new files added

README.md

@@ -1,3 +1,61 @@
 ---
-license: openrail
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: cont_medium_4_256
+  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. -->
+
+# cont_medium_4_256
+
+This model is a fine-tuned version of [sberbank-ai/rugpt3medium_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3medium_based_on_gpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.7602
+- Accuracy: 0.3436
+
+## 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: 1.5e-05
+- train_batch_size: 6
+- eval_batch_size: 12
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.4091        | 1.0   | 160  | 3.7238          | 0.3472   |
+| 3.2338        | 2.0   | 320  | 3.7393          | 0.3446   |
+| 3.1684        | 3.0   | 480  | 3.7518          | 0.3444   |
+| 3.0989        | 4.0   | 640  | 3.7602          | 0.3436   |
+
+
+### Framework versions
+
+- Transformers 4.23.1
+- Pytorch 1.8.1+cu111
+- Datasets 2.5.2
+- Tokenizers 0.13.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50257
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.3435947712418301,
+    "eval_loss": 3.7601635456085205,
+    "eval_runtime": 0.6972,
+    "eval_samples": 60,
+    "eval_samples_per_second": 86.059,
+    "eval_steps_per_second": 7.172,
+    "perplexity": 42.95545057963037,
+    "train_loss": 3.228607414290309,
+    "train_runtime": 136.9037,
+    "train_samples": 960,
+    "train_samples_per_second": 28.049,
+    "train_steps_per_second": 4.675
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "n_special": 0,
+  "output_past": true,
+  "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 50258
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.3435947712418301,
+    "eval_loss": 3.7601635456085205,
+    "eval_runtime": 0.6972,
+    "eval_samples": 60,
+    "eval_samples_per_second": 86.059,
+    "eval_steps_per_second": 7.172,
+    "perplexity": 42.95545057963037
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8da33443e589200d8f9f4d683972c2b66011f6047887ab88818a45ab1621fec
+size 1524270947

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 3.228607414290309,
+    "train_runtime": 136.9037,
+    "train_samples": 960,
+    "train_samples_per_second": 28.049,
+    "train_steps_per_second": 4.675
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.49765625e-05,
+      "loss": 3.2919,
+      "step": 1
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.2656250000000001e-05,
+      "loss": 3.4091,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.34718954248366013,
+      "eval_loss": 3.7237555980682373,
+      "eval_runtime": 0.6878,
+      "eval_samples_per_second": 87.234,
+      "eval_steps_per_second": 7.27,
+      "step": 160
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.03125e-05,
+      "loss": 3.3483,
+      "step": 200
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 7.96875e-06,
+      "loss": 3.2338,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.344640522875817,
+      "eval_loss": 3.739302396774292,
+      "eval_runtime": 0.6495,
+      "eval_samples_per_second": 92.384,
+      "eval_steps_per_second": 7.699,
+      "step": 320
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.625e-06,
+      "loss": 3.1684,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3443790849673203,
+      "eval_loss": 3.7517521381378174,
+      "eval_runtime": 0.6571,
+      "eval_samples_per_second": 91.306,
+      "eval_steps_per_second": 7.609,
+      "step": 480
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 3.28125e-06,
+      "loss": 3.1497,
+      "step": 500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 9.375e-07,
+      "loss": 3.0989,
+      "step": 600
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3435947712418301,
+      "eval_loss": 3.7601635456085205,
+      "eval_runtime": 0.6542,
+      "eval_samples_per_second": 91.721,
+      "eval_steps_per_second": 7.643,
+      "step": 640
+    },
+    {
+      "epoch": 4.0,
+      "step": 640,
+      "total_flos": 1783105333493760.0,
+      "train_loss": 3.228607414290309,
+      "train_runtime": 136.9037,
+      "train_samples_per_second": 28.049,
+      "train_steps_per_second": 4.675
+    }
+  ],
+  "max_steps": 640,
+  "num_train_epochs": 4,
+  "total_flos": 1783105333493760.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99542e16a7ecd60ffaa393cb4e2878b25ab1025ec072ac1e0070bd5995ead39e
+size 3439