Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: FR_30000_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_30000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.7585
+- Accuracy: 0.3321
+
+## 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   | 976  | 4.7817          | 0.2336   |
+| 1.2461        | 2.0   | 1952 | 4.3996          | 0.2655   |
+| 1.0362        | 3.0   | 2928 | 4.2040          | 0.2850   |
+| 0.9715        | 4.0   | 3904 | 4.0976          | 0.2939   |
+| 0.9346        | 5.0   | 4880 | 4.0111          | 0.3034   |
+| 0.9069        | 6.0   | 5856 | 3.9493          | 0.3088   |
+| 0.8835        | 7.0   | 6832 | 3.8856          | 0.3171   |
+| 0.8622        | 8.0   | 7808 | 3.8233          | 0.3234   |
+| 0.8415        | 9.0   | 8784 | 3.7798          | 0.3297   |
+| 0.8265        | 10.0  | 9760 | 3.7585          | 0.3321   |
+
+
+### 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": 0.3321018314568287,
+    "eval_loss": 3.758513927459717,
+    "eval_runtime": 6.8221,
+    "eval_samples": 223,
+    "eval_samples_per_second": 32.688,
+    "eval_steps_per_second": 1.026,
+    "perplexity": 42.8846489026855,
+    "total_flos": 8.16015015936e+16,
+    "train_loss": 0.9351713461954085,
+    "train_runtime": 10046.3917,
+    "train_samples": 31230,
+    "train_samples_per_second": 31.086,
+    "train_steps_per_second": 0.971
+}

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": 30000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.3321018314568287,
+    "eval_loss": 3.758513927459717,
+    "eval_runtime": 6.8221,
+    "eval_samples": 223,
+    "eval_samples_per_second": 32.688,
+    "eval_steps_per_second": 1.026,
+    "perplexity": 42.8846489026855
+}

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 sha256:2412b6fd9ec80d6c1d3f67e7830b6b98781701923d46b8125165cb39beaed289
+size 433971840

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": 8.16015015936e+16,
+    "train_loss": 0.9351713461954085,
+    "train_runtime": 10046.3917,
+    "train_samples": 31230,
+    "train_samples_per_second": 31.086,
+    "train_steps_per_second": 0.971
+}

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": 9760,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.23359630724948005,
+      "eval_loss": 4.781733989715576,
+      "eval_runtime": 7.3547,
+      "eval_samples_per_second": 30.321,
+      "eval_steps_per_second": 0.952,
+      "step": 976
+    },
+    {
+      "epoch": 1.0245901639344261,
+      "grad_norm": 13917.33203125,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.2461,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2654778724561881,
+      "eval_loss": 4.399641990661621,
+      "eval_runtime": 6.6539,
+      "eval_samples_per_second": 33.514,
+      "eval_steps_per_second": 1.052,
+      "step": 1952
+    },
+    {
+      "epoch": 2.0491803278688523,
+      "grad_norm": 10209.078125,
+      "learning_rate": 0.0005315753424657533,
+      "loss": 1.0362,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.28501224188919994,
+      "eval_loss": 4.204015254974365,
+      "eval_runtime": 6.7337,
+      "eval_samples_per_second": 33.117,
+      "eval_steps_per_second": 1.04,
+      "step": 2928
+    },
+    {
+      "epoch": 3.0737704918032787,
+      "grad_norm": 9973.97265625,
+      "learning_rate": 0.0004630821917808219,
+      "loss": 0.9715,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.29392819846778934,
+      "eval_loss": 4.097615718841553,
+      "eval_runtime": 6.7811,
+      "eval_samples_per_second": 32.886,
+      "eval_steps_per_second": 1.032,
+      "step": 3904
+    },
+    {
+      "epoch": 4.098360655737705,
+      "grad_norm": 10912.2734375,
+      "learning_rate": 0.00039458904109589035,
+      "loss": 0.9346,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3033619123673795,
+      "eval_loss": 4.011116027832031,
+      "eval_runtime": 6.6583,
+      "eval_samples_per_second": 33.492,
+      "eval_steps_per_second": 1.051,
+      "step": 4880
+    },
+    {
+      "epoch": 5.122950819672131,
+      "grad_norm": 9932.109375,
+      "learning_rate": 0.0003260958904109589,
+      "loss": 0.9069,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3087500987249129,
+      "eval_loss": 3.9493002891540527,
+      "eval_runtime": 6.7082,
+      "eval_samples_per_second": 33.243,
+      "eval_steps_per_second": 1.043,
+      "step": 5856
+    },
+    {
+      "epoch": 6.147540983606557,
+      "grad_norm": 9450.361328125,
+      "learning_rate": 0.00025760273972602734,
+      "loss": 0.8835,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3171044202434337,
+      "eval_loss": 3.8856163024902344,
+      "eval_runtime": 6.6331,
+      "eval_samples_per_second": 33.619,
+      "eval_steps_per_second": 1.055,
+      "step": 6832
+    },
+    {
+      "epoch": 7.172131147540983,
+      "grad_norm": 9493.173828125,
+      "learning_rate": 0.00018910958904109587,
+      "loss": 0.8622,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.32337893693013786,
+      "eval_loss": 3.8232619762420654,
+      "eval_runtime": 6.7593,
+      "eval_samples_per_second": 32.991,
+      "eval_steps_per_second": 1.036,
+      "step": 7808
+    },
+    {
+      "epoch": 8.19672131147541,
+      "grad_norm": 9608.576171875,
+      "learning_rate": 0.00012061643835616437,
+      "loss": 0.8415,
+      "step": 8000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.329653453616842,
+      "eval_loss": 3.7797963619232178,
+      "eval_runtime": 6.6962,
+      "eval_samples_per_second": 33.303,
+      "eval_steps_per_second": 1.045,
+      "step": 8784
+    },
+    {
+      "epoch": 9.221311475409836,
+      "grad_norm": 9442.396484375,
+      "learning_rate": 5.212328767123287e-05,
+      "loss": 0.8265,
+      "step": 9000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.3321018314568287,
+      "eval_loss": 3.758513927459717,
+      "eval_runtime": 6.7113,
+      "eval_samples_per_second": 33.228,
+      "eval_steps_per_second": 1.043,
+      "step": 9760
+    },
+    {
+      "epoch": 10.0,
+      "step": 9760,
+      "total_flos": 8.16015015936e+16,
+      "train_loss": 0.9351713461954085,
+      "train_runtime": 10046.3917,
+      "train_samples_per_second": 31.086,
+      "train_steps_per_second": 0.971
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 9760,
+  "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": 8.16015015936e+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 sha256:2da189a37f59b472fe26bfe5005e8ad24e3939ba7e27681a6b1776e93e7da3f6
+size 5304