Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: AR_50000_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. -->
+
+# AR_50000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.5747
+- Accuracy: 0.2285
+
+## 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   | 786  | 6.7948          | 0.1587   |
+| 1.6643        | 2.0   | 1572 | 6.4297          | 0.1732   |
+| 1.466         | 3.0   | 2358 | 6.1299          | 0.1882   |
+| 1.3707        | 4.0   | 3144 | 5.9718          | 0.1985   |
+| 1.3707        | 5.0   | 3930 | 5.8569          | 0.2068   |
+| 1.308         | 6.0   | 4716 | 5.7617          | 0.2124   |
+| 1.2627        | 7.0   | 5502 | 5.6931          | 0.2184   |
+| 1.2279        | 8.0   | 6288 | 5.6359          | 0.2233   |
+| 1.1974        | 9.0   | 7074 | 5.5984          | 0.2265   |
+| 1.1974        | 10.0  | 7860 | 5.5747          | 0.2285   |
+
+
+### 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": 0.2284676867941433,
+    "eval_loss": 5.574704170227051,
+    "eval_runtime": 5.4607,
+    "eval_samples": 166,
+    "eval_samples_per_second": 30.399,
+    "eval_steps_per_second": 1.099,
+    "perplexity": 263.6715422056962,
+    "total_flos": 6.569404268544e+16,
+    "train_loss": 1.3368007669618718,
+    "train_runtime": 10231.0545,
+    "train_samples": 25142,
+    "train_samples_per_second": 24.574,
+    "train_steps_per_second": 0.768
+}

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": 50000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.2284676867941433,
+    "eval_loss": 5.574704170227051,
+    "eval_runtime": 5.4607,
+    "eval_samples": 166,
+    "eval_samples_per_second": 30.399,
+    "eval_steps_per_second": 1.099,
+    "perplexity": 263.6715422056962
+}

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 sha256:500bbed20864fa441c51ddfe10542d2163edc39cbd9b229b598479d8c7a1248f
+size 495411840

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": 6.569404268544e+16,
+    "train_loss": 1.3368007669618718,
+    "train_runtime": 10231.0545,
+    "train_samples": 25142,
+    "train_samples_per_second": 24.574,
+    "train_steps_per_second": 0.768
+}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 7860,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.15867776389314597,
+      "eval_loss": 6.794844150543213,
+      "eval_runtime": 6.6858,
+      "eval_samples_per_second": 24.829,
+      "eval_steps_per_second": 0.897,
+      "step": 786
+    },
+    {
+      "epoch": 1.272264631043257,
+      "grad_norm": 11287.4306640625,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.6643,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.173225190389739,
+      "eval_loss": 6.429712295532227,
+      "eval_runtime": 5.2622,
+      "eval_samples_per_second": 31.546,
+      "eval_steps_per_second": 1.14,
+      "step": 1572
+    },
+    {
+      "epoch": 2.544529262086514,
+      "grad_norm": 9641.5859375,
+      "learning_rate": 0.0005126239067055393,
+      "loss": 1.466,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.18816164855115178,
+      "eval_loss": 6.129866123199463,
+      "eval_runtime": 5.4576,
+      "eval_samples_per_second": 30.416,
+      "eval_steps_per_second": 1.099,
+      "step": 2358
+    },
+    {
+      "epoch": 3.816793893129771,
+      "grad_norm": 9910.599609375,
+      "learning_rate": 0.00042516034985422735,
+      "loss": 1.3707,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.1985358262796784,
+      "eval_loss": 5.971755027770996,
+      "eval_runtime": 5.5163,
+      "eval_samples_per_second": 30.093,
+      "eval_steps_per_second": 1.088,
+      "step": 3144
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.2067880131091882,
+      "eval_loss": 5.8568878173828125,
+      "eval_runtime": 5.2842,
+      "eval_samples_per_second": 31.414,
+      "eval_steps_per_second": 1.135,
+      "step": 3930
+    },
+    {
+      "epoch": 5.089058524173028,
+      "grad_norm": 10377.1337890625,
+      "learning_rate": 0.00033769679300291546,
+      "loss": 1.308,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.21243486666823852,
+      "eval_loss": 5.761693000793457,
+      "eval_runtime": 5.5936,
+      "eval_samples_per_second": 29.677,
+      "eval_steps_per_second": 1.073,
+      "step": 4716
+    },
+    {
+      "epoch": 6.361323155216285,
+      "grad_norm": 11166.55078125,
+      "learning_rate": 0.00025023323615160347,
+      "loss": 1.2627,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.2184118077004692,
+      "eval_loss": 5.693126201629639,
+      "eval_runtime": 5.4671,
+      "eval_samples_per_second": 30.363,
+      "eval_steps_per_second": 1.097,
+      "step": 5502
+    },
+    {
+      "epoch": 7.633587786259542,
+      "grad_norm": 11332.716796875,
+      "learning_rate": 0.00016276967930029153,
+      "loss": 1.2279,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.2233277532831915,
+      "eval_loss": 5.635900974273682,
+      "eval_runtime": 5.6909,
+      "eval_samples_per_second": 29.169,
+      "eval_steps_per_second": 1.054,
+      "step": 6288
+    },
+    {
+      "epoch": 8.9058524173028,
+      "grad_norm": 11919.126953125,
+      "learning_rate": 7.530612244897959e-05,
+      "loss": 1.1974,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.22648716195506094,
+      "eval_loss": 5.598357677459717,
+      "eval_runtime": 5.3666,
+      "eval_samples_per_second": 30.932,
+      "eval_steps_per_second": 1.118,
+      "step": 7074
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.2284676867941433,
+      "eval_loss": 5.574704170227051,
+      "eval_runtime": 5.4915,
+      "eval_samples_per_second": 30.229,
+      "eval_steps_per_second": 1.093,
+      "step": 7860
+    },
+    {
+      "epoch": 10.0,
+      "step": 7860,
+      "total_flos": 6.569404268544e+16,
+      "train_loss": 1.3368007669618718,
+      "train_runtime": 10231.0545,
+      "train_samples_per_second": 24.574,
+      "train_steps_per_second": 0.768
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 7860,
+  "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": 6.569404268544e+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 sha256:1449cf4b7cba83a9bc623d1d4af34249878daaa7ef0bd567ce6e32a71b26c710
+size 5304