Upload folder using huggingface_hub

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93f303b33aca20ea8deb0319665b8a4be6f598f3c595bdeff0b163ff243f659
+size 2471645608

results.json

@@ -0,0 +1,19 @@
+{
+  "results": {
+    "glue_mrpc_acc_score": 0.8014705882352942,
+    "glue_mrpc_acc_sem": 0.019772383169192092,
+    "glue_mrpc_f1_score": 0.8421052631578947,
+    "glue_mrpc_f1_sem": 0.017407398689792023,
+    "glue_rte_acc_score": 0.5234657039711191,
+    "glue_rte_acc_sem": 0.030063300411902607,
+    "glue_sst2_acc_score": 0.5229357798165137,
+    "glue_sst2_acc_sem": 0.01692401977869958
+  },
+  "energy": {
+    "total": 58401.35561,
+    "train": 45370.694260000004,
+    "eval": 13030.661350000002
+  },
+  "train_energy": 45370.694260000004,
+  "eval_energy": 13030.661350000002
+}

summary.json

@@ -0,0 +1,23 @@
+{
+    "flops": {
+        "eval": 5014951860256000,
+        "train": 10640863719936576,
+        "total": 15655815580192576
+    },
+    "total": {
+        "total": 58401.35561,
+        "train": 45370.694260000004,
+        "eval": 13030.661350000002
+    },
+    "best_evals": {
+        "pplx": {
+            "score": 36628973.8921973,
+            "step": 2751
+        },
+        "rougel": {
+            "precision": 0.7598039215686274,
+            "recall": 0.7598039215686274,
+            "fmeasure": 0.7598039215686274
+        }
+    }
+}