Training in progress, step 264

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "JackFram/llama-68m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 12,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf56ee83260fde89e0fb0c75299781b01ec56374207a45a3529203f18d66bb8
+size 272123144

runs/May24_17-55-02_afc171c95cab/events.out.tfevents.1716573303.afc171c95cab.17338.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fedbd28bffc42e0c44b8e3049386ba2a3bf5dc338edb703eae6569988544e9b
+size 19058

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1892436d6f67cbf260858c1d8b64dea09b34f940aa4c979ac7e1908fd78aff5f
+size 5112