Training in progress, step 175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f0e2ca13e33a85b3120a4ee713ea0e06007c9189c4a3e7fa7b167a9e3c4f20
+oid sha256:b4811d78b9dd78d9aebe7b80047f6217dcfdc6526595cda2721fecd638a5693d
 size 69839888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df2282fccbd13d593ec483631834e137826c7a4f170bcecec0d10f808adb66a
+oid sha256:bb20d043b220c3d5a39ce637102af1f6c75cf597f4b0132882fba06e001f6bd3
 size 139961199

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a08711b58e82a94c7d430db91c18062e356888f736cdc904051ea42bffee1f
+oid sha256:170c7959150cf68a6db943e8d36c0961729d2d4eb32726fb3dee9c6cff97c3e7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88fff52255c07c1bc4a8c7a336a046e1a58603d0ff7c2a9d4b7c1a94aea45fe9
+oid sha256:0cf6561675164f7b29c0db741edcb28bfc670b31565f97f608dc8729c5ab4465
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 150,
-  "best_metric": 0.0021258138585835695,
-  "best_model_checkpoint": "./c2c_gemma4_e4b_qlora_checkpoint/checkpoint-150",
-  "epoch": 1.5,
+  "best_global_step": 175,
+  "best_metric": 0.0012933596735820174,
+  "best_model_checkpoint": "./c2c_gemma4_e4b_qlora_checkpoint/checkpoint-175",
+  "epoch": 1.75,
   "eval_steps": 25,
-  "global_step": 150,
+  "global_step": 175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -194,6 +194,37 @@
       "eval_samples_per_second": 0.716,
       "eval_steps_per_second": 0.716,
       "step": 150
+    },
+    {
+      "entropy": 0.9431026068826517,
+      "epoch": 1.56,
+      "grad_norm": 0.0030975341796875,
+      "learning_rate": 9.965635738831616e-05,
+      "loss": 0.003447669247786204,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 280420.0,
+      "step": 156
+    },
+    {
+      "entropy": 0.9445797273268303,
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.0017852783203125,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0011490107669184606,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 302272.0,
+      "step": 168
+    },
+    {
+      "epoch": 1.75,
+      "eval_entropy": 0.9432125598192215,
+      "eval_loss": 0.0012933596735820174,
+      "eval_mean_token_accuracy": 0.9997524043917656,
+      "eval_num_tokens": 314960.0,
+      "eval_runtime": 279.3708,
+      "eval_samples_per_second": 0.716,
+      "eval_steps_per_second": 0.716,
+      "step": 175
     }
   ],
   "logging_steps": 12,
@@ -213,7 +244,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7245552687886080.0,
+  "total_flos": 8478070804454400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null