Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: DE_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. -->
+
+# DE_20000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.2294
+- Accuracy: 0.2857
+
+## 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   | 913  | 5.5561          | 0.1731   |
+| 1.3899        | 2.0   | 1826 | 5.0780          | 0.2045   |
+| 1.2094        | 3.0   | 2739 | 4.8542          | 0.2239   |
+| 1.1228        | 4.0   | 3652 | 4.7063          | 0.2345   |
+| 1.0785        | 5.0   | 4565 | 4.5756          | 0.2468   |
+| 1.0404        | 6.0   | 5478 | 4.4678          | 0.2570   |
+| 1.0075        | 7.0   | 6391 | 4.3799          | 0.2667   |
+| 0.9795        | 8.0   | 7304 | 4.3070          | 0.2754   |
+| 0.9548        | 9.0   | 8217 | 4.2560          | 0.2826   |
+| 0.9379        | 10.0  | 9130 | 4.2294          | 0.2857   |
+
+
+### 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": 0.2856770105302395,
+    "eval_loss": 4.229422569274902,
+    "eval_runtime": 4.0213,
+    "eval_samples": 210,
+    "eval_samples_per_second": 52.222,
+    "eval_steps_per_second": 1.741,
+    "perplexity": 68.67756418650515,
+    "total_flos": 7.626330537984e+16,
+    "train_loss": 1.0780007603656814,
+    "train_runtime": 8944.428,
+    "train_samples": 29187,
+    "train_samples_per_second": 32.631,
+    "train_steps_per_second": 1.021
+}

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": 0.2856770105302395,
+    "eval_loss": 4.229422569274902,
+    "eval_runtime": 4.0213,
+    "eval_samples": 210,
+    "eval_samples_per_second": 52.222,
+    "eval_steps_per_second": 1.741,
+    "perplexity": 68.67756418650515
+}

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 sha256:4e41868ad917d79050548de5ca45d889b1955c00cbbb9b1cfe206fd7bf0a4f24
+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": 7.626330537984e+16,
+    "train_loss": 1.0780007603656814,
+    "train_runtime": 8944.428,
+    "train_samples": 29187,
+    "train_samples_per_second": 32.631,
+    "train_steps_per_second": 1.021
+}

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": 9130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.17310595471065138,
+      "eval_loss": 5.5561370849609375,
+      "eval_runtime": 4.6624,
+      "eval_samples_per_second": 45.041,
+      "eval_steps_per_second": 1.501,
+      "step": 913
+    },
+    {
+      "epoch": 1.095290251916758,
+      "grad_norm": 11655.0771484375,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.3899,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.20447302208554655,
+      "eval_loss": 5.078013896942139,
+      "eval_runtime": 4.1906,
+      "eval_samples_per_second": 50.112,
+      "eval_steps_per_second": 1.67,
+      "step": 1826
+    },
+    {
+      "epoch": 2.190580503833516,
+      "grad_norm": 12689.8798828125,
+      "learning_rate": 0.0005262730627306273,
+      "loss": 1.2094,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.22389339297362781,
+      "eval_loss": 4.854242324829102,
+      "eval_runtime": 4.1924,
+      "eval_samples_per_second": 50.09,
+      "eval_steps_per_second": 1.67,
+      "step": 2739
+    },
+    {
+      "epoch": 3.285870755750274,
+      "grad_norm": 11689.5693359375,
+      "learning_rate": 0.0004524723247232472,
+      "loss": 1.1228,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.23449818283477775,
+      "eval_loss": 4.706299781799316,
+      "eval_runtime": 4.1947,
+      "eval_samples_per_second": 50.063,
+      "eval_steps_per_second": 1.669,
+      "step": 3652
+    },
+    {
+      "epoch": 4.381161007667032,
+      "grad_norm": 10716.5498046875,
+      "learning_rate": 0.0003786715867158671,
+      "loss": 1.0785,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.24677103718199608,
+      "eval_loss": 4.575649738311768,
+      "eval_runtime": 4.1893,
+      "eval_samples_per_second": 50.128,
+      "eval_steps_per_second": 1.671,
+      "step": 4565
+    },
+    {
+      "epoch": 5.47645125958379,
+      "grad_norm": 9507.984375,
+      "learning_rate": 0.00030487084870848706,
+      "loss": 1.0404,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.25699375640667227,
+      "eval_loss": 4.467764854431152,
+      "eval_runtime": 4.1954,
+      "eval_samples_per_second": 50.055,
+      "eval_steps_per_second": 1.668,
+      "step": 5478
+    },
+    {
+      "epoch": 6.571741511500548,
+      "grad_norm": 9934.1025390625,
+      "learning_rate": 0.000231070110701107,
+      "loss": 1.0075,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.26667598546267823,
+      "eval_loss": 4.3798675537109375,
+      "eval_runtime": 4.1936,
+      "eval_samples_per_second": 50.076,
+      "eval_steps_per_second": 1.669,
+      "step": 6391
+    },
+    {
+      "epoch": 7.667031763417306,
+      "grad_norm": 9912.5068359375,
+      "learning_rate": 0.00015726937269372693,
+      "loss": 0.9795,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.27538905973348243,
+      "eval_loss": 4.306954383850098,
+      "eval_runtime": 4.1817,
+      "eval_samples_per_second": 50.218,
+      "eval_steps_per_second": 1.674,
+      "step": 7304
+    },
+    {
+      "epoch": 8.762322015334064,
+      "grad_norm": 10251.361328125,
+      "learning_rate": 8.346863468634686e-05,
+      "loss": 0.9548,
+      "step": 8000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.2825924890504147,
+      "eval_loss": 4.256042957305908,
+      "eval_runtime": 4.1902,
+      "eval_samples_per_second": 50.117,
+      "eval_steps_per_second": 1.671,
+      "step": 8217
+    },
+    {
+      "epoch": 9.857612267250822,
+      "grad_norm": 10095.9697265625,
+      "learning_rate": 9.66789667896679e-06,
+      "loss": 0.9379,
+      "step": 9000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.2856770105302395,
+      "eval_loss": 4.229422569274902,
+      "eval_runtime": 4.1938,
+      "eval_samples_per_second": 50.074,
+      "eval_steps_per_second": 1.669,
+      "step": 9130
+    },
+    {
+      "epoch": 10.0,
+      "step": 9130,
+      "total_flos": 7.626330537984e+16,
+      "train_loss": 1.0780007603656814,
+      "train_runtime": 8944.428,
+      "train_samples_per_second": 32.631,
+      "train_steps_per_second": 1.021
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 9130,
+  "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": 7.626330537984e+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 sha256:5b7925c57147833ba587cd420e590ecc3143d3df770c959dc24933ce5aeee63c
+size 5304