Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: NL_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. -->
+
+# NL_30000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.1461
+- Accuracy: 0.2990
+
+## 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   | 867  | 5.4512          | 0.1859   |
+| 1.3675        | 2.0   | 1734 | 4.9265          | 0.2254   |
+| 1.1799        | 3.0   | 2601 | 4.7038          | 0.2432   |
+| 1.0961        | 4.0   | 3468 | 4.5697          | 0.2548   |
+| 1.0515        | 5.0   | 4335 | 4.4518          | 0.2681   |
+| 1.0172        | 6.0   | 5202 | 4.3518          | 0.2768   |
+| 0.9873        | 7.0   | 6069 | 4.2935          | 0.2831   |
+| 0.9873        | 8.0   | 6936 | 4.2205          | 0.2899   |
+| 0.9636        | 9.0   | 7803 | 4.1697          | 0.2958   |
+| 0.9396        | 10.0  | 8670 | 4.1461          | 0.2990   |
+
+
+### 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": 0.29895913100201366,
+    "eval_loss": 4.146071434020996,
+    "eval_runtime": 4.3764,
+    "eval_samples": 207,
+    "eval_samples_per_second": 47.3,
+    "eval_steps_per_second": 1.6,
+    "perplexity": 63.18528451071264,
+    "total_flos": 7.241186082816e+16,
+    "train_loss": 1.0640484907772851,
+    "train_runtime": 8887.9479,
+    "train_samples": 27713,
+    "train_samples_per_second": 31.18,
+    "train_steps_per_second": 0.975
+}

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": 0.29895913100201366,
+    "eval_loss": 4.146071434020996,
+    "eval_runtime": 4.3764,
+    "eval_samples": 207,
+    "eval_samples_per_second": 47.3,
+    "eval_steps_per_second": 1.6,
+    "perplexity": 63.18528451071264
+}

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 sha256:98d8c6503cf6332ac1724b1a3d8e165cf60589db7d3cf691f5c85623592e41fe
+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": 7.241186082816e+16,
+    "train_loss": 1.0640484907772851,
+    "train_runtime": 8887.9479,
+    "train_samples": 27713,
+    "train_samples_per_second": 31.18,
+    "train_steps_per_second": 0.975
+}

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": 8670,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1858627111753973,
+      "eval_loss": 5.451210975646973,
+      "eval_runtime": 5.0824,
+      "eval_samples_per_second": 40.729,
+      "eval_steps_per_second": 1.377,
+      "step": 867
+    },
+    {
+      "epoch": 1.1534025374855825,
+      "grad_norm": 10704.4248046875,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.3675,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2253798084649782,
+      "eval_loss": 4.926455974578857,
+      "eval_runtime": 4.5511,
+      "eval_samples_per_second": 45.484,
+      "eval_steps_per_second": 1.538,
+      "step": 1734
+    },
+    {
+      "epoch": 2.306805074971165,
+      "grad_norm": 10061.9482421875,
+      "learning_rate": 0.000521851368970013,
+      "loss": 1.1799,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.24317195609631584,
+      "eval_loss": 4.703815460205078,
+      "eval_runtime": 4.5518,
+      "eval_samples_per_second": 45.476,
+      "eval_steps_per_second": 1.538,
+      "step": 2601
+    },
+    {
+      "epoch": 3.4602076124567476,
+      "grad_norm": 9991.9482421875,
+      "learning_rate": 0.0004436245110821382,
+      "loss": 1.0961,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.2547812851565085,
+      "eval_loss": 4.569740295410156,
+      "eval_runtime": 4.5485,
+      "eval_samples_per_second": 45.51,
+      "eval_steps_per_second": 1.539,
+      "step": 3468
+    },
+    {
+      "epoch": 4.61361014994233,
+      "grad_norm": 9533.0634765625,
+      "learning_rate": 0.0003653976531942633,
+      "loss": 1.0515,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.268139576656551,
+      "eval_loss": 4.45181131362915,
+      "eval_runtime": 4.5457,
+      "eval_samples_per_second": 45.537,
+      "eval_steps_per_second": 1.54,
+      "step": 4335
+    },
+    {
+      "epoch": 5.767012687427912,
+      "grad_norm": 9257.6689453125,
+      "learning_rate": 0.0002871707953063885,
+      "loss": 1.0172,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.276780396494512,
+      "eval_loss": 4.351844787597656,
+      "eval_runtime": 4.5386,
+      "eval_samples_per_second": 45.609,
+      "eval_steps_per_second": 1.542,
+      "step": 5202
+    },
+    {
+      "epoch": 6.920415224913495,
+      "grad_norm": 9516.7802734375,
+      "learning_rate": 0.00020894393741851367,
+      "loss": 0.9873,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.2830766612779716,
+      "eval_loss": 4.293467998504639,
+      "eval_runtime": 4.5677,
+      "eval_samples_per_second": 45.318,
+      "eval_steps_per_second": 1.532,
+      "step": 6069
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.28988343401684674,
+      "eval_loss": 4.220463275909424,
+      "eval_runtime": 4.5448,
+      "eval_samples_per_second": 45.547,
+      "eval_steps_per_second": 1.54,
+      "step": 6936
+    },
+    {
+      "epoch": 8.073817762399077,
+      "grad_norm": 9788.2294921875,
+      "learning_rate": 0.00013071707953063883,
+      "loss": 0.9636,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.29579209090823144,
+      "eval_loss": 4.169673919677734,
+      "eval_runtime": 4.5415,
+      "eval_samples_per_second": 45.579,
+      "eval_steps_per_second": 1.541,
+      "step": 7803
+    },
+    {
+      "epoch": 9.22722029988466,
+      "grad_norm": 10080.197265625,
+      "learning_rate": 5.249022164276401e-05,
+      "loss": 0.9396,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.29895913100201366,
+      "eval_loss": 4.146071434020996,
+      "eval_runtime": 4.5417,
+      "eval_samples_per_second": 45.577,
+      "eval_steps_per_second": 1.541,
+      "step": 8670
+    },
+    {
+      "epoch": 10.0,
+      "step": 8670,
+      "total_flos": 7.241186082816e+16,
+      "train_loss": 1.0640484907772851,
+      "train_runtime": 8887.9479,
+      "train_samples_per_second": 31.18,
+      "train_steps_per_second": 0.975
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8670,
+  "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": 7.241186082816e+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:d4d34a5972adeb61cbe8a7b28ff95df1374cc0e06b6ce2ee9ca631915582f8da
+size 5304