Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: FR_20000_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_20000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.7302
+- Accuracy: 0.3312
+
+## 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   | 998  | 4.7661          | 0.2262   |
+| 1.2399        | 2.0   | 1996 | 4.3380          | 0.2675   |
+| 1.0378        | 3.0   | 2994 | 4.1929          | 0.2781   |
+| 0.9739        | 4.0   | 3992 | 4.1035          | 0.2866   |
+| 0.9423        | 5.0   | 4990 | 4.0010          | 0.2978   |
+| 0.9155        | 6.0   | 5988 | 3.9371          | 0.3040   |
+| 0.8943        | 7.0   | 6986 | 3.8595          | 0.3146   |
+| 0.8736        | 8.0   | 7984 | 3.8007          | 0.3212   |
+| 0.8539        | 9.0   | 8982 | 3.7534          | 0.3274   |
+| 0.8352        | 10.0  | 9980 | 3.7302          | 0.3312   |
+
+
+### 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": 0.3312282620770986,
+    "eval_loss": 3.730226755142212,
+    "eval_runtime": 6.0547,
+    "eval_samples": 229,
+    "eval_samples_per_second": 37.822,
+    "eval_steps_per_second": 1.321,
+    "perplexity": 41.688560187735284,
+    "total_flos": 8.34436104192e+16,
+    "train_loss": 0.9392847890605429,
+    "train_runtime": 9744.779,
+    "train_samples": 31935,
+    "train_samples_per_second": 32.771,
+    "train_steps_per_second": 1.024
+}

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": 20000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.3312282620770986,
+    "eval_loss": 3.730226755142212,
+    "eval_runtime": 6.0547,
+    "eval_samples": 229,
+    "eval_samples_per_second": 37.822,
+    "eval_steps_per_second": 1.321,
+    "perplexity": 41.688560187735284
+}

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:f09e8229a3f94288b9ce040fa7ca1762ac1393b79946a608219b90ff11b8f166
+size 403251840

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": 8.34436104192e+16,
+    "train_loss": 0.9392847890605429,
+    "train_runtime": 9744.779,
+    "train_samples": 31935,
+    "train_samples_per_second": 32.771,
+    "train_steps_per_second": 1.024
+}

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": 9980,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.22615130876182502,
+      "eval_loss": 4.766125679016113,
+      "eval_runtime": 6.8593,
+      "eval_samples_per_second": 33.385,
+      "eval_steps_per_second": 1.166,
+      "step": 998
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 11396.599609375,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.2399,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26749502217588594,
+      "eval_loss": 4.338047504425049,
+      "eval_runtime": 6.3687,
+      "eval_samples_per_second": 35.957,
+      "eval_steps_per_second": 1.256,
+      "step": 1996
+    },
+    {
+      "epoch": 2.004008016032064,
+      "grad_norm": 10861.8779296875,
+      "learning_rate": 0.0005332516703786191,
+      "loss": 1.0378,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2781343200676813,
+      "eval_loss": 4.19285249710083,
+      "eval_runtime": 5.938,
+      "eval_samples_per_second": 38.565,
+      "eval_steps_per_second": 1.347,
+      "step": 2994
+    },
+    {
+      "epoch": 3.006012024048096,
+      "grad_norm": 10864.8798828125,
+      "learning_rate": 0.00046643652561247214,
+      "loss": 0.9739,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.286568847793948,
+      "eval_loss": 4.103455066680908,
+      "eval_runtime": 6.2421,
+      "eval_samples_per_second": 36.687,
+      "eval_steps_per_second": 1.282,
+      "step": 3992
+    },
+    {
+      "epoch": 4.008016032064128,
+      "grad_norm": 10894.2529296875,
+      "learning_rate": 0.00039962138084632514,
+      "loss": 0.9423,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.29784906724549004,
+      "eval_loss": 4.001025676727295,
+      "eval_runtime": 6.0982,
+      "eval_samples_per_second": 37.552,
+      "eval_steps_per_second": 1.312,
+      "step": 4990
+    },
+    {
+      "epoch": 5.01002004008016,
+      "grad_norm": 11722.3232421875,
+      "learning_rate": 0.00033280623608017814,
+      "loss": 0.9155,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.30403609670224496,
+      "eval_loss": 3.937136650085449,
+      "eval_runtime": 6.0876,
+      "eval_samples_per_second": 37.618,
+      "eval_steps_per_second": 1.314,
+      "step": 5988
+    },
+    {
+      "epoch": 6.012024048096192,
+      "grad_norm": 10417.4404296875,
+      "learning_rate": 0.0002659910913140312,
+      "loss": 0.8943,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3146412121108538,
+      "eval_loss": 3.859510898590088,
+      "eval_runtime": 6.1124,
+      "eval_samples_per_second": 37.465,
+      "eval_steps_per_second": 1.309,
+      "step": 6986
+    },
+    {
+      "epoch": 7.014028056112225,
+      "grad_norm": 10313.73828125,
+      "learning_rate": 0.00019917594654788416,
+      "loss": 0.8736,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.32122988574504996,
+      "eval_loss": 3.8007497787475586,
+      "eval_runtime": 6.1187,
+      "eval_samples_per_second": 37.426,
+      "eval_steps_per_second": 1.307,
+      "step": 7984
+    },
+    {
+      "epoch": 8.016032064128256,
+      "grad_norm": 9752.1123046875,
+      "learning_rate": 0.00013236080178173718,
+      "loss": 0.8539,
+      "step": 8000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.32736564147702507,
+      "eval_loss": 3.7534029483795166,
+      "eval_runtime": 4.519,
+      "eval_samples_per_second": 50.675,
+      "eval_steps_per_second": 1.77,
+      "step": 8982
+    },
+    {
+      "epoch": 9.01803607214429,
+      "grad_norm": 9999.22265625,
+      "learning_rate": 6.554565701559019e-05,
+      "loss": 0.8352,
+      "step": 9000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.3312282620770986,
+      "eval_loss": 3.730226755142212,
+      "eval_runtime": 6.1123,
+      "eval_samples_per_second": 37.465,
+      "eval_steps_per_second": 1.309,
+      "step": 9980
+    },
+    {
+      "epoch": 10.0,
+      "step": 9980,
+      "total_flos": 8.34436104192e+16,
+      "train_loss": 0.9392847890605429,
+      "train_runtime": 9744.779,
+      "train_samples_per_second": 32.771,
+      "train_steps_per_second": 1.024
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 9980,
+  "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": 8.34436104192e+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:cdc37fdc15a84011052f212646d924e720a0768c3bf6c46c344a47ae628c66f1
+size 5304