Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: AR_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. -->
+
+# AR_20000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.0999
+- Accuracy: 0.2370
+
+## 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   | 851  | 6.3643          | 0.1492   |
+| 1.5936        | 2.0   | 1702 | 6.0323          | 0.1620   |
+| 1.4068        | 3.0   | 2553 | 5.7425          | 0.1821   |
+| 1.3224        | 4.0   | 3404 | 5.5530          | 0.1944   |
+| 1.2597        | 5.0   | 4255 | 5.4375          | 0.2044   |
+| 1.2168        | 6.0   | 5106 | 5.3256          | 0.2138   |
+| 1.2168        | 7.0   | 5957 | 5.2476          | 0.2211   |
+| 1.1808        | 8.0   | 6808 | 5.1822          | 0.2280   |
+| 1.1503        | 9.0   | 7659 | 5.1285          | 0.2331   |
+| 1.1255        | 10.0  | 8510 | 5.0999          | 0.2370   |
+
+
+### 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": 0.23701765577191294,
+    "eval_loss": 5.099877834320068,
+    "eval_runtime": 3.4893,
+    "eval_samples": 181,
+    "eval_samples_per_second": 51.872,
+    "eval_steps_per_second": 1.72,
+    "perplexity": 164.00187067599157,
+    "total_flos": 7.112107819008e+16,
+    "train_loss": 1.2718536484535656,
+    "train_runtime": 8434.8319,
+    "train_samples": 27219,
+    "train_samples_per_second": 32.27,
+    "train_steps_per_second": 1.009
+}

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": 0.23701765577191294,
+    "eval_loss": 5.099877834320068,
+    "eval_runtime": 3.4893,
+    "eval_samples": 181,
+    "eval_samples_per_second": 51.872,
+    "eval_steps_per_second": 1.72,
+    "perplexity": 164.00187067599157
+}

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 sha256:48c2b77161582fd4f788751831c671567b4133ae955622a330b2084b25acab50
+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": 7.112107819008e+16,
+    "train_loss": 1.2718536484535656,
+    "train_runtime": 8434.8319,
+    "train_samples": 27219,
+    "train_samples_per_second": 32.27,
+    "train_steps_per_second": 1.009
+}

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": 8510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1492145181693354,
+      "eval_loss": 6.3642778396606445,
+      "eval_runtime": 4.1353,
+      "eval_samples_per_second": 43.77,
+      "eval_steps_per_second": 1.451,
+      "step": 851
+    },
+    {
+      "epoch": 1.1750881316098707,
+      "grad_norm": 10913.1396484375,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.5936,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.16200495183315133,
+      "eval_loss": 6.032303333282471,
+      "eval_runtime": 3.7669,
+      "eval_samples_per_second": 48.05,
+      "eval_steps_per_second": 1.593,
+      "step": 1702
+    },
+    {
+      "epoch": 2.3501762632197414,
+      "grad_norm": 9681.1015625,
+      "learning_rate": 0.0005201864181091877,
+      "loss": 1.4068,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.18210420473343353,
+      "eval_loss": 5.742514610290527,
+      "eval_runtime": 3.6239,
+      "eval_samples_per_second": 49.946,
+      "eval_steps_per_second": 1.656,
+      "step": 2553
+    },
+    {
+      "epoch": 3.525264394829612,
+      "grad_norm": 10410.8232421875,
+      "learning_rate": 0.0004402929427430093,
+      "loss": 1.3224,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.19439729270956094,
+      "eval_loss": 5.552978038787842,
+      "eval_runtime": 3.6717,
+      "eval_samples_per_second": 49.296,
+      "eval_steps_per_second": 1.634,
+      "step": 3404
+    },
+    {
+      "epoch": 4.700352526439483,
+      "grad_norm": 10486.552734375,
+      "learning_rate": 0.0003603994673768309,
+      "loss": 1.2597,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.20436583018888324,
+      "eval_loss": 5.43747091293335,
+      "eval_runtime": 3.6239,
+      "eval_samples_per_second": 49.946,
+      "eval_steps_per_second": 1.656,
+      "step": 4255
+    },
+    {
+      "epoch": 5.875440658049354,
+      "grad_norm": 10774.3271484375,
+      "learning_rate": 0.00028050599201065245,
+      "loss": 1.2168,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.2138262101177412,
+      "eval_loss": 5.3256096839904785,
+      "eval_runtime": 3.6215,
+      "eval_samples_per_second": 49.979,
+      "eval_steps_per_second": 1.657,
+      "step": 5106
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.2211242174914316,
+      "eval_loss": 5.247638702392578,
+      "eval_runtime": 3.6307,
+      "eval_samples_per_second": 49.852,
+      "eval_steps_per_second": 1.653,
+      "step": 5957
+    },
+    {
+      "epoch": 7.050528789659224,
+      "grad_norm": 11328.8466796875,
+      "learning_rate": 0.00020061251664447402,
+      "loss": 1.1808,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.2280438096679677,
+      "eval_loss": 5.182240962982178,
+      "eval_runtime": 3.6289,
+      "eval_samples_per_second": 49.878,
+      "eval_steps_per_second": 1.653,
+      "step": 6808
+    },
+    {
+      "epoch": 8.225616921269095,
+      "grad_norm": 11665.4501953125,
+      "learning_rate": 0.0001207190412782956,
+      "loss": 1.1503,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.23310376144705972,
+      "eval_loss": 5.128500461578369,
+      "eval_runtime": 3.6237,
+      "eval_samples_per_second": 49.949,
+      "eval_steps_per_second": 1.656,
+      "step": 7659
+    },
+    {
+      "epoch": 9.400705052878966,
+      "grad_norm": 12125.7978515625,
+      "learning_rate": 4.082556591211717e-05,
+      "loss": 1.1255,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.23701765577191294,
+      "eval_loss": 5.099877834320068,
+      "eval_runtime": 3.6231,
+      "eval_samples_per_second": 49.957,
+      "eval_steps_per_second": 1.656,
+      "step": 8510
+    },
+    {
+      "epoch": 10.0,
+      "step": 8510,
+      "total_flos": 7.112107819008e+16,
+      "train_loss": 1.2718536484535656,
+      "train_runtime": 8434.8319,
+      "train_samples_per_second": 32.27,
+      "train_steps_per_second": 1.009
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8510,
+  "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": 7.112107819008e+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 sha256:5dd7702a34df6373f2c4aca3b7abce3a1e59874d533970e72f715b7ee6c04364
+size 5304