Training in progress, step 500

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+base_model: cointegrated/rubert-tiny
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [cointegrated/rubert-tiny](https://huggingface.co/cointegrated/rubert-tiny) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5832
+- Accuracy: 0.5167
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.5167136043030395,
+    "eval_loss": 2.5832159519195557,
+    "eval_runtime": 62.4515,
+    "eval_samples": 15263,
+    "eval_samples_per_second": 244.398,
+    "eval_steps_per_second": 7.638,
+    "perplexity": 13.23964783936109,
+    "train_loss": 3.04393067064311,
+    "train_runtime": 385.498,
+    "train_samples": 35613,
+    "train_samples_per_second": 92.382,
+    "train_steps_per_second": 2.887
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29564
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.5167136043030395,
+    "eval_loss": 2.5832159519195557,
+    "eval_runtime": 62.4515,
+    "eval_samples": 15263,
+    "eval_samples_per_second": 244.398,
+    "eval_steps_per_second": 7.638,
+    "perplexity": 13.23964783936109
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b9eea13496ee952998eaa62a72f4de0dd223f682a5b4db70f7a92bc501888b
+size 47264040

runs/Feb25_10-29-44_e77a61bc3de0/events.out.tfevents.1708857000.e77a61bc3de0.6826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4604f0053a35b601c702ee480abb2db026ab97348acc8056b48a8009f47fa634
+size 4614

runs/Feb25_10-32-21_e77a61bc3de0/events.out.tfevents.1708857146.e77a61bc3de0.7516.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9baf0b0085289efb645cdf5e7d619dc09d232d42ddda8686fc49a672f4af3fb1
+size 5390

runs/Feb25_10-32-21_e77a61bc3de0/events.out.tfevents.1708857594.e77a61bc3de0.7516.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec3aad5c238784aafe439506a9cef10a9bb94329d635249d8e26eb7dd77ee0c3
+size 411

runs/Feb25_10-54-45_e77a61bc3de0/events.out.tfevents.1708858488.e77a61bc3de0.13217.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31a290f7d79a5cbe9779ca7f5706793205cee87beec603bfba7cdc71278b97b
+size 4865

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 3.04393067064311,
+    "train_runtime": 385.498,
+    "train_samples": 35613,
+    "train_samples_per_second": 92.382,
+    "train_steps_per_second": 2.887
+}

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.323787212371826,
+      "learning_rate": 2.75381850853549e-05,
+      "loss": 3.2259,
+      "step": 500
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.575705528259277,
+      "learning_rate": 5.0763701707097935e-06,
+      "loss": 2.9056,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "step": 1113,
+      "total_flos": 159583189651080.0,
+      "train_loss": 3.04393067064311,
+      "train_runtime": 385.498,
+      "train_samples_per_second": 92.382,
+      "train_steps_per_second": 2.887
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1113,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 159583189651080.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53e7d980c2f7e3631977781c63fcec5c68709b4f89cbcebab446b708e3941d8
+size 4984