Training in progress, step 200

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "dtype": "float16",
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "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": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3709b968765746094c2ee23196c3a028eb60fd8ad72838511bf6d6be9714887
+size 28143920

runs/Feb21_10-40-52_c83a631fdb95/events.out.tfevents.1771670452.c83a631fdb95.1165.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c742300a6d1396d8b61492d32cb6ed7fa315861cb0f33517874bdcb2ee814f
+size 5592

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19dd72015cba9eaa0dee9f06603dea3dd31ededf0e748d9c47ea18b22a9803b
+size 5201