Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: RU_30000_41
+  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. -->
+
+# RU_30000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.5860
+- Accuracy: 0.2907
+
+## 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: 0.0006
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 41
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 865  | 5.9242          | 0.1826   |
+| 1.4825        | 2.0   | 1730 | 5.4700          | 0.2094   |
+| 1.278         | 3.0   | 2595 | 5.1790          | 0.2330   |
+| 1.1768        | 4.0   | 3460 | 5.0254          | 0.2463   |
+| 1.1207        | 5.0   | 4325 | 4.8923          | 0.2576   |
+| 1.083         | 6.0   | 5190 | 4.8086          | 0.2663   |
+| 1.0491        | 7.0   | 6055 | 4.7249          | 0.2750   |
+| 1.0491        | 8.0   | 6920 | 4.6643          | 0.2814   |
+| 1.0193        | 9.0   | 7785 | 4.6059          | 0.2879   |
+| 0.9915        | 10.0  | 8650 | 4.5860          | 0.2907   |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.6.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.2907289628180039,
+    "eval_loss": 4.5860066413879395,
+    "eval_runtime": 3.987,
+    "eval_samples": 192,
+    "eval_samples_per_second": 48.156,
+    "eval_steps_per_second": 1.505,
+    "perplexity": 98.10189087773372,
+    "total_flos": 7.227860189184e+16,
+    "train_loss": 1.1371644900988982,
+    "train_runtime": 8936.9854,
+    "train_samples": 27662,
+    "train_samples_per_second": 30.952,
+    "train_steps_per_second": 0.968
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 0,
+  "prefix": "<|endoftext|>",
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.2907289628180039,
+    "eval_loss": 4.5860066413879395,
+    "eval_runtime": 3.987,
+    "eval_samples": 192,
+    "eval_samples_per_second": 48.156,
+    "eval_steps_per_second": 1.505,
+    "perplexity": 98.10189087773372
+}

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": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e61963d7a75ee2614a46099168dca0f6c1dbfdab8de877bf21ff5ef29cb06f
+size 433971840

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 7.227860189184e+16,
+    "train_loss": 1.1371644900988982,
+    "train_runtime": 8936.9854,
+    "train_samples": 27662,
+    "train_samples_per_second": 30.952,
+    "train_steps_per_second": 0.968
+}

trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 8650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.18263820939334638,
+      "eval_loss": 5.924222469329834,
+      "eval_runtime": 4.5576,
+      "eval_samples_per_second": 42.127,
+      "eval_steps_per_second": 1.316,
+      "step": 865
+    },
+    {
+      "epoch": 1.1560693641618498,
+      "grad_norm": 10577.5283203125,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.4825,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2094035388127854,
+      "eval_loss": 5.4699883460998535,
+      "eval_runtime": 4.2355,
+      "eval_samples_per_second": 45.331,
+      "eval_steps_per_second": 1.417,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3121387283236996,
+      "grad_norm": 10539.6064453125,
+      "learning_rate": 0.0005216470588235294,
+      "loss": 1.278,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2329786366601435,
+      "eval_loss": 5.17898416519165,
+      "eval_runtime": 4.1051,
+      "eval_samples_per_second": 46.771,
+      "eval_steps_per_second": 1.462,
+      "step": 2595
+    },
+    {
+      "epoch": 3.468208092485549,
+      "grad_norm": 10572.8818359375,
+      "learning_rate": 0.00044321568627450977,
+      "loss": 1.1768,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.24628995433789955,
+      "eval_loss": 5.025396823883057,
+      "eval_runtime": 4.1012,
+      "eval_samples_per_second": 46.815,
+      "eval_steps_per_second": 1.463,
+      "step": 3460
+    },
+    {
+      "epoch": 4.624277456647399,
+      "grad_norm": 11170.2646484375,
+      "learning_rate": 0.0003647843137254902,
+      "loss": 1.1207,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.2575729778212655,
+      "eval_loss": 4.892265319824219,
+      "eval_runtime": 4.0658,
+      "eval_samples_per_second": 47.223,
+      "eval_steps_per_second": 1.476,
+      "step": 4325
+    },
+    {
+      "epoch": 5.780346820809249,
+      "grad_norm": 11376.833984375,
+      "learning_rate": 0.00028635294117647055,
+      "loss": 1.083,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.26632827788649704,
+      "eval_loss": 4.8085503578186035,
+      "eval_runtime": 4.1174,
+      "eval_samples_per_second": 46.631,
+      "eval_steps_per_second": 1.457,
+      "step": 5190
+    },
+    {
+      "epoch": 6.936416184971098,
+      "grad_norm": 11552.1865234375,
+      "learning_rate": 0.00020792156862745097,
+      "loss": 1.0491,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.2750224233529028,
+      "eval_loss": 4.724864482879639,
+      "eval_runtime": 4.0931,
+      "eval_samples_per_second": 46.908,
+      "eval_steps_per_second": 1.466,
+      "step": 6055
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.2814028864970646,
+      "eval_loss": 4.664273738861084,
+      "eval_runtime": 4.1968,
+      "eval_samples_per_second": 45.749,
+      "eval_steps_per_second": 1.43,
+      "step": 6920
+    },
+    {
+      "epoch": 8.092485549132949,
+      "grad_norm": 12136.4814453125,
+      "learning_rate": 0.00012949019607843136,
+      "loss": 1.0193,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.2878954664057404,
+      "eval_loss": 4.605855464935303,
+      "eval_runtime": 4.1869,
+      "eval_samples_per_second": 45.858,
+      "eval_steps_per_second": 1.433,
+      "step": 7785
+    },
+    {
+      "epoch": 9.248554913294798,
+      "grad_norm": 12644.693359375,
+      "learning_rate": 5.105882352941176e-05,
+      "loss": 0.9915,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.2907289628180039,
+      "eval_loss": 4.5860066413879395,
+      "eval_runtime": 4.1305,
+      "eval_samples_per_second": 46.483,
+      "eval_steps_per_second": 1.453,
+      "step": 8650
+    },
+    {
+      "epoch": 10.0,
+      "step": 8650,
+      "total_flos": 7.227860189184e+16,
+      "train_loss": 1.1371644900988982,
+      "train_runtime": 8936.9854,
+      "train_samples_per_second": 30.952,
+      "train_steps_per_second": 0.968
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8650,
+  "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": 7.227860189184e+16,
+  "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 sha256:375d2c62f2ef95de0bc19788719bdeff239aef20e28fee5bfbb04873c79edaaa
+size 5304