walser larger commit

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: 22_09_07_walser_blocks_larger_fp16_5ep
+  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. -->
+
+# 22_09_07_walser_blocks_larger_fp16_5ep
+
+This model is a fine-tuned version of [stefan-it/german-gpt2-larger](https://huggingface.co/stefan-it/german-gpt2-larger) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.1738
+- Accuracy: 0.2760
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 0.45  | 50   | 5.2435          | 0.1883   |
+| No log        | 0.91  | 100  | 4.6670          | 0.2259   |
+| No log        | 1.36  | 150  | 4.4367          | 0.2481   |
+| No log        | 1.82  | 200  | 4.3258          | 0.2597   |
+| 6.175         | 2.27  | 250  | 4.2705          | 0.2648   |
+| 6.175         | 2.73  | 300  | 4.2318          | 0.2697   |
+| 6.175         | 3.18  | 350  | 4.2090          | 0.2719   |
+| 6.175         | 3.64  | 400  | 4.1915          | 0.2740   |
+| 6.175         | 4.09  | 450  | 4.1823          | 0.2746   |
+| 3.9191        | 4.55  | 500  | 4.1761          | 0.2757   |
+| 3.9191        | 5.0   | 550  | 4.1738          | 0.2760   |
+
+
+### Framework versions
+
+- Transformers 4.22.0.dev0
+- Pytorch 1.11.0.post202
+- Datasets 2.3.2
+- Tokenizers 0.12.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50265
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.27604251159501675,
+    "eval_loss": 4.173768997192383,
+    "eval_runtime": 4.8911,
+    "eval_samples": 235,
+    "eval_samples_per_second": 48.047,
+    "eval_steps_per_second": 6.134,
+    "perplexity": 64.9598246952154,
+    "train_loss": 4.937346829501065,
+    "train_runtime": 481.6631,
+    "train_samples": 1755,
+    "train_samples_per_second": 18.218,
+    "train_steps_per_second": 1.142
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "stefan-it/german-gpt2-larger",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "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": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "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": "4.22.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50266
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.27604251159501675,
+    "eval_loss": 4.173768997192383,
+    "eval_runtime": 4.8911,
+    "eval_samples": 235,
+    "eval_samples_per_second": 48.047,
+    "eval_steps_per_second": 6.134,
+    "perplexity": 64.9598246952154
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8686b622d57b7c3a05f767d38c9f954533353563244d16cb011c4560d7aec41
+size 510424169

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "stefan-it/german-gpt2-larger",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 4.937346829501065,
+    "train_runtime": 481.6631,
+    "train_samples": 1755,
+    "train_samples_per_second": 18.218,
+    "train_steps_per_second": 1.142
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.1882656350741457,
+      "eval_loss": 5.243511199951172,
+      "eval_runtime": 4.8686,
+      "eval_samples_per_second": 48.268,
+      "eval_steps_per_second": 6.162,
+      "step": 50
+    },
+    {
+      "epoch": 0.91,
+      "eval_accuracy": 0.2259354006780225,
+      "eval_loss": 4.6670308113098145,
+      "eval_runtime": 4.8738,
+      "eval_samples_per_second": 48.217,
+      "eval_steps_per_second": 6.155,
+      "step": 100
+    },
+    {
+      "epoch": 1.36,
+      "eval_accuracy": 0.24813543811484787,
+      "eval_loss": 4.436723709106445,
+      "eval_runtime": 4.8864,
+      "eval_samples_per_second": 48.093,
+      "eval_steps_per_second": 6.14,
+      "step": 150
+    },
+    {
+      "epoch": 1.82,
+      "eval_accuracy": 0.25969925750296374,
+      "eval_loss": 4.3258056640625,
+      "eval_runtime": 4.8712,
+      "eval_samples_per_second": 48.243,
+      "eval_steps_per_second": 6.159,
+      "step": 200
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.772727272727273e-05,
+      "loss": 6.175,
+      "step": 250
+    },
+    {
+      "epoch": 2.27,
+      "eval_accuracy": 0.26481562363511574,
+      "eval_loss": 4.270518779754639,
+      "eval_runtime": 4.8757,
+      "eval_samples_per_second": 48.198,
+      "eval_steps_per_second": 6.153,
+      "step": 250
+    },
+    {
+      "epoch": 2.73,
+      "eval_accuracy": 0.26965745304798155,
+      "eval_loss": 4.2317938804626465,
+      "eval_runtime": 4.8861,
+      "eval_samples_per_second": 48.096,
+      "eval_steps_per_second": 6.14,
+      "step": 300
+    },
+    {
+      "epoch": 3.18,
+      "eval_accuracy": 0.2718995029221522,
+      "eval_loss": 4.208972454071045,
+      "eval_runtime": 4.8935,
+      "eval_samples_per_second": 48.023,
+      "eval_steps_per_second": 6.131,
+      "step": 350
+    },
+    {
+      "epoch": 3.64,
+      "eval_accuracy": 0.27399596514215596,
+      "eval_loss": 4.191540718078613,
+      "eval_runtime": 4.8923,
+      "eval_samples_per_second": 48.035,
+      "eval_steps_per_second": 6.132,
+      "step": 400
+    },
+    {
+      "epoch": 4.09,
+      "eval_accuracy": 0.2745658368170379,
+      "eval_loss": 4.18229866027832,
+      "eval_runtime": 4.8912,
+      "eval_samples_per_second": 48.045,
+      "eval_steps_per_second": 6.133,
+      "step": 450
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 5e-06,
+      "loss": 3.9191,
+      "step": 500
+    },
+    {
+      "epoch": 4.55,
+      "eval_accuracy": 0.2756639836941827,
+      "eval_loss": 4.17605447769165,
+      "eval_runtime": 4.8985,
+      "eval_samples_per_second": 47.974,
+      "eval_steps_per_second": 6.124,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.27604251159501675,
+      "eval_loss": 4.173768997192383,
+      "eval_runtime": 4.8913,
+      "eval_samples_per_second": 48.044,
+      "eval_steps_per_second": 6.133,
+      "step": 550
+    },
+    {
+      "epoch": 5.0,
+      "step": 550,
+      "total_flos": 4585675161600000.0,
+      "train_loss": 4.937346829501065,
+      "train_runtime": 481.6631,
+      "train_samples_per_second": 18.218,
+      "train_steps_per_second": 1.142
+    }
+  ],
+  "max_steps": 550,
+  "num_train_epochs": 5,
+  "total_flos": 4585675161600000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9e22f4560c5384ce8d2001287f6eaf024c7133e249440682c6c714eab02c83
+size 3375