Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+experiment_config.json filter=lfs diff=lfs merge=lfs -text
+logs.jsonl filter=lfs diff=lfs merge=lfs -text

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
+}

experiment_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51f5dbc9c36c1bf5275e8da283fac468181c3ddd713c316d6c4d2d04548e9aa
+size 28759518

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"
+}

logs.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51f3e8a8c06f6bb7439ba983acf49d342a96ce323834ffe7d28e68a3a1b1732
+size 12790697

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332cae38bd84b6a1550b6200c875e44616e77e5f88e4065b3559f714a1f5c2d0
+size 2471645608

results.json

@@ -0,0 +1,19 @@
+{
+  "results": {
+    "commonsense_qa_commonsense_qa_acc_score": 0.447993447993448,
+    "commonsense_qa_commonsense_qa_acc_sem": 0.014237312976027771,
+    "mathqa_mathqa_acc_score": 0.5061976549413736,
+    "mathqa_mathqa_acc_sem": 0.009150704596340492,
+    "mathqa_mathqa_acc_norm_score": 0.4884422110552764,
+    "logiqa_logiqa_acc_score": 0.35944700460829493,
+    "logiqa_logiqa_acc_sem": 0.019017673991121007,
+    "logiqa_logiqa_acc_norm_score": 0.3778801843317972
+  },
+  "energy": {
+    "total": 1074204.4919399999,
+    "train": 709215.0616700001,
+    "eval": 364989.43027
+  },
+  "train_energy": 709215.0616700001,
+  "eval_energy": 364989.43027
+}

summary.json

@@ -0,0 +1,23 @@
+{
+    "flops": {
+        "eval": 162804001876448000,
+        "train": 232637820311129520,
+        "total": 395441822187577520
+    },
+    "total": {
+        "total": 1074204.4919399999,
+        "train": 709215.0616700001,
+        "eval": 364989.43027
+    },
+    "best_evals": {
+        "pplx": {
+            "score": 74.43227820021758,
+            "step": 1392
+        },
+        "rougel": {
+            "precision": 0.38466113072526587,
+            "recall": 0.3838580537206477,
+            "fmeasure": 0.3808062272246839
+        }
+    }
+}