Upload 8 files

config.json

@@ -1,28 +1,29 @@
-{
-  "_name_or_path": "assets/facebookai_xlm_roberta_base",
-  "architectures": [
-    "XLMRobertaForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.47.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
-}
+{
+  "_name_or_path": "assets/facebookai_xlm_roberta_base",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "reference_compile": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98afd8269c67540955c75445024b3e9f34640a3d60f70c5e7cec2f804e829877
+oid sha256:b2e50fb6e5cb06134cfd7be0ba9a6e01675ef132bdca1718c3aecc1c32fb842a
 size 1113205088

special_tokens_map.json

@@ -1,15 +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>"
-}
+{
+  "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>"
+}

tokenizer_config.json

@@ -1,56 +1,56 @@
-{
-  "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": false,
-  "cls_token": "<s>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "extra_special_tokens": {},
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
-}
+{
+  "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": false,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b08346156c4ed671d8256f9ee9e056de5bf583dbb21d4361955304edf918c897
-size 5304
+oid sha256:d0248bcc08258853752fa496fa7a411c44ef6785f0a082234eb6edfe80d95f73
+size 5432

training_args.json

@@ -1,147 +1,150 @@
-{
-    "output_dir": "output/facebookai_xlm_roberta_base_pretrain",
-    "overwrite_output_dir": false,
-    "do_train": false,
-    "do_eval": false,
-    "do_predict": false,
-    "eval_strategy": "no",
-    "prediction_loss_only": false,
-    "per_device_train_batch_size": 8,
-    "per_device_eval_batch_size": 8,
-    "per_gpu_train_batch_size": null,
-    "per_gpu_eval_batch_size": null,
-    "gradient_accumulation_steps": 16,
-    "eval_accumulation_steps": null,
-    "eval_delay": 0,
-    "torch_empty_cache_steps": null,
-    "learning_rate": 2e-05,
-    "weight_decay": 0.01,
-    "adam_beta1": 0.9,
-    "adam_beta2": 0.999,
-    "adam_epsilon": 1e-08,
-    "max_grad_norm": 1.0,
-    "num_train_epochs": 2,
-    "max_steps": -1,
-    "lr_scheduler_type": "linear",
-    "lr_scheduler_kwargs": {},
-    "warmup_ratio": 0.1,
-    "warmup_steps": 0,
-    "log_level": "passive",
-    "log_level_replica": "warning",
-    "log_on_each_node": true,
-    "logging_dir": "logs",
-    "logging_strategy": "steps",
-    "logging_first_step": false,
-    "logging_steps": 10,
-    "logging_nan_inf_filter": true,
-    "save_strategy": "steps",
-    "save_steps": 100,
-    "save_total_limit": 3,
-    "save_safetensors": true,
-    "save_on_each_node": false,
-    "save_only_model": false,
-    "restore_callback_states_from_checkpoint": false,
-    "no_cuda": false,
-    "use_cpu": false,
-    "use_mps_device": false,
-    "seed": 42,
-    "data_seed": null,
-    "jit_mode_eval": false,
-    "use_ipex": false,
-    "bf16": true,
-    "fp16": false,
-    "fp16_opt_level": "O1",
-    "half_precision_backend": "auto",
-    "bf16_full_eval": false,
-    "fp16_full_eval": false,
-    "tf32": null,
-    "local_rank": 0,
-    "ddp_backend": null,
-    "tpu_num_cores": null,
-    "tpu_metrics_debug": false,
-    "debug": [],
-    "dataloader_drop_last": false,
-    "eval_steps": null,
-    "dataloader_num_workers": 0,
-    "dataloader_prefetch_factor": null,
-    "past_index": -1,
-    "run_name": "output/facebookai_xlm_roberta_base_pretrain",
-    "disable_tqdm": false,
-    "remove_unused_columns": true,
-    "label_names": null,
-    "load_best_model_at_end": false,
-    "metric_for_best_model": null,
-    "greater_is_better": null,
-    "ignore_data_skip": false,
-    "fsdp": [],
-    "fsdp_min_num_params": 0,
-    "fsdp_config": {
-        "min_num_params": 0,
-        "xla": false,
-        "xla_fsdp_v2": false,
-        "xla_fsdp_grad_ckpt": false
-    },
-    "fsdp_transformer_layer_cls_to_wrap": null,
-    "accelerator_config": {
-        "split_batches": false,
-        "dispatch_batches": null,
-        "even_batches": true,
-        "use_seedable_sampler": true,
-        "non_blocking": false,
-        "gradient_accumulation_kwargs": null
-    },
-    "deepspeed": null,
-    "label_smoothing_factor": 0.0,
-    "optim": "ademamix_8bit",
-    "optim_args": null,
-    "adafactor": false,
-    "group_by_length": false,
-    "length_column_name": "length",
-    "report_to": [
-        "wandb"
-    ],
-    "ddp_find_unused_parameters": null,
-    "ddp_bucket_cap_mb": null,
-    "ddp_broadcast_buffers": null,
-    "dataloader_pin_memory": true,
-    "dataloader_persistent_workers": false,
-    "skip_memory_metrics": true,
-    "use_legacy_prediction_loop": false,
-    "push_to_hub": false,
-    "resume_from_checkpoint": null,
-    "hub_model_id": null,
-    "hub_strategy": "every_save",
-    "hub_token": "<HUB_TOKEN>",
-    "hub_private_repo": null,
-    "hub_always_push": false,
-    "gradient_checkpointing": false,
-    "gradient_checkpointing_kwargs": null,
-    "include_inputs_for_metrics": false,
-    "include_for_metrics": [],
-    "eval_do_concat_batches": true,
-    "fp16_backend": "auto",
-    "evaluation_strategy": null,
-    "push_to_hub_model_id": null,
-    "push_to_hub_organization": null,
-    "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
-    "mp_parameters": "",
-    "auto_find_batch_size": false,
-    "full_determinism": false,
-    "torchdynamo": null,
-    "ray_scope": "last",
-    "ddp_timeout": 1800,
-    "torch_compile": false,
-    "torch_compile_backend": null,
-    "torch_compile_mode": null,
-    "dispatch_batches": null,
-    "split_batches": null,
-    "include_tokens_per_second": false,
-    "include_num_input_tokens_seen": false,
-    "neftune_noise_alpha": null,
-    "optim_target_modules": null,
-    "batch_eval_metrics": false,
-    "eval_on_start": false,
-    "use_liger_kernel": false,
-    "eval_use_gather_object": false,
-    "average_tokens_across_devices": false
+{
+    "output_dir": "output/facebookai_xlm_roberta_base_pt_e1",
+    "overwrite_output_dir": false,
+    "do_train": false,
+    "do_eval": true,
+    "do_predict": false,
+    "eval_strategy": "steps",
+    "prediction_loss_only": false,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": 8,
+    "per_gpu_train_batch_size": null,
+    "per_gpu_eval_batch_size": null,
+    "gradient_accumulation_steps": 32,
+    "eval_accumulation_steps": null,
+    "eval_delay": 0,
+    "torch_empty_cache_steps": null,
+    "learning_rate": 5e-05,
+    "weight_decay": 0.01,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1.0,
+    "num_train_epochs": 1,
+    "max_steps": -1,
+    "lr_scheduler_type": "warmup_stable_decay",
+    "lr_scheduler_kwargs": {
+        "num_decay_steps": 1562,
+        "num_stable_steps": 12494
+    },
+    "warmup_ratio": 0.1,
+    "warmup_steps": 0,
+    "log_level": "passive",
+    "log_level_replica": "warning",
+    "log_on_each_node": true,
+    "logging_dir": "output/facebookai_xlm_roberta_base_pt_e1/runs/Jan18_11-08-32_Neavo-PC",
+    "logging_strategy": "steps",
+    "logging_first_step": false,
+    "logging_steps": 5,
+    "logging_nan_inf_filter": true,
+    "save_strategy": "no",
+    "save_steps": 0,
+    "save_total_limit": null,
+    "save_safetensors": true,
+    "save_on_each_node": false,
+    "save_only_model": false,
+    "restore_callback_states_from_checkpoint": false,
+    "no_cuda": false,
+    "use_cpu": false,
+    "use_mps_device": false,
+    "seed": 42,
+    "data_seed": null,
+    "jit_mode_eval": false,
+    "use_ipex": false,
+    "bf16": true,
+    "fp16": false,
+    "fp16_opt_level": "O1",
+    "half_precision_backend": "auto",
+    "bf16_full_eval": false,
+    "fp16_full_eval": false,
+    "tf32": null,
+    "local_rank": 0,
+    "ddp_backend": null,
+    "tpu_num_cores": null,
+    "tpu_metrics_debug": false,
+    "debug": [],
+    "dataloader_drop_last": false,
+    "eval_steps": 200,
+    "dataloader_num_workers": 4,
+    "dataloader_prefetch_factor": 8,
+    "past_index": -1,
+    "run_name": "output/facebookai_xlm_roberta_base_pt_e1",
+    "disable_tqdm": false,
+    "remove_unused_columns": true,
+    "label_names": null,
+    "load_best_model_at_end": false,
+    "metric_for_best_model": null,
+    "greater_is_better": null,
+    "ignore_data_skip": false,
+    "fsdp": [],
+    "fsdp_min_num_params": 0,
+    "fsdp_config": {
+        "min_num_params": 0,
+        "xla": false,
+        "xla_fsdp_v2": false,
+        "xla_fsdp_grad_ckpt": false
+    },
+    "fsdp_transformer_layer_cls_to_wrap": null,
+    "accelerator_config": {
+        "split_batches": false,
+        "dispatch_batches": null,
+        "even_batches": true,
+        "use_seedable_sampler": true,
+        "non_blocking": false,
+        "gradient_accumulation_kwargs": null
+    },
+    "deepspeed": null,
+    "label_smoothing_factor": 0.0,
+    "optim": "adamw_torch",
+    "optim_args": null,
+    "adafactor": false,
+    "group_by_length": false,
+    "length_column_name": "length",
+    "report_to": [
+        "wandb"
+    ],
+    "ddp_find_unused_parameters": null,
+    "ddp_bucket_cap_mb": null,
+    "ddp_broadcast_buffers": null,
+    "dataloader_pin_memory": true,
+    "dataloader_persistent_workers": true,
+    "skip_memory_metrics": true,
+    "use_legacy_prediction_loop": false,
+    "push_to_hub": false,
+    "resume_from_checkpoint": null,
+    "hub_model_id": null,
+    "hub_strategy": "every_save",
+    "hub_token": "<HUB_TOKEN>",
+    "hub_private_repo": null,
+    "hub_always_push": false,
+    "gradient_checkpointing": true,
+    "gradient_checkpointing_kwargs": null,
+    "include_inputs_for_metrics": false,
+    "include_for_metrics": [],
+    "eval_do_concat_batches": true,
+    "fp16_backend": "auto",
+    "evaluation_strategy": null,
+    "push_to_hub_model_id": null,
+    "push_to_hub_organization": null,
+    "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+    "mp_parameters": "",
+    "auto_find_batch_size": false,
+    "full_determinism": false,
+    "torchdynamo": null,
+    "ray_scope": "last",
+    "ddp_timeout": 1800,
+    "torch_compile": true,
+    "torch_compile_backend": "inductor",
+    "torch_compile_mode": null,
+    "dispatch_batches": null,
+    "split_batches": null,
+    "include_tokens_per_second": false,
+    "include_num_input_tokens_seen": false,
+    "neftune_noise_alpha": null,
+    "optim_target_modules": null,
+    "batch_eval_metrics": false,
+    "eval_on_start": false,
+    "use_liger_kernel": false,
+    "eval_use_gather_object": false,
+    "average_tokens_across_devices": false
 }