Update from ubuntu

all_results.json

@@ -1,11 +0,0 @@
-{
-    "epoch": 3.0,
-    "eval_accuracy": 0.9128440366972477,
-    "eval_loss": 0.25951144099235535,
-    "eval_runtime": 2.8609,
-    "eval_samples": 872,
-    "eval_samples_per_second": 304.803,
-    "train_runtime": 1054.1551,
-    "train_samples": 67349,
-    "train_samples_per_second": 5.991
-}

config.json

@@ -1,28 +0,0 @@
-{
-  "_name_or_path": "google/electra-small-discriminator",
-  "architectures": [
-    "ElectraForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "embedding_size": 128,
-  "finetuning_task": "sst2",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
-  "initializer_range": 0.02,
-  "intermediate_size": 1024,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "electra",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "summary_activation": "gelu",
-  "summary_last_dropout": 0.1,
-  "summary_type": "first",
-  "summary_use_proj": true,
-  "transformers_version": "4.6.0.dev0",
-  "type_vocab_size": 2,
-  "vocab_size": 30522
-}

eval_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 3.0,
-    "eval_accuracy": 0.9128440366972477,
-    "eval_loss": 0.25951144099235535,
-    "eval_runtime": 2.8609,
-    "eval_samples": 872,
-    "eval_samples_per_second": 304.803
-}

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b790bb52533c164846e151a013616e3616b5c2cfcec2a7ec704d7c4685bde328
-size 54286495

special_tokens_map.json

@@ -1 +0,0 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -1 +0,0 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-small-discriminator"}

train_results.json

@@ -1,6 +0,0 @@
-{
-    "epoch": 3.0,
-    "train_runtime": 1054.1551,
-    "train_samples": 67349,
-    "train_samples_per_second": 5.991
-}

trainer_state.json

@@ -1,95 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "global_step": 6315,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.24,
-      "learning_rate": 1.8416468725257326e-05,
-      "loss": 0.4758,
-      "step": 500
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 1.6832937450514647e-05,
-      "loss": 0.3164,
-      "step": 1000
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 1.5249406175771972e-05,
-      "loss": 0.2771,
-      "step": 1500
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 1.3665874901029297e-05,
-      "loss": 0.2512,
-      "step": 2000
-    },
-    {
-      "epoch": 1.19,
-      "learning_rate": 1.208234362628662e-05,
-      "loss": 0.217,
-      "step": 2500
-    },
-    {
-      "epoch": 1.43,
-      "learning_rate": 1.0498812351543943e-05,
-      "loss": 0.2064,
-      "step": 3000
-    },
-    {
-      "epoch": 1.66,
-      "learning_rate": 8.915281076801267e-06,
-      "loss": 0.2047,
-      "step": 3500
-    },
-    {
-      "epoch": 1.9,
-      "learning_rate": 7.331749802058591e-06,
-      "loss": 0.1887,
-      "step": 4000
-    },
-    {
-      "epoch": 2.14,
-      "learning_rate": 5.748218527315916e-06,
-      "loss": 0.1816,
-      "step": 4500
-    },
-    {
-      "epoch": 2.38,
-      "learning_rate": 4.164687252573238e-06,
-      "loss": 0.1662,
-      "step": 5000
-    },
-    {
-      "epoch": 2.61,
-      "learning_rate": 2.581155977830562e-06,
-      "loss": 0.171,
-      "step": 5500
-    },
-    {
-      "epoch": 2.85,
-      "learning_rate": 9.976247030878861e-07,
-      "loss": 0.1562,
-      "step": 6000
-    },
-    {
-      "epoch": 3.0,
-      "step": 6315,
-      "total_flos": 2102475452742144.0,
-      "train_runtime": 1054.1551,
-      "train_samples_per_second": 5.991
-    }
-  ],
-  "max_steps": 6315,
-  "num_train_epochs": 3,
-  "total_flos": 2102475452742144.0,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e7c074ae21d10b4edbf3818d9c99f6a1184770fb3a063efdc9a373b1d964e1a2
-size 2415