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:bda9fbf91b4be6e439e57b8d1be1a218a6b8aca3238139e38d76a93b75db6bca
+size 33744230

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 sha256:5121a797be67433a059859cf2d5954be230e5927f65a9b108ec2353d9c32ca9e
+size 16600550

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a867e26f170bf16867529fb1669b9673f5f98664909ccfee97bb2fdb906bbdb
+size 2471645608

results.json

@@ -0,0 +1,19 @@
+{
+  "results": {
+    "glue_mrpc_acc_score": 0.8161764705882353,
+    "glue_mrpc_acc_sem": 0.019199741465701966,
+    "glue_mrpc_f1_score": 0.8628884826325411,
+    "glue_mrpc_f1_sem": 0.01574402327423612,
+    "glue_rte_acc_score": 0.8086642599277978,
+    "glue_rte_acc_sem": 0.023677052322414436,
+    "glue_sst2_acc_score": 0.9231651376146789,
+    "glue_sst2_acc_sem": 0.009024222176285823
+  },
+  "energy": {
+    "total": 842507.9384200001,
+    "train": 789710.64375,
+    "eval": 52797.29467
+  },
+  "train_energy": 789710.64375,
+  "eval_energy": 52797.29467
+}

summary.json

@@ -0,0 +1,23 @@
+{
+    "flops": {
+        "eval": 20581868627334400,
+        "train": 148918793608399968,
+        "total": 169500662235734368
+    },
+    "total": {
+        "total": 842507.9384200001,
+        "train": 789710.64375,
+        "eval": 52797.29467
+    },
+    "best_evals": {
+        "pplx": {
+            "score": 25349132.253247358,
+            "step": 17220
+        },
+        "rougel": {
+            "precision": 0.8876043673731535,
+            "recall": 0.8876043673731535,
+            "fmeasure": 0.8876043673731535
+        }
+    }
+}