ninagroot/GPT2-705Mtest

README.md

@@ -0,0 +1,81 @@
+---
+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: 5.4628
+
+## 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: 40
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 9.7135        | 0.57  | 1    | 9.7272          |
+| 8.0222        | 1.71  | 3    | 9.3213          |
+| 7.6063        | 2.86  | 5    | 8.5841          |
+| 7.5596        | 4.0   | 7    | 7.9271          |
+| 7.4194        | 4.57  | 8    | 8.0942          |
+| 7.1644        | 5.71  | 10   | 7.5409          |
+| 6.8531        | 6.86  | 12   | 7.3028          |
+| 6.3614        | 8.0   | 14   | 9.3796          |
+| 8.5129        | 8.57  | 15   | 7.6361          |
+| 6.1325        | 9.71  | 17   | 6.7577          |
+| 5.8526        | 10.86 | 19   | 6.5249          |
+| 5.5941        | 12.0  | 21   | 6.2490          |
+| 5.4307        | 12.57 | 22   | 6.2442          |
+| 5.1381        | 13.71 | 24   | 5.9595          |
+| 4.8705        | 14.86 | 26   | 5.8944          |
+| 4.7083        | 16.0  | 28   | 5.7005          |
+| 4.5355        | 16.57 | 29   | 5.7459          |
+| 4.4187        | 17.71 | 31   | 5.5387          |
+| 4.3123        | 18.86 | 33   | 5.4863          |
+| 4.0269        | 20.0  | 35   | 5.3277          |
+| 3.942         | 20.57 | 36   | 5.3274          |
+| 3.784         | 21.71 | 38   | 5.3998          |
+| 3.4991        | 22.86 | 40   | 5.4628          |
+
+
+### 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 sha256:88489323ca20dc864aa1bbbb0229c3ee79409a0e79fb1746145003251f77a5ac
+size 2796386080

runs/Apr17_12-24-48_gcn61.local.snellius.surf.nl/events.out.tfevents.1713349497.gcn61.local.snellius.surf.nl.3984517.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f3d980b23d33ec2f66c7aa4389002abb105341cef143cc8b2622ea84f13474
+size 41155

runs/Apr17_14-09-48_gcn20.local.snellius.surf.nl/events.out.tfevents.1713355797.gcn20.local.snellius.surf.nl.1872804.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6700eac66ebd9f905898d40f4578bc648ede5bf54c07cccb52f61c44369a1d
+size 19424

runs/Apr17_14-30-23_gcn10.local.snellius.surf.nl/events.out.tfevents.1713357035.gcn10.local.snellius.surf.nl.3796627.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9ca5185347da1ec47e04458b55269d305bede1c4357f58f9c8bdea17c11933
+size 19424

runs/Apr17_14-39-08_gcn53.local.snellius.surf.nl/events.out.tfevents.1713357559.gcn53.local.snellius.surf.nl.4133403.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e820e6647d03c6ab72ff3c33a7673f486461751c2af756c36d13f8666cdaa193
+size 23090

runs/Apr17_14-54-37_gcn38.local.snellius.surf.nl/events.out.tfevents.1713358487.gcn38.local.snellius.surf.nl.1402374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37322800818c3695e4ce8ec27b3e2f30c509e94edfcd592f0832da014a5999b5
+size 19424

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 sha256:8771d2cfcef1d1ffe22114e70ebead0ecc08c4ee4084fd54fa207a9793c64510
+size 4984