Upload folder using huggingface_hub

Plato_based_on_rugpt3large_based_on_gpt2/README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+base_model: sberbank-ai/rugpt3large_based_on_gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: essays
+  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. -->
+
+# essays
+
+This model is a fine-tuned version of [sberbank-ai/rugpt3large_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3large_based_on_gpt2) on an unknown dataset.
+
+## 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: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use adafactor and the args are:
+No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.0.dev0
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.1

Plato_based_on_rugpt3large_based_on_gpt2/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 4.144250115588096e+16,
+    "train_loss": 2.163431647516066,
+    "train_runtime": 6094.6449,
+    "train_samples": 496,
+    "train_samples_per_second": 0.814,
+    "train_steps_per_second": 0.102
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "sberbank-ai/rugpt3large_based_on_gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1536,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "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": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.0.dev0"
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa63829171766a291cb972f07e4f37c3424e456f970764f3eaffaa54430a1b6
+size 3041230624

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3162fd9bbf0d72da8c7e3f03939791e39e62c0a62ebf2aa14e98622309c25e2d
+size 4703866

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c038c4b34b5166d0a8c82fe4b35a9b74e01ffc1a152bd0d65a765c95b7d50e
+size 14244

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14cd30ada4a550bb16cc3dd046e34b1e10f74d8fc32d4aba22043418e3a7f702
+size 1064

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "trust_remote_code": false,
+  "unk_token": "<unk>"
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.064516129032258,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 8.064516129032258,
+      "grad_norm": 0.49170875549316406,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 2.2228,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.3421371899904e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4854b70cb432cc802db057806dc2f09a84d0752fa15fe70d8e2055b7d762669
+size 5240

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "sberbank-ai/rugpt3large_based_on_gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1536,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "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": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.0.dev0"
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451d6b9ea22525e19df46f2a4bbeaee641949a2ce6c91cff1267ecaede4a56f5
+size 3041230624

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57f69a14cabbc4acd3f721665b7a6167b896f03f218c23c0eee3e6614bb1e54
+size 4703866

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34054fd682b1b0b098dfccbe737778bed62cfa23da58ccb260fe9206f715df3
+size 14244

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf99af278fbb6ef1fb8d874833d70b8772303898f1225c9e13b1c28ecd62aac
+size 1064

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "trust_remote_code": false,
+  "unk_token": "<unk>"
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 8.064516129032258,
+      "grad_norm": 0.49170875549316406,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 2.2228,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.144250115588096e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Plato_based_on_rugpt3large_based_on_gpt2/checkpoint-620/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4854b70cb432cc802db057806dc2f09a84d0752fa15fe70d8e2055b7d762669
+size 5240

Plato_based_on_rugpt3large_based_on_gpt2/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "models/essays",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1536,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "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": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

Plato_based_on_rugpt3large_based_on_gpt2/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.0.dev0"
+}

Plato_based_on_rugpt3large_based_on_gpt2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451d6b9ea22525e19df46f2a4bbeaee641949a2ce6c91cff1267ecaede4a56f5
+size 3041230624

Plato_based_on_rugpt3large_based_on_gpt2/runs/Oct11_16-27-51_7cbffaa6c21d/events.out.tfevents.1728664105.7cbffaa6c21d.13207.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff103708d3681c6cf7cee2b85a4b2e96933db4aeba8bfcc3df0caf5372d88bc
+size 5720

Plato_based_on_rugpt3large_based_on_gpt2/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Plato_based_on_rugpt3large_based_on_gpt2/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "trust_remote_code": false,
+  "unk_token": "<unk>"
+}

Plato_based_on_rugpt3large_based_on_gpt2/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 4.144250115588096e+16,
+    "train_loss": 2.163431647516066,
+    "train_runtime": 6094.6449,
+    "train_samples": 496,
+    "train_samples_per_second": 0.814,
+    "train_steps_per_second": 0.102
+}

Plato_based_on_rugpt3large_based_on_gpt2/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 8.064516129032258,
+      "grad_norm": 0.49170875549316406,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 2.2228,
+      "step": 500
+    },
+    {
+      "epoch": 10.0,
+      "step": 620,
+      "total_flos": 4.144250115588096e+16,
+      "train_loss": 2.163431647516066,
+      "train_runtime": 6094.6449,
+      "train_samples_per_second": 0.814,
+      "train_steps_per_second": 0.102
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.144250115588096e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Plato_based_on_rugpt3large_based_on_gpt2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4854b70cb432cc802db057806dc2f09a84d0752fa15fe70d8e2055b7d762669
+size 5240