initial upload

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9006305939788446,
+    "eval_loss": 0.6653109192848206,
+    "eval_runtime": 44.0823,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 223.037,
+    "eval_steps_per_second": 3.493,
+    "train_loss": 0.11237467917762077,
+    "train_runtime": 16896.1672,
+    "train_samples": 392702,
+    "train_samples_per_second": 232.421,
+    "train_steps_per_second": 1.211
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9006305939788446,
+    "eval_loss": 0.6653109192848206,
+    "eval_runtime": 44.0823,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 223.037,
+    "eval_steps_per_second": 3.493
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d4dfaf65f38bd982ea6a18151f22f5ff1a04fefa9cb7076f5c50385a6ff888
+size 1421620822

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 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.11237467917762077,
+    "train_runtime": 16896.1672,
+    "train_samples": 392702,
+    "train_samples_per_second": 232.421,
+    "train_steps_per_second": 1.211
+}

trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 20460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.951124144672532e-05,
+      "loss": 0.4362,
+      "step": 500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9022482893450638e-05,
+      "loss": 0.3315,
+      "step": 1000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.8533724340175954e-05,
+      "loss": 0.3213,
+      "step": 1500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.804496578690127e-05,
+      "loss": 0.3117,
+      "step": 2000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.755620723362659e-05,
+      "loss": 0.2432,
+      "step": 2500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.7067448680351906e-05,
+      "loss": 0.2339,
+      "step": 3000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.6578690127077226e-05,
+      "loss": 0.2348,
+      "step": 3500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.6089931573802543e-05,
+      "loss": 0.2313,
+      "step": 4000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.560117302052786e-05,
+      "loss": 0.1765,
+      "step": 4500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.5112414467253179e-05,
+      "loss": 0.1595,
+      "step": 5000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.4623655913978497e-05,
+      "loss": 0.1648,
+      "step": 5500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.4134897360703815e-05,
+      "loss": 0.169,
+      "step": 6000
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 1.364613880742913e-05,
+      "loss": 0.1249,
+      "step": 6500
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 1.3157380254154449e-05,
+      "loss": 0.1157,
+      "step": 7000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.2668621700879767e-05,
+      "loss": 0.1155,
+      "step": 7500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.2179863147605085e-05,
+      "loss": 0.1153,
+      "step": 8000
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 1.1691104594330403e-05,
+      "loss": 0.0929,
+      "step": 8500
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 1.1202346041055718e-05,
+      "loss": 0.082,
+      "step": 9000
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 1.0713587487781036e-05,
+      "loss": 0.0836,
+      "step": 9500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 1.0224828934506354e-05,
+      "loss": 0.083,
+      "step": 10000
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 9.736070381231672e-06,
+      "loss": 0.0685,
+      "step": 10500
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 9.24731182795699e-06,
+      "loss": 0.0584,
+      "step": 11000
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 8.758553274682308e-06,
+      "loss": 0.0589,
+      "step": 11500
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 8.269794721407626e-06,
+      "loss": 0.0612,
+      "step": 12000
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 7.781036168132942e-06,
+      "loss": 0.0507,
+      "step": 12500
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 7.292277614858261e-06,
+      "loss": 0.0445,
+      "step": 13000
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 6.8035190615835775e-06,
+      "loss": 0.0448,
+      "step": 13500
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 6.3147605083088955e-06,
+      "loss": 0.0441,
+      "step": 14000
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 5.8260019550342136e-06,
+      "loss": 0.0398,
+      "step": 14500
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 5.337243401759531e-06,
+      "loss": 0.0325,
+      "step": 15000
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 4.848484848484849e-06,
+      "loss": 0.0342,
+      "step": 15500
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 4.359726295210167e-06,
+      "loss": 0.0317,
+      "step": 16000
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 3.870967741935484e-06,
+      "loss": 0.0305,
+      "step": 16500
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 3.3822091886608016e-06,
+      "loss": 0.0249,
+      "step": 17000
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 2.8934506353861196e-06,
+      "loss": 0.0256,
+      "step": 17500
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 2.4046920821114372e-06,
+      "loss": 0.0246,
+      "step": 18000
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 1.915933528836755e-06,
+      "loss": 0.0239,
+      "step": 18500
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 1.4271749755620727e-06,
+      "loss": 0.019,
+      "step": 19000
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 9.384164222873901e-07,
+      "loss": 0.0179,
+      "step": 19500
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 4.496578690127078e-07,
+      "loss": 0.0192,
+      "step": 20000
+    },
+    {
+      "epoch": 10.0,
+      "step": 20460,
+      "total_flos": 1.0717569772564838e+18,
+      "train_loss": 0.11237467917762077,
+      "train_runtime": 16896.1672,
+      "train_samples_per_second": 232.421,
+      "train_steps_per_second": 1.211
+    }
+  ],
+  "max_steps": 20460,
+  "num_train_epochs": 10,
+  "total_flos": 1.0717569772564838e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93248c85e92bae8102f9993d06812f7de89a01a927f9b3e429c487d00b9e9bb
+size 2479