added model files

Browse files

Files changed (16) hide show

all_results.json +12 -0
config.json +31 -0
eval_nbest_predictions.json +0 -0
eval_predictions.json +0 -0
eval_results.json +6 -0
pytorch_model.bin +3 -0
special_tokens_map.json +7 -0
test_nbest_predictions.json +0 -0
test_predictions.json +0 -0
test_results.json +5 -0
tokenizer.json +0 -0
tokenizer_config.json +14 -0
train_results.json +8 -0
trainer_state.json +193 -0
training_args.bin +3 -0
vocab.txt +0 -0

all_results.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+    "epoch": 15.0,
+    "eval_samples": 1666,
+    "exact_match": 62.69946808510638,
+    "f1": 71.41972213728964,
+    "test_samples": 1626,
+    "train_loss": 0.41084846325115426,
+    "train_runtime": 10637.12,
+    "train_samples": 29233,
+    "train_samples_per_second": 41.223,
+    "train_steps_per_second": 1.289
+}

config.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

eval_nbest_predictions.json ADDED Viewed

The diff for this file is too large to render. See raw diff

eval_predictions.json ADDED Viewed

The diff for this file is too large to render. See raw diff

eval_results.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+    "epoch": 15.0,
+    "eval_samples": 1666,
+    "exact_match": 61.359093937375086,
+    "f1": 70.77972929660706
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:955adbdfdd50ba9afa9053865820df203068bd1fd18bfbd45dc4d8f482134bc8
+size 709129709

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

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

test_nbest_predictions.json ADDED Viewed

The diff for this file is too large to render. See raw diff

test_predictions.json ADDED Viewed

The diff for this file is too large to render. See raw diff

test_results.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+    "exact_match": 62.69946808510638,
+    "f1": 71.41972213728964,
+    "test_samples": 1626
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-multilingual-cased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 15.0,
+    "train_loss": 0.41084846325115426,
+    "train_runtime": 10637.12,
+    "train_samples": 29233,
+    "train_samples_per_second": 41.223,
+    "train_steps_per_second": 1.289
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,193 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.0,
+  "global_step": 13710,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 5.9308,
+      "step": 1
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.85304922850845e-05,
+      "loss": 2.2869,
+      "step": 500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 4.6693607641440116e-05,
+      "loss": 1.5406,
+      "step": 1000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.485672299779574e-05,
+      "loss": 1.1804,
+      "step": 1500
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 4.301983835415136e-05,
+      "loss": 1.0226,
+      "step": 2000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.1182953710506984e-05,
+      "loss": 0.8362,
+      "step": 2500
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.93460690668626e-05,
+      "loss": 0.6883,
+      "step": 3000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 3.750918442321822e-05,
+      "loss": 0.5913,
+      "step": 3500
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 3.5672299779573845e-05,
+      "loss": 0.456,
+      "step": 4000
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 3.383541513592947e-05,
+      "loss": 0.4352,
+      "step": 4500
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 3.1998530492285084e-05,
+      "loss": 0.3212,
+      "step": 5000
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 3.0161645848640706e-05,
+      "loss": 0.3159,
+      "step": 5500
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 2.8324761204996326e-05,
+      "loss": 0.2223,
+      "step": 6000
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 2.6487876561351948e-05,
+      "loss": 0.2304,
+      "step": 6500
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 2.465099191770757e-05,
+      "loss": 0.1776,
+      "step": 7000
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 2.281410727406319e-05,
+      "loss": 0.1594,
+      "step": 7500
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 2.097722263041881e-05,
+      "loss": 0.1383,
+      "step": 8000
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 1.9140337986774432e-05,
+      "loss": 0.1164,
+      "step": 8500
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 1.730345334313005e-05,
+      "loss": 0.1007,
+      "step": 9000
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 1.5466568699485674e-05,
+      "loss": 0.082,
+      "step": 9500
+    },
+    {
+      "epoch": 10.94,
+      "learning_rate": 1.3629684055841293e-05,
+      "loss": 0.0761,
+      "step": 10000
+    },
+    {
+      "epoch": 11.49,
+      "learning_rate": 1.1792799412196914e-05,
+      "loss": 0.0598,
+      "step": 10500
+    },
+    {
+      "epoch": 12.04,
+      "learning_rate": 9.955914768552535e-06,
+      "loss": 0.0599,
+      "step": 11000
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 8.119030124908156e-06,
+      "loss": 0.0395,
+      "step": 11500
+    },
+    {
+      "epoch": 13.13,
+      "learning_rate": 6.282145481263777e-06,
+      "loss": 0.0379,
+      "step": 12000
+    },
+    {
+      "epoch": 13.68,
+      "learning_rate": 4.445260837619398e-06,
+      "loss": 0.0282,
+      "step": 12500
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 2.6083761939750186e-06,
+      "loss": 0.0278,
+      "step": 13000
+    },
+    {
+      "epoch": 14.77,
+      "learning_rate": 7.714915503306393e-07,
+      "loss": 0.0203,
+      "step": 13500
+    },
+    {
+      "epoch": 15.0,
+      "step": 13710,
+      "total_flos": 8.593299100871424e+16,
+      "train_loss": 0.41084846325115426,
+      "train_runtime": 10637.12,
+      "train_samples_per_second": 41.223,
+      "train_steps_per_second": 1.289
+    }
+  ],
+  "max_steps": 13710,
+  "num_train_epochs": 15,
+  "total_flos": 8.593299100871424e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef2ef0c086667bf7b446f711ae785f2cfcfd861cc8d6a454efefb28c5718ee2
+size 3387

vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff