First model

README.md

@@ -1,3 +1,54 @@
----
-license: mit
----
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: '57426955'
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# 57426955
+
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4779
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 12
+- eval_batch_size: 16
+- seed: 1337
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.11.2
+- Pytorch 1.10.0
+- Datasets 1.8.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.4779146909713745,
+    "eval_runtime": 627.5406,
+    "eval_samples": 10042,
+    "eval_samples_per_second": 16.002,
+    "eval_steps_per_second": 1.001,
+    "perplexity": 4.383794576384671,
+    "train_loss": 1.5310567042443597,
+    "train_runtime": 46665.3959,
+    "train_samples": 109963,
+    "train_samples_per_second": 7.069,
+    "train_steps_per_second": 0.295
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "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": "4.11.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.4779146909713745,
+    "eval_runtime": 627.5406,
+    "eval_samples": 10042,
+    "eval_samples_per_second": 16.002,
+    "eval_steps_per_second": 1.001,
+    "perplexity": 4.383794576384671
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bfd8f492f818cc11747e1e925a0239e1065d4e84f1d53b91685f946b67d62a
+size 711982891

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "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, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.5310567042443597,
+    "train_runtime": 46665.3959,
+    "train_samples": 109963,
+    "train_samples_per_second": 7.069,
+    "train_steps_per_second": 0.295
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 13746,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8181289102284306e-05,
+      "loss": 2.1559,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.63625782045686e-05,
+      "loss": 1.9084,
+      "step": 1000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.4543867306852907e-05,
+      "loss": 1.8072,
+      "step": 1500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.272515640913721e-05,
+      "loss": 1.7445,
+      "step": 2000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.090644551142151e-05,
+      "loss": 1.6868,
+      "step": 2500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.9087734613705804e-05,
+      "loss": 1.659,
+      "step": 3000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.726902371599011e-05,
+      "loss": 1.6168,
+      "step": 3500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.545031281827441e-05,
+      "loss": 1.5922,
+      "step": 4000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.363160192055871e-05,
+      "loss": 1.5692,
+      "step": 4500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.181289102284301e-05,
+      "loss": 1.5414,
+      "step": 5000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.9994180125127312e-05,
+      "loss": 1.5159,
+      "step": 5500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.817546922741161e-05,
+      "loss": 1.5054,
+      "step": 6000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.6356758329695913e-05,
+      "loss": 1.4857,
+      "step": 6500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4538047431980213e-05,
+      "loss": 1.4778,
+      "step": 7000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.2719336534264517e-05,
+      "loss": 1.4614,
+      "step": 7500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.0900625636548813e-05,
+      "loss": 1.4475,
+      "step": 8000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.9081914738833114e-05,
+      "loss": 1.4312,
+      "step": 8500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.7263203841117417e-05,
+      "loss": 1.4272,
+      "step": 9000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.5444492943401718e-05,
+      "loss": 1.4061,
+      "step": 9500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.362578204568602e-05,
+      "loss": 1.3994,
+      "step": 10000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.180707114797032e-05,
+      "loss": 1.3973,
+      "step": 10500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 9.98836025025462e-06,
+      "loss": 1.3753,
+      "step": 11000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 8.16964935253892e-06,
+      "loss": 1.3756,
+      "step": 11500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.3509384548232216e-06,
+      "loss": 1.3687,
+      "step": 12000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.532227557107523e-06,
+      "loss": 1.361,
+      "step": 12500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.713516659391823e-06,
+      "loss": 1.3533,
+      "step": 13000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.948057616761241e-07,
+      "loss": 1.3555,
+      "step": 13500
+    },
+    {
+      "epoch": 3.0,
+      "step": 13746,
+      "total_flos": 8.69185921169664e+16,
+      "train_loss": 1.5310567042443597,
+      "train_runtime": 46665.3959,
+      "train_samples_per_second": 7.069,
+      "train_steps_per_second": 0.295
+    }
+  ],
+  "max_steps": 13746,
+  "num_train_epochs": 3,
+  "total_flos": 8.69185921169664e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b91a941f6e95564c63e27127b1f465c789f939765eca53e8b14d9ec705eabeb
+size 2863