Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "togethercomputer/GPT-NeoXT-Chat-Base-20B",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_fast",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 44,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.26.0",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50432
+}

logs/1678791639.548573/events.out.tfevents.1678791639.ip-26-0-150-12.2203689.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fd722598c9eb6ee885e5ba0fb70aaf772e5efd08c0ec9912a808d9a64844a9
+size 5776

logs/events.out.tfevents.1678791639.ip-26-0-150-12.2203689.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1003b4cad9a28e4db8b655ff1fef37518564a3456d6a6d5a6f583770dbc0c8
+size 3979

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54ba87e61e70d2ed2869b795a21d266c34ba60e57c0a2fe7954895427cacf51
+size 4795