Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: kgw_gamma0.25_delta2_640k_pythia-1.4b-lr1e-5
+  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. -->
+
+# kgw_gamma0.25_delta2_640k_pythia-1.4b-lr1e-5
+
+This model is a fine-tuned version of [/scr-ssd/cygu/weights/pythia-1.4b](https://huggingface.co//scr-ssd/cygu/weights/pythia-1.4b) 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: 1e-05
+- train_batch_size: 64
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.29.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 3.564992360377624,
+    "train_runtime": 9434.0892,
+    "train_samples_per_second": 56.448,
+    "train_steps_per_second": 0.882
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/scr-ssd/cygu/weights/pythia-1.4b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.29.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8572c4316194c1dd3c6ce9f870b07f9da009f0458ae00bce26bfa0f12828bd
+size 5759380001

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|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 3.564992360377624,
+    "train_runtime": 9434.0892,
+    "train_samples_per_second": 56.448,
+    "train_steps_per_second": 0.882
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bcbfb4b687a7d54ba7d962b993704d1afecffb406a10d2c6106f392a363fad8
+size 4155

watermark_config.json

@@ -0,0 +1 @@
+{"vocab_size": 32000, "gamma": 0.25, "delta": 2.0, "seeding_scheme": "simple_1", "hash_key": 15485863, "select_green_tokens": true}