End of training

README.md

@@ -0,0 +1,54 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: jonas
+  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. -->
+
+# jonas
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## 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: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 500
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu118
+- Datasets 2.16.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 51000
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 51000,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 51000,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51001
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 51000,
+  "eos_token_id": 51000,
+  "transformers_version": "4.37.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165d938f5f001035b0fced321a265e1b6d38c0b2efd3546899c7fbd5b4d8d0f3
+size 500059776

runs/Jan08_19-15-15_Haukurs-pc/events.out.tfevents.1704741322.Haukurs-pc.502.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2389f8906c8fe97600098a951d495616657fe95016464d588314087b72412f0
+size 4637

runs/Jan08_19-27-21_Haukurs-pc/events.out.tfevents.1704742041.Haukurs-pc.2269.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db548c479adf7e28b88d95fd05104903881333699c14f89d368d76acec820eae
+size 4637

runs/Jan08_19-30-31_Haukurs-pc/events.out.tfevents.1704742232.Haukurs-pc.2754.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30149879d36cd18171fcb564ca02e54fba94124f10ce787de5943253912a425
+size 4634

runs/Jan08_19-35-53_Haukurs-pc/events.out.tfevents.1704742555.Haukurs-pc.3237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:128e5ad3034748518d2dd68ff9ed8b30d762332270978307d8a042eff0c51b40
+size 4184

runs/Jan08_21-16-19_Haukurs-pc/events.out.tfevents.1704748580.Haukurs-pc.14689.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f5919c9d0d7a6687ff7fdc1590c7a21e5df152df76dae36995b086af803cc74
+size 4760

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 512,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc2c6782345264da0ecdde134624f56260ee2ccfdd727567332f0005f95da0c
+size 4728