Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: FR_10000_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. -->
+
+# FR_10000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.4917
+- Accuracy: 0.3542
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.2234        | 1.0   | 1051  | 4.6312          | 0.2227   |
+| 1.015         | 2.0   | 2102  | 4.2010          | 0.2651   |
+| 0.9468        | 3.0   | 3153  | 4.0149          | 0.2858   |
+| 0.9083        | 4.0   | 4204  | 3.8844          | 0.3032   |
+| 0.8769        | 5.0   | 5255  | 3.7722          | 0.3163   |
+| 0.8502        | 6.0   | 6306  | 3.6949          | 0.3261   |
+| 0.8276        | 7.0   | 7357  | 3.6137          | 0.3367   |
+| 0.8078        | 8.0   | 8408  | 3.5608          | 0.3435   |
+| 0.7895        | 9.0   | 9459  | 3.5129          | 0.3507   |
+| 0.7746        | 10.0  | 10510 | 3.4917          | 0.3542   |
+
+
+### 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": 0.35421552295773967,
+    "eval_loss": 3.491698741912842,
+    "eval_runtime": 5.8959,
+    "eval_samples": 242,
+    "eval_samples_per_second": 41.046,
+    "eval_steps_per_second": 1.357,
+    "perplexity": 32.84168990215025,
+    "total_flos": 8.78333165568e+16,
+    "train_loss": 0.8954192244133191,
+    "train_runtime": 9693.5758,
+    "train_samples": 33615,
+    "train_samples_per_second": 34.678,
+    "train_steps_per_second": 1.084
+}

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": 10000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.35421552295773967,
+    "eval_loss": 3.491698741912842,
+    "eval_runtime": 5.8959,
+    "eval_samples": 242,
+    "eval_samples_per_second": 41.046,
+    "eval_steps_per_second": 1.357,
+    "perplexity": 32.84168990215025
+}

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:ff722ff6f26923debfbe9e6a10a8c942c2c86d77dbc9af484293fb8721fd2c5b
+size 372531840

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": 8.78333165568e+16,
+    "train_loss": 0.8954192244133191,
+    "train_runtime": 9693.5758,
+    "train_samples": 33615,
+    "train_samples_per_second": 34.678,
+    "train_steps_per_second": 1.084
+}

trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 10510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9514747859181731,
+      "grad_norm": 12745.587890625,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.2234,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.22268764859051285,
+      "eval_loss": 4.631209373474121,
+      "eval_runtime": 6.498,
+      "eval_samples_per_second": 37.242,
+      "eval_steps_per_second": 1.231,
+      "step": 1051
+    },
+    {
+      "epoch": 1.9029495718363463,
+      "grad_norm": 11723.8271484375,
+      "learning_rate": 0.0005369716088328075,
+      "loss": 1.015,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26512590771619415,
+      "eval_loss": 4.201041221618652,
+      "eval_runtime": 5.77,
+      "eval_samples_per_second": 41.941,
+      "eval_steps_per_second": 1.386,
+      "step": 2102
+    },
+    {
+      "epoch": 2.8544243577545196,
+      "grad_norm": 10506.5712890625,
+      "learning_rate": 0.00047388012618296526,
+      "loss": 0.9468,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.28578706474098753,
+      "eval_loss": 4.014913558959961,
+      "eval_runtime": 5.9155,
+      "eval_samples_per_second": 40.91,
+      "eval_steps_per_second": 1.352,
+      "step": 3153
+    },
+    {
+      "epoch": 3.8058991436726926,
+      "grad_norm": 9833.72265625,
+      "learning_rate": 0.000410788643533123,
+      "loss": 0.9083,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.30322977147385616,
+      "eval_loss": 3.8843796253204346,
+      "eval_runtime": 5.9819,
+      "eval_samples_per_second": 40.455,
+      "eval_steps_per_second": 1.337,
+      "step": 4204
+    },
+    {
+      "epoch": 4.757373929590866,
+      "grad_norm": 9816.0380859375,
+      "learning_rate": 0.0003476971608832807,
+      "loss": 0.8769,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3162653038120037,
+      "eval_loss": 3.772235870361328,
+      "eval_runtime": 5.9202,
+      "eval_samples_per_second": 40.877,
+      "eval_steps_per_second": 1.351,
+      "step": 5255
+    },
+    {
+      "epoch": 5.708848715509039,
+      "grad_norm": 9225.9716796875,
+      "learning_rate": 0.00028460567823343844,
+      "loss": 0.8502,
+      "step": 6000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.32605003962413676,
+      "eval_loss": 3.6949210166931152,
+      "eval_runtime": 5.9591,
+      "eval_samples_per_second": 40.61,
+      "eval_steps_per_second": 1.342,
+      "step": 6306
+    },
+    {
+      "epoch": 6.660323501427213,
+      "grad_norm": 9708.4267578125,
+      "learning_rate": 0.00022151419558359621,
+      "loss": 0.8276,
+      "step": 7000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.33672429687373645,
+      "eval_loss": 3.613666296005249,
+      "eval_runtime": 5.9886,
+      "eval_samples_per_second": 40.41,
+      "eval_steps_per_second": 1.336,
+      "step": 7357
+    },
+    {
+      "epoch": 7.611798287345385,
+      "grad_norm": 9902.1474609375,
+      "learning_rate": 0.00015842271293375394,
+      "loss": 0.8078,
+      "step": 8000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.3435170060325727,
+      "eval_loss": 3.560777425765991,
+      "eval_runtime": 5.8919,
+      "eval_samples_per_second": 41.073,
+      "eval_steps_per_second": 1.358,
+      "step": 8408
+    },
+    {
+      "epoch": 8.56327307326356,
+      "grad_norm": 9983.5361328125,
+      "learning_rate": 9.533123028391166e-05,
+      "loss": 0.7895,
+      "step": 9000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.3506978700004852,
+      "eval_loss": 3.5129082202911377,
+      "eval_runtime": 6.0614,
+      "eval_samples_per_second": 39.925,
+      "eval_steps_per_second": 1.32,
+      "step": 9459
+    },
+    {
+      "epoch": 9.514747859181732,
+      "grad_norm": 10257.3037109375,
+      "learning_rate": 3.22397476340694e-05,
+      "loss": 0.7746,
+      "step": 10000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.35421552295773967,
+      "eval_loss": 3.491698741912842,
+      "eval_runtime": 5.9119,
+      "eval_samples_per_second": 40.935,
+      "eval_steps_per_second": 1.353,
+      "step": 10510
+    },
+    {
+      "epoch": 10.0,
+      "step": 10510,
+      "total_flos": 8.78333165568e+16,
+      "train_loss": 0.8954192244133191,
+      "train_runtime": 9693.5758,
+      "train_samples_per_second": 34.678,
+      "train_steps_per_second": 1.084
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10510,
+  "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": 8.78333165568e+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:fadd5295d0b49dfe2e5990dbbca2630c90d36db1730b2b03a970a1dc0795d2b5
+size 5304