These are the model files

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.8736294507980347,
+    "eval_mem_cpu_alloc_delta": 73728,
+    "eval_mem_cpu_peaked_delta": 69632,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 1368289280,
+    "eval_runtime": 1.981,
+    "eval_samples": 500,
+    "eval_samples_per_second": 252.396,
+    "init_mem_cpu_alloc_delta": 2391441408,
+    "init_mem_cpu_peaked_delta": 380411904,
+    "init_mem_gpu_alloc_delta": 500087808,
+    "init_mem_gpu_peaked_delta": 0,
+    "perplexity": 6.511888138461621,
+    "train_mem_cpu_alloc_delta": 2262335488,
+    "train_mem_cpu_peaked_delta": 53248,
+    "train_mem_gpu_alloc_delta": 1501058560,
+    "train_mem_gpu_peaked_delta": 1229582848,
+    "train_runtime": 25.2846,
+    "train_samples": 500,
+    "train_samples_per_second": 1.898
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.8736294507980347,
+    "eval_mem_cpu_alloc_delta": 73728,
+    "eval_mem_cpu_peaked_delta": 69632,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 1368289280,
+    "eval_runtime": 1.981,
+    "eval_samples": 500,
+    "eval_samples_per_second": 252.396,
+    "perplexity": 6.511888138461621
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdc3769ae3f2b4752dc6a39b2e501a814913b7966b847f73de72a8873fe36be
+size 498880850

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 2391441408,
+    "init_mem_cpu_peaked_delta": 380411904,
+    "init_mem_gpu_alloc_delta": 500087808,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 2262335488,
+    "train_mem_cpu_peaked_delta": 53248,
+    "train_mem_gpu_alloc_delta": 1501058560,
+    "train_mem_gpu_peaked_delta": 1229582848,
+    "train_runtime": 25.2846,
+    "train_samples": 500,
+    "train_samples_per_second": 1.898
+}

trainer_state.json

@@ -0,0 +1,23 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 48,
+      "total_flos": 63380213665776.0,
+      "train_runtime": 25.2846,
+      "train_samples_per_second": 1.898
+    }
+  ],
+  "max_steps": 48,
+  "num_train_epochs": 3,
+  "total_flos": 63380213665776.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eab11abe2ea9ab2fc14062da69206d6f58fc40eb057d3f6c96c36a6ac219810
+size 2415