Upload 18 files

README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: code
+  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. -->
+
+# code
+
+This model is a fine-tuned version of [sberbank-ai/rugpt3medium_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3medium_based_on_gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1352
+- Accuracy: 0.7530
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- 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 4.29.0.dev0
+- Pytorch 1.13.0
+- Datasets 2.1.0
+- Tokenizers 0.13.2

added_tokens.json

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

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7530332988402018,
+    "eval_loss": 1.135235071182251,
+    "eval_runtime": 258.9178,
+    "eval_samples": 1339,
+    "eval_samples_per_second": 5.172,
+    "eval_steps_per_second": 5.172,
+    "perplexity": 3.111904976114112,
+    "train_loss": 1.2911211150314672,
+    "train_runtime": 9784.2831,
+    "train_samples": 5323,
+    "train_samples_per_second": 1.632,
+    "train_steps_per_second": 1.632
+}

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": "4.29.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50258
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7530332988402018,
+    "eval_loss": 1.135235071182251,
+    "eval_runtime": 258.9178,
+    "eval_samples": 1339,
+    "eval_samples_per_second": 5.172,
+    "eval_steps_per_second": 5.172,
+    "perplexity": 3.111904976114112
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.29.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc38c2ec73e41fc4e616571ba07dd491c370cf18329469df50b959aec2a08f10
+size 1524265245

runs/May05_10-49-07_82b7056ff6d0/1683283804.8437665/events.out.tfevents.1683283804.82b7056ff6d0.173.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189993c5b74bc46bd707c87391bd7fe7b4262021429d211d9bef08021d3bcdad
+size 5850

runs/May05_10-49-07_82b7056ff6d0/events.out.tfevents.1683283804.82b7056ff6d0.173.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da854e231024a308f5600c77634e769db0eeeeb1235657eeb97f40417253411
+size 9450

runs/May05_10-49-07_82b7056ff6d0/events.out.tfevents.1683293851.82b7056ff6d0.173.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b31de3e619fe0b0b59f3e86abb687c1cf199601368ff82eed94d0a2fcd7eb7
+size 363

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
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": 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": 3.0,
+    "train_loss": 1.2911211150314672,
+    "train_runtime": 9784.2831,
+    "train_samples": 5323,
+    "train_samples_per_second": 1.632,
+    "train_steps_per_second": 1.632
+}

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 15969,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.843446677938506e-05,
+      "loss": 1.9037,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.686893355877012e-05,
+      "loss": 1.7424,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.530340033815518e-05,
+      "loss": 1.6677,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.373786711754024e-05,
+      "loss": 1.6062,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.2172333896925295e-05,
+      "loss": 1.5738,
+      "step": 2500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.060680067631035e-05,
+      "loss": 1.5341,
+      "step": 3000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.9041267455695416e-05,
+      "loss": 1.4979,
+      "step": 3500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.7475734235080466e-05,
+      "loss": 1.4711,
+      "step": 4000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.591020101446553e-05,
+      "loss": 1.4475,
+      "step": 4500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.434466779385059e-05,
+      "loss": 1.4165,
+      "step": 5000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.277913457323565e-05,
+      "loss": 1.3643,
+      "step": 5500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.12136013526207e-05,
+      "loss": 1.286,
+      "step": 6000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.9648068132005762e-05,
+      "loss": 1.2671,
+      "step": 6500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.8082534911390823e-05,
+      "loss": 1.2576,
+      "step": 7000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.6517001690775877e-05,
+      "loss": 1.2502,
+      "step": 7500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.4951468470160937e-05,
+      "loss": 1.2262,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3385935249545994e-05,
+      "loss": 1.223,
+      "step": 8500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.1820402028931055e-05,
+      "loss": 1.214,
+      "step": 9000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.0254868808316112e-05,
+      "loss": 1.1949,
+      "step": 9500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.868933558770117e-05,
+      "loss": 1.1977,
+      "step": 10000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.712380236708623e-05,
+      "loss": 1.1708,
+      "step": 10500
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.5558269146471287e-05,
+      "loss": 1.0994,
+      "step": 11000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.3992735925856349e-05,
+      "loss": 1.0833,
+      "step": 11500
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.2427202705241406e-05,
+      "loss": 1.0865,
+      "step": 12000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.0861669484626465e-05,
+      "loss": 1.073,
+      "step": 12500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 9.296136264011522e-06,
+      "loss": 1.072,
+      "step": 13000
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.730603043396581e-06,
+      "loss": 1.071,
+      "step": 13500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.16506982278164e-06,
+      "loss": 1.0711,
+      "step": 14000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.599536602166698e-06,
+      "loss": 1.0627,
+      "step": 14500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.034003381551757e-06,
+      "loss": 1.06,
+      "step": 15000
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.4684701609368152e-06,
+      "loss": 1.0543,
+      "step": 15500
+    },
+    {
+      "epoch": 3.0,
+      "step": 15969,
+      "total_flos": 2.977670544895181e+16,
+      "train_loss": 1.2911211150314672,
+      "train_runtime": 9784.2831,
+      "train_samples_per_second": 1.632,
+      "train_steps_per_second": 1.632
+    }
+  ],
+  "max_steps": 15969,
+  "num_train_epochs": 3,
+  "total_flos": 2.977670544895181e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ffe0bc0ccfccb47ca9e5119f5d90b4a9d06ad86079a770ef1ca9ab60ab906c
+size 3899