Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "EleutherAI/pythia-70m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

logs/1676885969.597473/events.out.tfevents.1676885969.Lewiss-MacBook-Pro.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0473564deb29d0f0901ff8bfdae455d99e77136121844a60c3a8d816011ab49
+size 5412

logs/1676886291.254921/events.out.tfevents.1676886291.Lewiss-MacBook-Pro.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5259e311ccf76af9cadc6522f802962bebdf1bd2af1a7bc9906089d41c75c9
+size 5412

logs/1676886358.586945/events.out.tfevents.1676886358.Lewiss-MacBook-Pro.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cde1682c4010f594a612782e05597909050a202ae7ef5387daeeb8fb2b8289
+size 5412

logs/events.out.tfevents.1676885969.Lewiss-MacBook-Pro.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69629acb26ea95ba0f32cd4cf23979411d74adc172e57d350b7ab0da3ab9769a
+size 3780

logs/events.out.tfevents.1676886291.Lewiss-MacBook-Pro.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f5338b18c7971ddd5118dd3e1427bd33b5f486445e7abe6b7eb457a408ce65
+size 3780

logs/events.out.tfevents.1676886358.Lewiss-MacBook-Pro.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836efba0f2892adbdeeeb6fcf122060484aa051e0930546877a24b2588b2261b
+size 3779

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b959cbf52e16456cf124174189a9719c34fad40e2bf00acc0c3ecb2685a526
+size 306902347

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "EleutherAI/pythia-70m",
+  "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3102de411df6cfb8128cb3c3d4ab8025c1304dba1b6e59791f5a897633ba04
+size 3515