Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: EN_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. -->
+
+# EN_30000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.2839
+- Accuracy: 0.2821
+
+## 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   | 891  | 5.1377          | 0.2004   |
+| 1.2877        | 2.0   | 1782 | 4.8901          | 0.2236   |
+| 1.1355        | 3.0   | 2673 | 4.7772          | 0.2356   |
+| 1.0964        | 4.0   | 3564 | 4.7023          | 0.2399   |
+| 1.0755        | 5.0   | 4455 | 4.6125          | 0.2460   |
+| 1.0502        | 6.0   | 5346 | 4.5341          | 0.2551   |
+| 1.0248        | 7.0   | 6237 | 4.4484          | 0.2643   |
+| 1.0035        | 8.0   | 7128 | 4.3691          | 0.2732   |
+| 0.9814        | 9.0   | 8019 | 4.3135          | 0.2788   |
+| 0.9814        | 10.0  | 8910 | 4.2839          | 0.2821   |
+
+
+### 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": 0.28208133924938483,
+    "eval_loss": 4.283874988555908,
+    "eval_runtime": 4.2634,
+    "eval_samples": 202,
+    "eval_samples_per_second": 47.38,
+    "eval_steps_per_second": 1.642,
+    "perplexity": 72.52091395133368,
+    "total_flos": 7.44290353152e+16,
+    "train_loss": 1.0702610208530619,
+    "train_runtime": 9181.6961,
+    "train_samples": 28485,
+    "train_samples_per_second": 31.024,
+    "train_steps_per_second": 0.97
+}

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": 0.28208133924938483,
+    "eval_loss": 4.283874988555908,
+    "eval_runtime": 4.2634,
+    "eval_samples": 202,
+    "eval_samples_per_second": 47.38,
+    "eval_steps_per_second": 1.642,
+    "perplexity": 72.52091395133368
+}

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:d72011799d6303b611461db70c6ea1bfc12ce207700832f5dda66b4b676d20f7
+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": 7.44290353152e+16,
+    "train_loss": 1.0702610208530619,
+    "train_runtime": 9181.6961,
+    "train_samples": 28485,
+    "train_samples_per_second": 31.024,
+    "train_steps_per_second": 0.97
+}

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": 8910,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.20035457557497433,
+      "eval_loss": 5.137700080871582,
+      "eval_runtime": 4.7614,
+      "eval_samples_per_second": 42.424,
+      "eval_steps_per_second": 1.47,
+      "step": 891
+    },
+    {
+      "epoch": 1.122334455667789,
+      "grad_norm": 12257.177734375,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.2877,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.22360543295034005,
+      "eval_loss": 4.890064239501953,
+      "eval_runtime": 4.3477,
+      "eval_samples_per_second": 46.461,
+      "eval_steps_per_second": 1.61,
+      "step": 1782
+    },
+    {
+      "epoch": 2.244668911335578,
+      "grad_norm": 16755.361328125,
+      "learning_rate": 0.0005242225031605562,
+      "loss": 1.1355,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2355505609269342,
+      "eval_loss": 4.7771735191345215,
+      "eval_runtime": 4.3663,
+      "eval_samples_per_second": 46.264,
+      "eval_steps_per_second": 1.603,
+      "step": 2673
+    },
+    {
+      "epoch": 3.3670033670033668,
+      "grad_norm": 27167.396484375,
+      "learning_rate": 0.0004483691529709229,
+      "loss": 1.0964,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.2399488481137742,
+      "eval_loss": 4.702260971069336,
+      "eval_runtime": 4.4874,
+      "eval_samples_per_second": 45.014,
+      "eval_steps_per_second": 1.56,
+      "step": 3564
+    },
+    {
+      "epoch": 4.489337822671156,
+      "grad_norm": 20150.478515625,
+      "learning_rate": 0.00037251580278128944,
+      "loss": 1.0755,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.2460231346030885,
+      "eval_loss": 4.61249303817749,
+      "eval_runtime": 4.3579,
+      "eval_samples_per_second": 46.353,
+      "eval_steps_per_second": 1.606,
+      "step": 4455
+    },
+    {
+      "epoch": 5.611672278338945,
+      "grad_norm": 24080.505859375,
+      "learning_rate": 0.0002966624525916561,
+      "loss": 1.0502,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.2551200325512003,
+      "eval_loss": 4.534069538116455,
+      "eval_runtime": 4.3651,
+      "eval_samples_per_second": 46.276,
+      "eval_steps_per_second": 1.604,
+      "step": 5346
+    },
+    {
+      "epoch": 6.7340067340067336,
+      "grad_norm": 19178.21484375,
+      "learning_rate": 0.00022080910240202274,
+      "loss": 1.0248,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.2642556819282711,
+      "eval_loss": 4.448388576507568,
+      "eval_runtime": 4.4493,
+      "eval_samples_per_second": 45.401,
+      "eval_steps_per_second": 1.573,
+      "step": 6237
+    },
+    {
+      "epoch": 7.856341189674523,
+      "grad_norm": 13593.7294921875,
+      "learning_rate": 0.00014495575221238938,
+      "loss": 1.0035,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.2731878863033074,
+      "eval_loss": 4.369141578674316,
+      "eval_runtime": 4.3376,
+      "eval_samples_per_second": 46.569,
+      "eval_steps_per_second": 1.614,
+      "step": 7128
+    },
+    {
+      "epoch": 8.978675645342312,
+      "grad_norm": 12907.32421875,
+      "learning_rate": 6.9102402022756e-05,
+      "loss": 0.9814,
+      "step": 8000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.27882621921683365,
+      "eval_loss": 4.313453197479248,
+      "eval_runtime": 4.3378,
+      "eval_samples_per_second": 46.567,
+      "eval_steps_per_second": 1.614,
+      "step": 8019
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.28208133924938483,
+      "eval_loss": 4.283874988555908,
+      "eval_runtime": 4.4601,
+      "eval_samples_per_second": 45.29,
+      "eval_steps_per_second": 1.569,
+      "step": 8910
+    },
+    {
+      "epoch": 10.0,
+      "step": 8910,
+      "total_flos": 7.44290353152e+16,
+      "train_loss": 1.0702610208530619,
+      "train_runtime": 9181.6961,
+      "train_samples_per_second": 31.024,
+      "train_steps_per_second": 0.97
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8910,
+  "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": 7.44290353152e+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 sha256:37fc240412e1778ac7688802426838e21972b7375a0f2e2e863972c28e38b5a1
+size 5304