Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: AR_8680_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_8680_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.5867
+- Accuracy: 0.2572
+
+## 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   | 940  | 5.8610          | 0.1440   |
+| 1.4989        | 2.0   | 1880 | 5.5649          | 0.1544   |
+| 1.3199        | 3.0   | 2820 | 5.2958          | 0.1757   |
+| 1.2518        | 4.0   | 3760 | 5.0584          | 0.1987   |
+| 1.1835        | 5.0   | 4700 | 4.9272          | 0.2129   |
+| 1.1333        | 6.0   | 5640 | 4.8093          | 0.2278   |
+| 1.095         | 7.0   | 6580 | 4.7237          | 0.2380   |
+| 1.0654        | 8.0   | 7520 | 4.6550          | 0.2473   |
+| 1.0384        | 9.0   | 8460 | 4.6116          | 0.2542   |
+| 1.0178        | 10.0  | 9400 | 4.5867          | 0.2572   |
+
+
+### 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": 0.25717221135029356,
+    "eval_loss": 4.586706638336182,
+    "eval_runtime": 3.3963,
+    "eval_samples": 200,
+    "eval_samples_per_second": 58.888,
+    "eval_steps_per_second": 2.061,
+    "perplexity": 98.17058594232769,
+    "total_flos": 7.852870729728e+16,
+    "train_loss": 1.1709923861889129,
+    "train_runtime": 8649.5012,
+    "train_samples": 30054,
+    "train_samples_per_second": 34.747,
+    "train_steps_per_second": 1.087
+}

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": 8680
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.25717221135029356,
+    "eval_loss": 4.586706638336182,
+    "eval_runtime": 3.3963,
+    "eval_samples": 200,
+    "eval_samples_per_second": 58.888,
+    "eval_steps_per_second": 2.061,
+    "perplexity": 98.17058594232769
+}

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 sha256:677b7f8db8469e55cf4f52beb9b0a87c641b90ae174ee7cbb2f80f52b71f76a5
+size 368476800

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": 7.852870729728e+16,
+    "train_loss": 1.1709923861889129,
+    "train_runtime": 8649.5012,
+    "train_samples": 30054,
+    "train_samples_per_second": 34.747,
+    "train_steps_per_second": 1.087
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 9400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1439921722113503,
+      "eval_loss": 5.860990047454834,
+      "eval_runtime": 4.0326,
+      "eval_samples_per_second": 49.595,
+      "eval_steps_per_second": 1.736,
+      "step": 940
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 11397.4248046875,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.4989,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.15442270058708416,
+      "eval_loss": 5.5648722648620605,
+      "eval_runtime": 3.5249,
+      "eval_samples_per_second": 56.74,
+      "eval_steps_per_second": 1.986,
+      "step": 1880
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 11682.119140625,
+      "learning_rate": 0.0005286428571428571,
+      "loss": 1.3199,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.17572407045009786,
+      "eval_loss": 5.295774936676025,
+      "eval_runtime": 3.5315,
+      "eval_samples_per_second": 56.633,
+      "eval_steps_per_second": 1.982,
+      "step": 2820
+    },
+    {
+      "epoch": 3.1914893617021276,
+      "grad_norm": 9340.4306640625,
+      "learning_rate": 0.0004572142857142857,
+      "loss": 1.2518,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.19866927592954992,
+      "eval_loss": 5.058368682861328,
+      "eval_runtime": 3.5342,
+      "eval_samples_per_second": 56.589,
+      "eval_steps_per_second": 1.981,
+      "step": 3760
+    },
+    {
+      "epoch": 4.25531914893617,
+      "grad_norm": 9656.10546875,
+      "learning_rate": 0.00038578571428571427,
+      "loss": 1.1835,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.21291585127201565,
+      "eval_loss": 4.927198886871338,
+      "eval_runtime": 3.5327,
+      "eval_samples_per_second": 56.613,
+      "eval_steps_per_second": 1.981,
+      "step": 4700
+    },
+    {
+      "epoch": 5.319148936170213,
+      "grad_norm": 10298.4814453125,
+      "learning_rate": 0.0003143571428571428,
+      "loss": 1.1333,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.22777886497064578,
+      "eval_loss": 4.809349536895752,
+      "eval_runtime": 3.5307,
+      "eval_samples_per_second": 56.645,
+      "eval_steps_per_second": 1.983,
+      "step": 5640
+    },
+    {
+      "epoch": 6.382978723404255,
+      "grad_norm": 10808.5107421875,
+      "learning_rate": 0.00024292857142857143,
+      "loss": 1.095,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.23796477495107632,
+      "eval_loss": 4.723742485046387,
+      "eval_runtime": 3.5271,
+      "eval_samples_per_second": 56.704,
+      "eval_steps_per_second": 1.985,
+      "step": 6580
+    },
+    {
+      "epoch": 7.446808510638298,
+      "grad_norm": 11282.56640625,
+      "learning_rate": 0.0001715,
+      "loss": 1.0654,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.2473385518590998,
+      "eval_loss": 4.654984474182129,
+      "eval_runtime": 3.5239,
+      "eval_samples_per_second": 56.755,
+      "eval_steps_per_second": 1.986,
+      "step": 7520
+    },
+    {
+      "epoch": 8.51063829787234,
+      "grad_norm": 12032.25,
+      "learning_rate": 0.00010007142857142856,
+      "loss": 1.0384,
+      "step": 8000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.25424657534246575,
+      "eval_loss": 4.611558437347412,
+      "eval_runtime": 3.5329,
+      "eval_samples_per_second": 56.611,
+      "eval_steps_per_second": 1.981,
+      "step": 8460
+    },
+    {
+      "epoch": 9.574468085106384,
+      "grad_norm": 11857.1240234375,
+      "learning_rate": 2.864285714285714e-05,
+      "loss": 1.0178,
+      "step": 9000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.25717221135029356,
+      "eval_loss": 4.586706638336182,
+      "eval_runtime": 3.5354,
+      "eval_samples_per_second": 56.57,
+      "eval_steps_per_second": 1.98,
+      "step": 9400
+    },
+    {
+      "epoch": 10.0,
+      "step": 9400,
+      "total_flos": 7.852870729728e+16,
+      "train_loss": 1.1709923861889129,
+      "train_runtime": 8649.5012,
+      "train_samples_per_second": 34.747,
+      "train_steps_per_second": 1.087
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 9400,
+  "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": 7.852870729728e+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 sha256:62c45f9befc045443cf531cb6e34aa47eab49162bdff1dd424b59d0a6bba3f89
+size 5304