Training in progress, step 270, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8043f610454848959146a4a0a6a319b6974aacf97199f93ccdc9807cdee87d
+oid sha256:a96bb255d96fa6a5c36b2a68ed9f157cb7ce4d904166afe1554a5aeab24df468
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47d8ed2af66819690de3a91b313d8b3cc9cf175b4c8c5b09f5f07edab59d149
+oid sha256:0bb86e83d07a08af27b3be9f2175e8a0f16b03763e0c8cdd676dff4d98e6b334
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61da44741eb913b25288310a2c5a8061ca4e7ccbd656d4d5374480814010d063
+oid sha256:e9795343af1ea69aed71e480b971fd4b8490c009519e844b26a34d8fe7d5fb38
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb48cc07c2a9bb46a803e4b228893e55e8f4cc181dfe614534c68943bb96b36d
+oid sha256:978b2fc5e17da46b55d130e174b6d196c16b7559a4a5513939af034ef3402d76
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 180,
-  "best_metric": 0.5925899147987366,
-  "best_model_checkpoint": "/teamspace/studios/this_studio/workspace_3/outputs/Qwen25_Coder_MCQ_5Epochs_0402_2229/checkpoint-180",
-  "epoch": 1.6822429906542056,
+  "best_global_step": 270,
+  "best_metric": 0.5840281248092651,
+  "best_model_checkpoint": "/teamspace/studios/this_studio/workspace_3/outputs/Qwen25_Coder_MCQ_5Epochs_0402_2229/checkpoint-270",
+  "epoch": 2.5233644859813085,
   "eval_steps": 30,
-  "global_step": 180,
+  "global_step": 270,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -98,6 +98,51 @@
       "eval_samples_per_second": 1.813,
       "eval_steps_per_second": 0.23,
       "step": 180
+    },
+    {
+      "epoch": 1.9626168224299065,
+      "grad_norm": 0.17269107699394226,
+      "learning_rate": 3.531442281389441e-05,
+      "loss": 0.594,
+      "step": 210
+    },
+    {
+      "epoch": 1.9626168224299065,
+      "eval_loss": 0.5875635147094727,
+      "eval_runtime": 78.9327,
+      "eval_samples_per_second": 1.799,
+      "eval_steps_per_second": 0.228,
+      "step": 210
+    },
+    {
+      "epoch": 2.2429906542056073,
+      "grad_norm": 0.1980254054069519,
+      "learning_rate": 2.0056981513219942e-05,
+      "loss": 0.5762,
+      "step": 240
+    },
+    {
+      "epoch": 2.2429906542056073,
+      "eval_loss": 0.5854137539863586,
+      "eval_runtime": 78.9377,
+      "eval_samples_per_second": 1.799,
+      "eval_steps_per_second": 0.228,
+      "step": 240
+    },
+    {
+      "epoch": 2.5233644859813085,
+      "grad_norm": 0.19368061423301697,
+      "learning_rate": 8.307466849412366e-06,
+      "loss": 0.5782,
+      "step": 270
+    },
+    {
+      "epoch": 2.5233644859813085,
+      "eval_loss": 0.5840281248092651,
+      "eval_runtime": 77.425,
+      "eval_samples_per_second": 1.834,
+      "eval_steps_per_second": 0.232,
+      "step": 270
     }
   ],
   "logging_steps": 30,
@@ -117,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.377377412343398e+16,
+  "total_flos": 1.4052187012123853e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null