ninagroot/GPT2-705Mtest

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: GPT2-705M
+  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. -->
+
+# GPT2-705M
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.5041
+
+## 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: 0.00025
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 7.6866        | 0.98  | 7    | 8.0542          |
+| 6.8762        | 1.96  | 14   | 7.3416          |
+| 6.1904        | 2.95  | 21   | 6.8861          |
+| 5.7933        | 3.93  | 28   | 6.6310          |
+| 5.3583        | 4.91  | 35   | 6.3709          |
+| 4.8424        | 5.89  | 42   | 6.1468          |
+| 4.4728        | 6.88  | 49   | 5.8255          |
+| 3.8852        | 8.0   | 57   | 5.6175          |
+| 3.4495        | 8.98  | 64   | 5.5436          |
+| 3.2287        | 9.82  | 70   | 5.5041          |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 12198
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 1536,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 256,
+  "pad_token_id": 0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 12198
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bed8a252f812d3946366bc6263b0719dd2660d6c6fa33ed368cd4ed8001e733
+size 2796386080

runs/Apr18_09-41-06_gcn43.local.snellius.surf.nl/events.out.tfevents.1713426076.gcn43.local.snellius.surf.nl.1680661.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f2bcb0497ed12338dbe3232bfa17ae8f7cf08a155adba1483349c7ff626b15
+size 74359

runs/Apr18_11-42-53_gcn65.local.snellius.surf.nl/events.out.tfevents.1713433381.gcn65.local.snellius.surf.nl.1139270.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e0f924bad2bcd533ebf4a112c524c6636522ab0d7d7ada36af8423f256186e
+size 18745

runs/Apr18_12-09-23_gcn14.local.snellius.surf.nl/events.out.tfevents.1713434972.gcn14.local.snellius.surf.nl.894979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4cc5b06d9d53cd009cb22691bf1d02db7b2f55be575052f2ed3ad02a42be93
+size 22176

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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
+    },
+    "12198": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51cd671d71df72bdf5cfdc25fe916cc54fdc35454d912d0063d528cf1c8a8a4
+size 4984