Training in progress, step 500

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "EleutherAI/pythia-70m-deduped",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "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,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d18d517137e2e667bf6270d3bba877deea6f1501aac1a63a4c0ffd811786f5
+size 281715176

runs/Apr13_17-49-41_DESKTOP-7EBBP1S/events.out.tfevents.1713001793.DESKTOP-7EBBP1S.222013.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16148b5b5e9f75f8454cd772fba876a93e1b6d14e2c674f93b96787be7c4b09
+size 7371

runs/Apr13_18-03-40_DESKTOP-7EBBP1S/events.out.tfevents.1713002620.DESKTOP-7EBBP1S.223104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8da20e5d1df9fb8b898a4cb0d284e967f6838a608a58dde9023ed3a7b811f7
+size 15980

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3817999c410b320a86fcff4e4295c89bda8e5cfe7620aeb4ccb23207569631
+size 4984