v1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d83c87c39dd5e6d0aa4540b2c74ce843963c83bcd4ca4e3ad49c5ad41ac000
+size 1421612622

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-large"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "init_mem_cpu_alloc_delta": 2172727296,
+    "init_mem_cpu_peaked_delta": 1010765824,
+    "init_mem_gpu_alloc_delta": 1421448192,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 360235008,
+    "train_mem_cpu_peaked_delta": 411705344,
+    "train_mem_gpu_alloc_delta": 4275038720,
+    "train_mem_gpu_peaked_delta": 15916604928,
+    "train_runtime": 4895.7804,
+    "train_samples": 39905,
+    "train_samples_per_second": 1.02
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 4992,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.4750000000000002e-05,
+      "loss": 1.0323,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.975e-05,
+      "loss": 0.8721,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6721768379211426,
+      "eval_loss": 0.8143573999404907,
+      "eval_runtime": 184.4068,
+      "eval_samples_per_second": 54.456,
+      "step": 1248
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 4.38001002004008e-05,
+      "loss": 0.7668,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.7537575150300605e-05,
+      "loss": 0.6107,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7067317366600037,
+      "eval_loss": 0.8285614252090454,
+      "eval_runtime": 184.2958,
+      "eval_samples_per_second": 54.488,
+      "step": 2496
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.12875751503006e-05,
+      "loss": 0.5935,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.5025050100200405e-05,
+      "loss": 0.2335,
+      "step": 3000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.8762525050100204e-05,
+      "loss": 0.2216,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.731925904750824,
+      "eval_loss": 1.0460597276687622,
+      "eval_runtime": 184.6236,
+      "eval_samples_per_second": 54.392,
+      "step": 3744
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 1.25e-05,
+      "loss": 0.1372,
+      "step": 4000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 6.2374749498998e-06,
+      "loss": 0.0771,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7498506307601929,
+      "eval_loss": 1.6021397113800049,
+      "eval_runtime": 184.1793,
+      "eval_samples_per_second": 54.523,
+      "step": 4992
+    },
+    {
+      "epoch": 4.0,
+      "step": 4992,
+      "total_flos": 0,
+      "train_runtime": 4895.7804,
+      "train_samples_per_second": 1.02
+    }
+  ],
+  "max_steps": 4992,
+  "num_train_epochs": 4,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": null
+}