Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: EN_50000_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. -->
+
+# EN_50000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3035
+- Accuracy: 0.2843
+
+## 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   | 879  | 5.1363          | 0.2075   |
+| 1.2933        | 2.0   | 1758 | 4.8442          | 0.2329   |
+| 1.1247        | 3.0   | 2637 | 4.7518          | 0.2381   |
+| 1.0823        | 4.0   | 3516 | 4.7017          | 0.2449   |
+| 1.0676        | 5.0   | 4395 | 4.6547          | 0.2471   |
+| 1.0504        | 6.0   | 5274 | 4.5688          | 0.2568   |
+| 1.0252        | 7.0   | 6153 | 4.4703          | 0.2681   |
+| 0.9998        | 8.0   | 7032 | 4.3841          | 0.2754   |
+| 0.9998        | 9.0   | 7911 | 4.3409          | 0.2797   |
+| 0.9762        | 10.0  | 8790 | 4.3035          | 0.2843   |
+
+
+### 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": 0.2842540256489217,
+    "eval_loss": 4.3034586906433105,
+    "eval_runtime": 5.0383,
+    "eval_samples": 197,
+    "eval_samples_per_second": 39.101,
+    "eval_steps_per_second": 1.389,
+    "perplexity": 73.95513981353707,
+    "total_flos": 7.34753193984e+16,
+    "train_loss": 1.0670098383950157,
+    "train_runtime": 10225.3656,
+    "train_samples": 28120,
+    "train_samples_per_second": 27.5,
+    "train_steps_per_second": 0.86
+}

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": 50000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.2842540256489217,
+    "eval_loss": 4.3034586906433105,
+    "eval_runtime": 5.0383,
+    "eval_samples": 197,
+    "eval_samples_per_second": 39.101,
+    "eval_steps_per_second": 1.389,
+    "perplexity": 73.95513981353707
+}

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:ec93f941f5e5cbbafacdfd572f2eae2d7ff4ed5b8840b5ac889ac5c6cb5329d9
+size 495411840

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": 7.34753193984e+16,
+    "train_loss": 1.0670098383950157,
+    "train_runtime": 10225.3656,
+    "train_samples": 28120,
+    "train_samples_per_second": 27.5,
+    "train_steps_per_second": 0.86
+}

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": 8790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2074662004430449,
+      "eval_loss": 5.136288642883301,
+      "eval_runtime": 6.2541,
+      "eval_samples_per_second": 31.499,
+      "eval_steps_per_second": 1.119,
+      "step": 879
+    },
+    {
+      "epoch": 1.1376564277588168,
+      "grad_norm": 12871.9697265625,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.2933,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.23289657981264963,
+      "eval_loss": 4.844233989715576,
+      "eval_runtime": 5.189,
+      "eval_samples_per_second": 37.965,
+      "eval_steps_per_second": 1.349,
+      "step": 1758
+    },
+    {
+      "epoch": 2.2753128555176336,
+      "grad_norm": 17373.572265625,
+      "learning_rate": 0.0005230551989730423,
+      "loss": 1.1247,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.23807205936404185,
+      "eval_loss": 4.751773834228516,
+      "eval_runtime": 5.1988,
+      "eval_samples_per_second": 37.893,
+      "eval_steps_per_second": 1.346,
+      "step": 2637
+    },
+    {
+      "epoch": 3.4129692832764507,
+      "grad_norm": 20363.787109375,
+      "learning_rate": 0.0004460333761232349,
+      "loss": 1.0823,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.2448866063357406,
+      "eval_loss": 4.701653957366943,
+      "eval_runtime": 5.2667,
+      "eval_samples_per_second": 37.405,
+      "eval_steps_per_second": 1.329,
+      "step": 3516
+    },
+    {
+      "epoch": 4.550625711035267,
+      "grad_norm": 25301.0234375,
+      "learning_rate": 0.00036901155327342743,
+      "loss": 1.0676,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.24713163201446353,
+      "eval_loss": 4.654669284820557,
+      "eval_runtime": 5.195,
+      "eval_samples_per_second": 37.921,
+      "eval_steps_per_second": 1.347,
+      "step": 4395
+    },
+    {
+      "epoch": 5.688282138794084,
+      "grad_norm": 24580.740234375,
+      "learning_rate": 0.00029198973042362,
+      "loss": 1.0504,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.25679716292330157,
+      "eval_loss": 4.568830966949463,
+      "eval_runtime": 5.1829,
+      "eval_samples_per_second": 38.009,
+      "eval_steps_per_second": 1.351,
+      "step": 5274
+    },
+    {
+      "epoch": 6.825938566552901,
+      "grad_norm": 18673.5703125,
+      "learning_rate": 0.00021496790757381256,
+      "loss": 1.0252,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.2680719600266224,
+      "eval_loss": 4.470284461975098,
+      "eval_runtime": 5.1877,
+      "eval_samples_per_second": 37.974,
+      "eval_steps_per_second": 1.349,
+      "step": 6153
+    },
+    {
+      "epoch": 7.963594994311718,
+      "grad_norm": 14578.203125,
+      "learning_rate": 0.0001379460847240051,
+      "loss": 0.9998,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.27541299532120755,
+      "eval_loss": 4.384091377258301,
+      "eval_runtime": 5.2699,
+      "eval_samples_per_second": 37.382,
+      "eval_steps_per_second": 1.328,
+      "step": 7032
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.2796547031301221,
+      "eval_loss": 4.340909957885742,
+      "eval_runtime": 5.1886,
+      "eval_samples_per_second": 37.968,
+      "eval_steps_per_second": 1.349,
+      "step": 7911
+    },
+    {
+      "epoch": 9.101251422070535,
+      "grad_norm": 12082.904296875,
+      "learning_rate": 6.092426187419768e-05,
+      "loss": 0.9762,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.2842540256489217,
+      "eval_loss": 4.3034586906433105,
+      "eval_runtime": 5.2131,
+      "eval_samples_per_second": 37.789,
+      "eval_steps_per_second": 1.343,
+      "step": 8790
+    },
+    {
+      "epoch": 10.0,
+      "step": 8790,
+      "total_flos": 7.34753193984e+16,
+      "train_loss": 1.0670098383950157,
+      "train_runtime": 10225.3656,
+      "train_samples_per_second": 27.5,
+      "train_steps_per_second": 0.86
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8790,
+  "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": 7.34753193984e+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 sha256:72197e232889bc5e7245be8ae9f26420c9bce170d7f588a44f3a2c446202ba1b
+size 5304