Upload 13 files

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "sberbank-ai/rugpt3small_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,
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 50264
+}

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": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b48bb88717fa7e4d9bf8812f97382740ecd368ff5946ca0c1c507040373c18b
+size 500941440

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ff1b874446290e3364184801ae2031ea1e86c22688f9b63375bd78124ffd57
+size 1001976325

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c825e42f9ec1557d98f7f80c719d5c6bf1489ae976d68fd566133d5b620efc
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a70360f0689566ec8797eeb3f241d2155b29e05af08f526b5122083e26599c
+size 627

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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",
+  "extra_special_tokens": {},
+  "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>"
+}

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2388,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8375209380234506,
+      "grad_norm": 1.082448959350586,
+      "learning_rate": 3.953098827470687e-05,
+      "loss": 1.6167,
+      "step": 500
+    },
+    {
+      "epoch": 0.8375209380234506,
+      "eval_CEFR_f1": 0.3644590403211093,
+      "eval_loss": 1.5046868324279785,
+      "eval_rouge1": 0.31,
+      "eval_rouge2": 0.13131313131313133,
+      "eval_runtime": 15.7708,
+      "eval_samples_per_second": 6.341,
+      "eval_steps_per_second": 0.127,
+      "step": 500
+    },
+    {
+      "epoch": 1.675041876046901,
+      "grad_norm": 1.0536589622497559,
+      "learning_rate": 2.906197654941374e-05,
+      "loss": 1.3693,
+      "step": 1000
+    },
+    {
+      "epoch": 1.675041876046901,
+      "eval_CEFR_f1": 0.3023575040876079,
+      "eval_loss": 1.43952214717865,
+      "eval_rouge1": 0.35,
+      "eval_rouge2": 0.15151515151515152,
+      "eval_runtime": 17.1613,
+      "eval_samples_per_second": 5.827,
+      "eval_steps_per_second": 0.117,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5125628140703515,
+      "grad_norm": 1.0843034982681274,
+      "learning_rate": 1.8592964824120602e-05,
+      "loss": 1.2575,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5125628140703515,
+      "eval_CEFR_f1": 0.30705782312925173,
+      "eval_loss": 1.4209942817687988,
+      "eval_rouge1": 0.33,
+      "eval_rouge2": 0.13131313131313133,
+      "eval_runtime": 16.7011,
+      "eval_samples_per_second": 5.988,
+      "eval_steps_per_second": 0.12,
+      "step": 1500
+    },
+    {
+      "epoch": 3.3500837520938025,
+      "grad_norm": 1.1220632791519165,
+      "learning_rate": 8.123953098827471e-06,
+      "loss": 1.1912,
+      "step": 2000
+    },
+    {
+      "epoch": 3.3500837520938025,
+      "eval_CEFR_f1": 0.31766408627240766,
+      "eval_loss": 1.4111934900283813,
+      "eval_rouge1": 0.34,
+      "eval_rouge2": 0.1414141414141414,
+      "eval_runtime": 15.8447,
+      "eval_samples_per_second": 6.311,
+      "eval_steps_per_second": 0.126,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2388,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1.2855167870976e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a83ad47773a500690c389f0d8d3b47e7d1e969b30fd0a37bedd7bb85e841bf
+size 4859