Training in progress, step 500

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "attn_pdrop": 0.0,
+  "bos_token_id": 98,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 98,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_ctx": 512,
+  "n_embd": 32,
+  "n_head": 4,
+  "n_inner": null,
+  "n_layer": 5,
+  "n_positions": 512,
+  "pad_token_id": 98,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 4,
+  "scale_attn_weights": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 1000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e7c2cd04f9dbb4837160697f0f0022d29a8e9755b1bce5252eeb4cacc4f262
+size 515784

runs/Apr21_08-48-05_6cac394efccd/events.out.tfevents.1745225294.6cac394efccd.214.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e3a769b622a48d8b36ac6911384c118833d2044b8e39c5fb17648303f97393
+size 5357

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91bc0e6877ae72cc5f0a94f7b8d3cb3d466925f83fc51661df1158bee5a122cb
+size 5368