Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: DE_42180_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. -->
+
+# DE_42180_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3944
+- Accuracy: 0.2822
+
+## 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   | 872  | 5.6647          | 0.1788   |
+| 1.4046        | 2.0   | 1744 | 5.1683          | 0.2129   |
+| 1.2091        | 3.0   | 2616 | 4.9529          | 0.2289   |
+| 1.1255        | 4.0   | 3488 | 4.8098          | 0.2390   |
+| 1.0815        | 5.0   | 4360 | 4.7006          | 0.2516   |
+| 1.0464        | 6.0   | 5232 | 4.6056          | 0.2593   |
+| 1.0152        | 7.0   | 6104 | 4.5306          | 0.2684   |
+| 1.0152        | 8.0   | 6976 | 4.4713          | 0.2733   |
+| 0.9871        | 9.0   | 7848 | 4.4170          | 0.2794   |
+| 0.9652        | 10.0  | 8720 | 4.3944          | 0.2822   |
+
+
+### 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": 0.28218009755527645,
+    "eval_loss": 4.394373416900635,
+    "eval_runtime": 4.7826,
+    "eval_samples": 201,
+    "eval_samples_per_second": 42.027,
+    "eval_steps_per_second": 1.464,
+    "perplexity": 80.99386547279452,
+    "total_flos": 7.289002524672e+16,
+    "train_loss": 1.0915990706977494,
+    "train_runtime": 9580.1911,
+    "train_samples": 27896,
+    "train_samples_per_second": 29.118,
+    "train_steps_per_second": 0.91
+}

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": 42180
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.28218009755527645,
+    "eval_loss": 4.394373416900635,
+    "eval_runtime": 4.7826,
+    "eval_samples": 201,
+    "eval_samples_per_second": 42.027,
+    "eval_steps_per_second": 1.464,
+    "perplexity": 80.99386547279452
+}

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:c492e886c7c64e3bd00043029751750228d14cfbab3d0e705d44b236bb6d4197
+size 471388800

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": 7.289002524672e+16,
+    "train_loss": 1.0915990706977494,
+    "train_runtime": 9580.1911,
+    "train_samples": 27896,
+    "train_samples_per_second": 29.118,
+    "train_steps_per_second": 0.91
+}

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": 8720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1788318680569754,
+      "eval_loss": 5.664701461791992,
+      "eval_runtime": 5.5561,
+      "eval_samples_per_second": 36.177,
+      "eval_steps_per_second": 1.26,
+      "step": 872
+    },
+    {
+      "epoch": 1.146788990825688,
+      "grad_norm": 12179.96484375,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.4046,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.21293727059419146,
+      "eval_loss": 5.168335437774658,
+      "eval_runtime": 4.9453,
+      "eval_samples_per_second": 40.644,
+      "eval_steps_per_second": 1.415,
+      "step": 1744
+    },
+    {
+      "epoch": 2.293577981651376,
+      "grad_norm": 11207.146484375,
+      "learning_rate": 0.0005223575129533678,
+      "loss": 1.2091,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2289336098373105,
+      "eval_loss": 4.952887535095215,
+      "eval_runtime": 4.9471,
+      "eval_samples_per_second": 40.629,
+      "eval_steps_per_second": 1.415,
+      "step": 2616
+    },
+    {
+      "epoch": 3.4403669724770642,
+      "grad_norm": 10774.6064453125,
+      "learning_rate": 0.0004446373056994818,
+      "loss": 1.1255,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.23901042731547742,
+      "eval_loss": 4.809762954711914,
+      "eval_runtime": 4.9444,
+      "eval_samples_per_second": 40.652,
+      "eval_steps_per_second": 1.416,
+      "step": 3488
+    },
+    {
+      "epoch": 4.587155963302752,
+      "grad_norm": 10522.4833984375,
+      "learning_rate": 0.00036691709844559583,
+      "loss": 1.0815,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.25158941106600075,
+      "eval_loss": 4.700604438781738,
+      "eval_runtime": 4.9483,
+      "eval_samples_per_second": 40.62,
+      "eval_steps_per_second": 1.415,
+      "step": 4360
+    },
+    {
+      "epoch": 5.73394495412844,
+      "grad_norm": 9989.0810546875,
+      "learning_rate": 0.0002891968911917098,
+      "loss": 1.0464,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.25925168677162136,
+      "eval_loss": 4.605610370635986,
+      "eval_runtime": 4.9476,
+      "eval_samples_per_second": 40.626,
+      "eval_steps_per_second": 1.415,
+      "step": 5232
+    },
+    {
+      "epoch": 6.8807339449541285,
+      "grad_norm": 9755.447265625,
+      "learning_rate": 0.00021147668393782382,
+      "loss": 1.0152,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.2683646347518766,
+      "eval_loss": 4.530576705932617,
+      "eval_runtime": 4.9425,
+      "eval_samples_per_second": 40.667,
+      "eval_steps_per_second": 1.416,
+      "step": 6104
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.2732813427967793,
+      "eval_loss": 4.471287250518799,
+      "eval_runtime": 4.945,
+      "eval_samples_per_second": 40.647,
+      "eval_steps_per_second": 1.416,
+      "step": 6976
+    },
+    {
+      "epoch": 8.027522935779816,
+      "grad_norm": 9654.5634765625,
+      "learning_rate": 0.0001337564766839378,
+      "loss": 0.9871,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.2794150577834896,
+      "eval_loss": 4.416961669921875,
+      "eval_runtime": 4.9455,
+      "eval_samples_per_second": 40.643,
+      "eval_steps_per_second": 1.415,
+      "step": 7848
+    },
+    {
+      "epoch": 9.174311926605505,
+      "grad_norm": 9890.5673828125,
+      "learning_rate": 5.603626943005181e-05,
+      "loss": 0.9652,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.28218009755527645,
+      "eval_loss": 4.394373416900635,
+      "eval_runtime": 4.9589,
+      "eval_samples_per_second": 40.534,
+      "eval_steps_per_second": 1.412,
+      "step": 8720
+    },
+    {
+      "epoch": 10.0,
+      "step": 8720,
+      "total_flos": 7.289002524672e+16,
+      "train_loss": 1.0915990706977494,
+      "train_runtime": 9580.1911,
+      "train_samples_per_second": 29.118,
+      "train_steps_per_second": 0.91
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8720,
+  "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": 7.289002524672e+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:bddf7d487a2c8b32d56d6d41c4ec313fdd0d5f8044a69689fd73a4971529e466
+size 5304