Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sft_a1_magicoder__Qwen3-8B
 
-This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--perturbed-docker-exp-magicoder-tasks-2_glm_4.7_traces_jupiter_upsampled_10k/snapshots/1d42cc3dc0818f1642c4f0120875810d492cd923_thinking_preprocessed dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--Magicoder-Evol-Instruct-110K-sandboxes-1_10k_glm_4.7_traces_jupiter/snapshots/5aeec71d5cdc4cd588e71eed903e3ab2f7b35051_thinking_preprocessed dataset.
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "achieved_tflops_per_gpu": 0.0034522879542614945,
-    "achieved_tflops_per_gpu_theoretical": 1151.8875513598773,
+    "achieved_tflops_per_gpu": 0.002110187398451811,
+    "achieved_tflops_per_gpu_theoretical": 650.4776760620482,
     "epoch": 7.0,
     "loss_nan_ranks": 0,
-    "loss_rank_avg": 0.20906896889209747,
-    "mfu_percent": 0.00024397794729763214,
-    "mfu_percent_theoretical": 81.40548066147542,
-    "total_flos": 702151473364992.0,
-    "train_loss": 0.11156423039722288,
-    "train_runtime": 12711.7053,
-    "train_samples_per_second": 5.432,
-    "train_steps_per_second": 0.34,
-    "valid_targets_mean": 3750.0,
-    "valid_targets_min": 750
+    "loss_rank_avg": 0.2384590357542038,
+    "mfu_percent": 0.00014912985148069337,
+    "mfu_percent_theoretical": 45.97015378530376,
+    "total_flos": 688651439570944.0,
+    "train_loss": 0.26049303336732077,
+    "train_runtime": 20396.6316,
+    "train_samples_per_second": 3.064,
+    "train_steps_per_second": 0.192,
+    "valid_targets_mean": 4082.4,
+    "valid_targets_min": 866
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e345b6afa60fa4829f5948b59ba8c50e55cb24728f0a0680678a76131d155f6
+oid sha256:daffa32e7444e736a1c517d62c2a55d9f96260371213ac37e97ac9827b55b478
 size 4902257696

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7f01ba11e70af275526f9878acfb0967b7aa77386c0cfe13ffdf81cd0fa2854
+oid sha256:dfe4bb96e03e07782586ca63884f59543a475c5932ac4ccf440848b3736ff540
 size 4915960368

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d25dd5e86fc1746044ec8925f77ec7e7454177ae06c88238f8d14bd506c9a86
+oid sha256:cc931313941b618ca7de44a63927fa3a1e43ed4b723a103c01493d683889d17b
 size 4983068496

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94d06ce0ca1539eb63055462f2bfb734ce12783f11f9ce8f55e7a63078b4bfc
+oid sha256:7ab55fd4c4fd1cdb8d41f5aee283940231d28eba52cc99ebf70cf3cbf11b598d
 size 1580230264

run_summary.json

@@ -1,10 +1,10 @@
 {
-  "agent_name": "1d42cc3dc0818f1642c4f0120875810d492cd923_thinking_preprocessed",
+  "agent_name": "5aeec71d5cdc4cd588e71eed903e3ab2f7b35051_thinking_preprocessed",
   "training_start": null,
   "training_end": null,
   "created_by": "raoof1",
   "base_model_name": "Qwen/Qwen3-8B",
-  "dataset_name": "/e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--perturbed-docker-exp-magicoder-tasks-2_glm_4.7_traces_jupiter_upsampled_10k/snapshots/1d42cc3dc0818f1642c4f0120875810d492cd923_thinking_preprocessed",
+  "dataset_name": "/e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--Magicoder-Evol-Instruct-110K-sandboxes-1_10k_glm_4.7_traces_jupiter/snapshots/5aeec71d5cdc4cd588e71eed903e3ab2f7b35051_thinking_preprocessed",
   "training_type": "SFT",
   "training_parameters": "https://huggingface.co/DCAgent/a1-magicoder/blob/main/config.json",
   "wandb_link": null,

train_results.json

@@ -1,16 +1,16 @@
 {
-    "achieved_tflops_per_gpu": 0.0034522879542614945,
-    "achieved_tflops_per_gpu_theoretical": 1151.8875513598773,
+    "achieved_tflops_per_gpu": 0.002110187398451811,
+    "achieved_tflops_per_gpu_theoretical": 650.4776760620482,
     "epoch": 7.0,
     "loss_nan_ranks": 0,
-    "loss_rank_avg": 0.20906896889209747,
-    "mfu_percent": 0.00024397794729763214,
-    "mfu_percent_theoretical": 81.40548066147542,
-    "total_flos": 702151473364992.0,
-    "train_loss": 0.11156423039722288,
-    "train_runtime": 12711.7053,
-    "train_samples_per_second": 5.432,
-    "train_steps_per_second": 0.34,
-    "valid_targets_mean": 3750.0,
-    "valid_targets_min": 750
+    "loss_rank_avg": 0.2384590357542038,
+    "mfu_percent": 0.00014912985148069337,
+    "mfu_percent_theoretical": 45.97015378530376,
+    "total_flos": 688651439570944.0,
+    "train_loss": 0.26049303336732077,
+    "train_runtime": 20396.6316,
+    "train_samples_per_second": 3.064,
+    "train_steps_per_second": 0.192,
+    "valid_targets_mean": 4082.4,
+    "valid_targets_min": 866
 }