initial commit

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8731692432872253,
+    "eval_loss": 0.34625929594039917,
+    "eval_mem_cpu_alloc_delta": 249856,
+    "eval_mem_cpu_peaked_delta": 77824,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 94700544,
+    "eval_runtime": 127.1083,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 77.351,
+    "init_mem_cpu_alloc_delta": 1903816704,
+    "init_mem_cpu_peaked_delta": 378310656,
+    "init_mem_gpu_alloc_delta": 499890176,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 1347997696,
+    "train_mem_cpu_peaked_delta": 317304832,
+    "train_mem_gpu_alloc_delta": 1509584384,
+    "train_mem_gpu_peaked_delta": 18134628864,
+    "train_runtime": 11284.7294,
+    "train_samples": 392702,
+    "train_samples_per_second": 0.816
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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": "4.6.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8731692432872253,
+    "eval_loss": 0.34625929594039917,
+    "eval_mem_cpu_alloc_delta": 249856,
+    "eval_mem_cpu_peaked_delta": 77824,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 94700544,
+    "eval_runtime": 127.1083,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 77.351
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee70226272188425fd3a08559358b7b7970f7b07147dfb3dff8bca09380b42a
+size 498682313

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": 1903816704,
+    "init_mem_cpu_peaked_delta": 378310656,
+    "init_mem_gpu_alloc_delta": 499890176,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 1347997696,
+    "train_mem_cpu_peaked_delta": 317304832,
+    "train_mem_gpu_alloc_delta": 1509584384,
+    "train_mem_gpu_peaked_delta": 18134628864,
+    "train_runtime": 11284.7294,
+    "train_samples": 392702,
+    "train_samples_per_second": 0.816
+}

trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 9204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.456757931334203e-06,
+      "loss": 0.6319,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 8.913515862668406e-06,
+      "loss": 0.4731,
+      "step": 1000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 8.370273794002608e-06,
+      "loss": 0.4403,
+      "step": 1500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.827031725336811e-06,
+      "loss": 0.4279,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 7.283789656671013e-06,
+      "loss": 0.4164,
+      "step": 2500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.7405475880052155e-06,
+      "loss": 0.4081,
+      "step": 3000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.197305519339418e-06,
+      "loss": 0.3643,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.65406345067362e-06,
+      "loss": 0.3663,
+      "step": 4000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.110821382007823e-06,
+      "loss": 0.3533,
+      "step": 4500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.567579313342025e-06,
+      "loss": 0.359,
+      "step": 5000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.024337244676228e-06,
+      "loss": 0.3517,
+      "step": 5500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.4810951760104307e-06,
+      "loss": 0.3553,
+      "step": 6000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 2.9378531073446333e-06,
+      "loss": 0.3249,
+      "step": 6500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.3946110386788354e-06,
+      "loss": 0.3133,
+      "step": 7000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.851368970013038e-06,
+      "loss": 0.3178,
+      "step": 7500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.3081269013472406e-06,
+      "loss": 0.3139,
+      "step": 8000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 7.648848326814429e-07,
+      "loss": 0.3131,
+      "step": 8500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.216427640156454e-07,
+      "loss": 0.3173,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "step": 9204,
+      "total_flos": 4999000607677440.0,
+      "train_runtime": 11284.7294,
+      "train_samples_per_second": 0.816
+    }
+  ],
+  "max_steps": 9204,
+  "num_train_epochs": 3,
+  "total_flos": 4999000607677440.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88624d6cb2ed510a014a91d53de61761086e406a1ed2b518f143249670e70ecd
+size 2415