commit from sam

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.8.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc373b66d56527651e4613cba6008f5021dfe36fe0206d59a3aa67f153f242f6
+size 2219761645

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52c5dd3e7b61b2a0513041afde4903740f3e6fcad21d6746457c49b976f7646
+size 1109908151

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2bc88db5639fe3d100b25f8d9370284950d7178561dd4b4a49491b9fe314e5
+size 15690

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0f822ac2d3545f63d77b2445333934cef92ac0f71feddc9b92d5bd3fda7d6d
+size 623

sentencepiece.bpe.model

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

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 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": 0.9914958477020264,
+  "best_model_checkpoint": "test-squad/checkpoint-6000",
+  "epoch": 2.1849963583394025,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9635833940276766e-05,
+      "loss": 1.2131,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9271667880553534e-05,
+      "loss": 1.2772,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8907501820830302e-05,
+      "loss": 1.1877,
+      "step": 1500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.8543335761107067e-05,
+      "loss": 1.1523,
+      "step": 2000
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 1.0681313276290894,
+      "eval_runtime": 119.1833,
+      "eval_samples_per_second": 89.417,
+      "eval_steps_per_second": 2.802,
+      "step": 2000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.8179169701383832e-05,
+      "loss": 1.0754,
+      "step": 2500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.7815003641660596e-05,
+      "loss": 0.987,
+      "step": 3000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.7450837581937364e-05,
+      "loss": 0.9121,
+      "step": 3500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.7086671522214133e-05,
+      "loss": 0.8929,
+      "step": 4000
+    },
+    {
+      "epoch": 1.46,
+      "eval_loss": 0.9955193996429443,
+      "eval_runtime": 56.1478,
+      "eval_samples_per_second": 189.803,
+      "eval_steps_per_second": 5.949,
+      "step": 4000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.6722505462490897e-05,
+      "loss": 0.8909,
+      "step": 4500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.6358339402767662e-05,
+      "loss": 0.8772,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.599417334304443e-05,
+      "loss": 0.8696,
+      "step": 5500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.5630007283321195e-05,
+      "loss": 0.7111,
+      "step": 6000
+    },
+    {
+      "epoch": 2.18,
+      "eval_loss": 0.9914958477020264,
+      "eval_runtime": 56.0391,
+      "eval_samples_per_second": 190.171,
+      "eval_steps_per_second": 5.96,
+      "step": 6000
+    }
+  ],
+  "max_steps": 27460,
+  "num_train_epochs": 10,
+  "total_flos": 1.63649378451456e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef8d55518333df5c1715e4d97378eeb714c781d2fd8ce9ecd70b8ea126463b0
+size 2607