initial commit

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9084,
+    "eval_loss": 0.28339844942092896,
+    "eval_mem_cpu_alloc_delta": 1593344,
+    "eval_mem_cpu_peaked_delta": 294912,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 94704128,
+    "eval_runtime": 116.0156,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 86.195,
+    "init_mem_cpu_alloc_delta": 1990225920,
+    "init_mem_cpu_peaked_delta": 378310656,
+    "init_mem_gpu_alloc_delta": 499890176,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 879861760,
+    "train_mem_cpu_peaked_delta": 80719872,
+    "train_mem_gpu_alloc_delta": 1509100544,
+    "train_mem_gpu_peaked_delta": 18135112704,
+    "train_runtime": 16177.7165,
+    "train_samples": 550152,
+    "train_samples_per_second": 0.797
+}

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": "snli",
+  "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": 0.9084,
+    "eval_loss": 0.28339844942092896,
+    "eval_mem_cpu_alloc_delta": 1593344,
+    "eval_mem_cpu_peaked_delta": 294912,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 94704128,
+    "eval_runtime": 116.0156,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 86.195
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e5e0c28b7a558ff71fd13ecc5bef507a571cbbdea47581841195e40a3c07a7
+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": 1990225920,
+    "init_mem_cpu_peaked_delta": 378310656,
+    "init_mem_gpu_alloc_delta": 499890176,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 879861760,
+    "train_mem_cpu_peaked_delta": 80719872,
+    "train_mem_gpu_alloc_delta": 1509100544,
+    "train_mem_gpu_peaked_delta": 18135112704,
+    "train_runtime": 16177.7165,
+    "train_samples": 550152,
+    "train_samples_per_second": 0.797
+}

trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 12897,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.612312940994031e-06,
+      "loss": 0.5637,
+      "step": 500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.22462588198806e-06,
+      "loss": 0.4,
+      "step": 1000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8.83693882298209e-06,
+      "loss": 0.3797,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.44925176397612e-06,
+      "loss": 0.3645,
+      "step": 2000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.061564704970149e-06,
+      "loss": 0.3484,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.673877645964178e-06,
+      "loss": 0.3472,
+      "step": 3000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 7.286190586958209e-06,
+      "loss": 0.3356,
+      "step": 3500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.898503527952237e-06,
+      "loss": 0.3341,
+      "step": 4000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 6.5108164689462675e-06,
+      "loss": 0.3156,
+      "step": 4500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.123129409940297e-06,
+      "loss": 0.3061,
+      "step": 5000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.735442350934326e-06,
+      "loss": 0.3022,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.347755291928356e-06,
+      "loss": 0.2965,
+      "step": 6000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 4.960068232922385e-06,
+      "loss": 0.2934,
+      "step": 6500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.572381173916415e-06,
+      "loss": 0.2979,
+      "step": 7000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 4.184694114910445e-06,
+      "loss": 0.2915,
+      "step": 7500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.797007055904474e-06,
+      "loss": 0.2914,
+      "step": 8000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.4093199968985036e-06,
+      "loss": 0.2909,
+      "step": 8500
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 3.0216329378925334e-06,
+      "loss": 0.2711,
+      "step": 9000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 2.6339458788865628e-06,
+      "loss": 0.2674,
+      "step": 9500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.2462588198805926e-06,
+      "loss": 0.2683,
+      "step": 10000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.858571760874622e-06,
+      "loss": 0.2631,
+      "step": 10500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.4708847018686518e-06,
+      "loss": 0.2637,
+      "step": 11000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 1.0831976428626812e-06,
+      "loss": 0.2643,
+      "step": 11500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.955105838567109e-07,
+      "loss": 0.2689,
+      "step": 12000
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 3.078235248507405e-07,
+      "loss": 0.2695,
+      "step": 12500
+    },
+    {
+      "epoch": 3.0,
+      "step": 12897,
+      "total_flos": 3.159950420124426e+17,
+      "train_runtime": 16177.7165,
+      "train_samples_per_second": 0.797
+    }
+  ],
+  "max_steps": 12897,
+  "num_train_epochs": 3,
+  "total_flos": 3.159950420124426e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25aca90058b828e8681314d06a4c93dc8871b4ac24c52382b111dd5c3b8b040
+size 2415