Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: TR_13222_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. -->
+
+# TR_13222_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.4819
+- Accuracy: 0.2913
+
+## 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   | 839  | 5.7348          | 0.1989   |
+| 1.4608        | 2.0   | 1678 | 5.4191          | 0.2107   |
+| 1.2692        | 3.0   | 2517 | 5.1890          | 0.2246   |
+| 1.198         | 4.0   | 3356 | 4.9807          | 0.2392   |
+| 1.14          | 5.0   | 4195 | 4.8342          | 0.2530   |
+| 1.0965        | 6.0   | 5034 | 4.7234          | 0.2629   |
+| 1.0965        | 7.0   | 5873 | 4.6437          | 0.2730   |
+| 1.0589        | 8.0   | 6712 | 4.5623          | 0.2803   |
+| 1.0308        | 9.0   | 7551 | 4.5085          | 0.2873   |
+| 1.0071        | 10.0  | 8390 | 4.4819          | 0.2913   |
+
+
+### 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": 0.29131827077032557,
+    "eval_loss": 4.481873512268066,
+    "eval_runtime": 3.4675,
+    "eval_samples": 198,
+    "eval_samples_per_second": 57.101,
+    "eval_steps_per_second": 2.019,
+    "perplexity": 88.4001363681082,
+    "total_flos": 7.01438459904e+16,
+    "train_loss": 1.150104701845808,
+    "train_runtime": 7913.1947,
+    "train_samples": 26845,
+    "train_samples_per_second": 33.924,
+    "train_steps_per_second": 1.06
+}

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": 13222
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.29131827077032557,
+    "eval_loss": 4.481873512268066,
+    "eval_runtime": 3.4675,
+    "eval_samples": 198,
+    "eval_samples_per_second": 57.101,
+    "eval_steps_per_second": 2.019,
+    "perplexity": 88.4001363681082
+}

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 sha256:25473fcdbac60e78099e4d279f1a4b79afe88a448254e53decb6867169c45b1d
+size 382429824

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": 7.01438459904e+16,
+    "train_loss": 1.150104701845808,
+    "train_runtime": 7913.1947,
+    "train_samples": 26845,
+    "train_samples_per_second": 33.924,
+    "train_steps_per_second": 1.06
+}

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": 8390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.19888710984601396,
+      "eval_loss": 5.734804153442383,
+      "eval_runtime": 4.1958,
+      "eval_samples_per_second": 47.19,
+      "eval_steps_per_second": 1.668,
+      "step": 839
+    },
+    {
+      "epoch": 1.1918951132300357,
+      "grad_norm": 11337.7734375,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.4608,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.21073751210737512,
+      "eval_loss": 5.419137477874756,
+      "eval_runtime": 3.5721,
+      "eval_samples_per_second": 55.429,
+      "eval_steps_per_second": 1.96,
+      "step": 1678
+    },
+    {
+      "epoch": 2.3837902264600714,
+      "grad_norm": 9227.62890625,
+      "learning_rate": 0.0005188903924221921,
+      "loss": 1.2692,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.22459427938879994,
+      "eval_loss": 5.1890034675598145,
+      "eval_runtime": 3.5903,
+      "eval_samples_per_second": 55.149,
+      "eval_steps_per_second": 1.95,
+      "step": 2517
+    },
+    {
+      "epoch": 3.575685339690107,
+      "grad_norm": 9546.443359375,
+      "learning_rate": 0.0004376995940460081,
+      "loss": 1.198,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.23924173239241733,
+      "eval_loss": 4.980679512023926,
+      "eval_runtime": 3.584,
+      "eval_samples_per_second": 55.245,
+      "eval_steps_per_second": 1.953,
+      "step": 3356
+    },
+    {
+      "epoch": 4.767580452920143,
+      "grad_norm": 9724.2109375,
+      "learning_rate": 0.0003565087956698241,
+      "loss": 1.14,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.25296012967245846,
+      "eval_loss": 4.834165573120117,
+      "eval_runtime": 3.5941,
+      "eval_samples_per_second": 55.09,
+      "eval_steps_per_second": 1.948,
+      "step": 4195
+    },
+    {
+      "epoch": 5.959475566150179,
+      "grad_norm": 10006.009765625,
+      "learning_rate": 0.00027531799729364,
+      "loss": 1.0965,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.26287335191444783,
+      "eval_loss": 4.723355293273926,
+      "eval_runtime": 3.5903,
+      "eval_samples_per_second": 55.149,
+      "eval_steps_per_second": 1.95,
+      "step": 5034
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.2729842455869853,
+      "eval_loss": 4.64369535446167,
+      "eval_runtime": 3.6319,
+      "eval_samples_per_second": 54.517,
+      "eval_steps_per_second": 1.927,
+      "step": 5873
+    },
+    {
+      "epoch": 7.151370679380214,
+      "grad_norm": 10823.7548828125,
+      "learning_rate": 0.000194127198917456,
+      "loss": 1.0589,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.28027832137421177,
+      "eval_loss": 4.56227445602417,
+      "eval_runtime": 3.5958,
+      "eval_samples_per_second": 55.065,
+      "eval_steps_per_second": 1.947,
+      "step": 6712
+    },
+    {
+      "epoch": 8.34326579261025,
+      "grad_norm": 11669.6923828125,
+      "learning_rate": 0.00011293640054127199,
+      "loss": 1.0308,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.28728577358714347,
+      "eval_loss": 4.508500576019287,
+      "eval_runtime": 3.7301,
+      "eval_samples_per_second": 53.081,
+      "eval_steps_per_second": 1.877,
+      "step": 7551
+    },
+    {
+      "epoch": 9.535160905840286,
+      "grad_norm": 11752.251953125,
+      "learning_rate": 3.174560216508796e-05,
+      "loss": 1.0071,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.29131827077032557,
+      "eval_loss": 4.481873512268066,
+      "eval_runtime": 3.587,
+      "eval_samples_per_second": 55.199,
+      "eval_steps_per_second": 1.951,
+      "step": 8390
+    },
+    {
+      "epoch": 10.0,
+      "step": 8390,
+      "total_flos": 7.01438459904e+16,
+      "train_loss": 1.150104701845808,
+      "train_runtime": 7913.1947,
+      "train_samples_per_second": 33.924,
+      "train_steps_per_second": 1.06
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8390,
+  "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": 7.01438459904e+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 sha256:98d3cb5261bae920ea77d2369d981b806dfb38c5239e3c70799301febdba7fec
+size 5304