684/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a921a72cdabca7c39ac9b4fa0be0cc871fbe54bb5eeb97a5ae1bbab6efd3df
+size 470641664

run-1/checkpoint-1684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80aaa8d2c4d28a382afec04f4a59dd03df0e8c190d750e8c9adfe90a07f79acd
+size 941404410

run-1/checkpoint-1684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6134807491dee851aa7553fa633268a2a24961a412137c1864392e5e48f836f
+size 14244

run-1/checkpoint-1684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f297e6c0dfd39d248d448aac313b29c2ee18621b19510394ed51bc68abf1a6
+size 1064