Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: NL_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. -->
+
+# NL_50000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.1997
+- Accuracy: 0.2997
+
+## 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   | 848  | 5.4854          | 0.1911   |
+| 1.3692        | 2.0   | 1696 | 4.9672          | 0.2266   |
+| 1.1717        | 3.0   | 2544 | 4.7297          | 0.2465   |
+| 1.0915        | 4.0   | 3392 | 4.5808          | 0.2606   |
+| 1.0455        | 5.0   | 4240 | 4.4883          | 0.2690   |
+| 1.0097        | 6.0   | 5088 | 4.3928          | 0.2784   |
+| 1.0097        | 7.0   | 5936 | 4.3270          | 0.2845   |
+| 0.9791        | 8.0   | 6784 | 4.2612          | 0.2923   |
+| 0.9538        | 9.0   | 7632 | 4.2181          | 0.2984   |
+| 0.9328        | 10.0  | 8480 | 4.1997          | 0.2997   |
+
+
+### 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": 0.29974068040064394,
+    "eval_loss": 4.199666976928711,
+    "eval_runtime": 5.3142,
+    "eval_samples": 203,
+    "eval_samples_per_second": 38.199,
+    "eval_steps_per_second": 1.317,
+    "perplexity": 66.66412665164107,
+    "total_flos": 7.084149571584e+16,
+    "train_loss": 1.060806609099766,
+    "train_runtime": 9600.4507,
+    "train_samples": 27112,
+    "train_samples_per_second": 28.24,
+    "train_steps_per_second": 0.883
+}

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": 0.29974068040064394,
+    "eval_loss": 4.199666976928711,
+    "eval_runtime": 5.3142,
+    "eval_samples": 203,
+    "eval_samples_per_second": 38.199,
+    "eval_steps_per_second": 1.317,
+    "perplexity": 66.66412665164107
+}

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 sha256:149e16527a46367173cd7d06598ab3d7ff875a3ecb61c5670703aa01aae1ecc1
+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": 7.084149571584e+16,
+    "train_loss": 1.060806609099766,
+    "train_runtime": 9600.4507,
+    "train_samples": 27112,
+    "train_samples_per_second": 28.24,
+    "train_steps_per_second": 0.883
+}

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": 8480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.19114457308667443,
+      "eval_loss": 5.485433578491211,
+      "eval_runtime": 6.2048,
+      "eval_samples_per_second": 32.717,
+      "eval_steps_per_second": 1.128,
+      "step": 848
+    },
+    {
+      "epoch": 1.179245283018868,
+      "grad_norm": 10153.7734375,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.3692,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.22659134508786982,
+      "eval_loss": 4.967179775238037,
+      "eval_runtime": 5.2959,
+      "eval_samples_per_second": 38.332,
+      "eval_steps_per_second": 1.322,
+      "step": 1696
+    },
+    {
+      "epoch": 2.358490566037736,
+      "grad_norm": 9826.4130859375,
+      "learning_rate": 0.0005198663101604277,
+      "loss": 1.1717,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.24649822139531297,
+      "eval_loss": 4.729686737060547,
+      "eval_runtime": 5.4538,
+      "eval_samples_per_second": 37.222,
+      "eval_steps_per_second": 1.284,
+      "step": 2544
+    },
+    {
+      "epoch": 3.5377358490566038,
+      "grad_norm": 9650.4951171875,
+      "learning_rate": 0.00043965240641711227,
+      "loss": 1.0915,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.26064993782113693,
+      "eval_loss": 4.58077335357666,
+      "eval_runtime": 5.3661,
+      "eval_samples_per_second": 37.83,
+      "eval_steps_per_second": 1.304,
+      "step": 3392
+    },
+    {
+      "epoch": 4.716981132075472,
+      "grad_norm": 9259.5615234375,
+      "learning_rate": 0.0003594385026737968,
+      "loss": 1.0455,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.26902721409773167,
+      "eval_loss": 4.488346099853516,
+      "eval_runtime": 5.4522,
+      "eval_samples_per_second": 37.233,
+      "eval_steps_per_second": 1.284,
+      "step": 4240
+    },
+    {
+      "epoch": 5.89622641509434,
+      "grad_norm": 9346.7109375,
+      "learning_rate": 0.0002792245989304813,
+      "loss": 1.0097,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.2784456248252726,
+      "eval_loss": 4.392796993255615,
+      "eval_runtime": 5.4575,
+      "eval_samples_per_second": 37.197,
+      "eval_steps_per_second": 1.283,
+      "step": 5088
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.28446106831962825,
+      "eval_loss": 4.326977252960205,
+      "eval_runtime": 5.3698,
+      "eval_samples_per_second": 37.804,
+      "eval_steps_per_second": 1.304,
+      "step": 5936
+    },
+    {
+      "epoch": 7.0754716981132075,
+      "grad_norm": 9462.390625,
+      "learning_rate": 0.00019901069518716573,
+      "loss": 0.9791,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.29227921683552965,
+      "eval_loss": 4.261207103729248,
+      "eval_runtime": 5.3532,
+      "eval_samples_per_second": 37.921,
+      "eval_steps_per_second": 1.308,
+      "step": 6784
+    },
+    {
+      "epoch": 8.254716981132075,
+      "grad_norm": 9632.466796875,
+      "learning_rate": 0.00011879679144385025,
+      "loss": 0.9538,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.29841034193554605,
+      "eval_loss": 4.2181220054626465,
+      "eval_runtime": 5.3385,
+      "eval_samples_per_second": 38.026,
+      "eval_steps_per_second": 1.311,
+      "step": 7632
+    },
+    {
+      "epoch": 9.433962264150944,
+      "grad_norm": 9782.0498046875,
+      "learning_rate": 3.8582887700534754e-05,
+      "loss": 0.9328,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.29974068040064394,
+      "eval_loss": 4.199666976928711,
+      "eval_runtime": 5.4632,
+      "eval_samples_per_second": 37.158,
+      "eval_steps_per_second": 1.281,
+      "step": 8480
+    },
+    {
+      "epoch": 10.0,
+      "step": 8480,
+      "total_flos": 7.084149571584e+16,
+      "train_loss": 1.060806609099766,
+      "train_runtime": 9600.4507,
+      "train_samples_per_second": 28.24,
+      "train_steps_per_second": 0.883
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8480,
+  "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": 7.084149571584e+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:df4b7bf3dcefce6c8b84fdcf75426c2d80187ce67d1edb9ae79bde67148379fc
+size 5304