Training in progress, step 428, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9703f14666b0a7b428e5538b02b42d07e939f0ed596ca1de7c7458b03578106c
+oid sha256:5edf0f88f8f2e77ac94d05aceec9aba273d720dcd1481e1016e8ee91c4f65a86
 size 201880976

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a77b53a8ef0108a74749a4fc70eb63cd6fb4c7463fa6988bb4b7bdbc658e00
+oid sha256:cb5bc5310f6e8984854e8b0a8f074e20d6f57e5be6750d3e330f559c6f2e7d52
 size 102771659

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc1bb0b94bf887d7599f604268735ce8390dcb29cc5afbba0858f97039cc450
+oid sha256:e61e21d7a01dc7c642e9701af3fb914f9e6ca6f2866bd5182c14f9860c3646dc
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f85d84e1e08e1f08e16e94ced0fcf0653086b3d51679d3503f16c4bdd8524fb5
+oid sha256:13916fdf7ba8313e9fab314d766f1e35afde90bbe7316098fdd56f9cc606892b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 400,
   "best_metric": 0.754337888795046,
   "best_model_checkpoint": "./qwen2.5-7b-sft-qlora/checkpoint-400",
-  "epoch": 1.8701754385964913,
+  "epoch": 2.0,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 428,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -512,6 +512,26 @@
       "eval_samples_per_second": 27.224,
       "eval_steps_per_second": 1.703,
       "step": 400
+    },
+    {
+      "entropy": 0.5425351396203041,
+      "epoch": 1.9169590643274854,
+      "grad_norm": 0.2328052669763565,
+      "learning_rate": 1.1994589235353681e-06,
+      "loss": 0.5376,
+      "mean_token_accuracy": 0.8435128018260002,
+      "num_tokens": 9853669.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.533241743594408,
+      "epoch": 1.9637426900584796,
+      "grad_norm": 0.22453628480434418,
+      "learning_rate": 2.695492370149988e-07,
+      "loss": 0.5238,
+      "mean_token_accuracy": 0.8451769664883614,
+      "num_tokens": 10097512.0,
+      "step": 420
     }
   ],
   "logging_steps": 10,
@@ -526,12 +546,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.368108050339717e+17,
+  "total_flos": 8.941697521363354e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null