End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: other
+base_model: AI-Sweden-Models/gpt-sw3-126m-instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: confluence-model-test
+  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. -->
+
+# confluence-model-test
+
+This model is a fine-tuned version of [AI-Sweden-Models/gpt-sw3-126m-instruct](https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m-instruct) 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "AI-Sweden-Models/gpt-sw3-126m-instruct",
+  "activation_function": "gelu",
+  "apply_query_key_layer_scaling": true,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "initializer_range": 0.023,
+  "layer_norm_epsilon": 1e-05,
+  "max_length": 2048,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "normalize_attention_scores": true,
+  "pad_token_id": 0,
+  "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,
+  "tokenizer_class": "GPTSw3Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8628a176d9a0f56f0fade2c680d697dece1cc6a35c5f7e134110ca1643fa0111
+size 543138432

runs/Dec20_07-23-48_d85ef0b1f8ab/events.out.tfevents.1703057029.d85ef0b1f8ab.228.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f262d337e900baf66f212d2f2df67189168b21a6e80b8f9b76cdf3d230bed53a
+size 4926

runs/Dec20_07-25-43_d85ef0b1f8ab/events.out.tfevents.1703057144.d85ef0b1f8ab.228.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da9f6d9bb3d65b7a29b289344fa72fd9b51e719b4ae046674fa0ab5eb6f68f8
+size 4926

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251e64939d960a1a7eb4fd8293abdc3e76c382d2aa695735d681a5d6e23a3e51
+size 4600