Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe5f4401515e7f8c04702f29139103b362d4b72459b914907c6a4beeac13a8c
+oid sha256:11f0e2ca13e33a85b3120a4ee713ea0e06007c9189c4a3e7fa7b167a9e3c4f20
 size 69839888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97633cc78b6f5944566b39074c35f615d1189957d3c37bcfd1d701e02d9be687
+oid sha256:4df2282fccbd13d593ec483631834e137826c7a4f170bcecec0d10f808adb66a
 size 139961199

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754399d1834ff01f9450ef44b2e14df008190846354d1ef70746aae4591d4ea6
+oid sha256:25a08711b58e82a94c7d430db91c18062e356888f736cdc904051ea42bffee1f
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a4d7a648c7af1e6ae060ef7b768cb4a152a53bf12caf8e299dd53248f81d43
+oid sha256:88fff52255c07c1bc4a8c7a336a046e1a58603d0ff7c2a9d4b7c1a94aea45fe9
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 75,
-  "best_metric": 0.002200173679739237,
-  "best_model_checkpoint": "./c2c_gemma4_e4b_qlora_checkpoint/checkpoint-75",
-  "epoch": 1.25,
+  "best_global_step": 150,
+  "best_metric": 0.0021258138585835695,
+  "best_model_checkpoint": "./c2c_gemma4_e4b_qlora_checkpoint/checkpoint-150",
+  "epoch": 1.5,
   "eval_steps": 25,
-  "global_step": 125,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,37 @@
       "eval_samples_per_second": 0.717,
       "eval_steps_per_second": 0.717,
       "step": 125
+    },
+    {
+      "entropy": 0.9591117737193903,
+      "epoch": 1.32,
+      "grad_norm": 0.01495361328125,
+      "learning_rate": 0.00011615120274914091,
+      "loss": 0.0018487606818477313,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 236737.0,
+      "step": 132
+    },
+    {
+      "entropy": 0.9401631454626719,
+      "epoch": 1.44,
+      "grad_norm": 0.0022735595703125,
+      "learning_rate": 0.00010790378006872852,
+      "loss": 0.004954988757769267,
+      "mean_token_accuracy": 0.9997710343450308,
+      "num_tokens": 258514.0,
+      "step": 144
+    },
+    {
+      "epoch": 1.5,
+      "eval_entropy": 0.9480650842189788,
+      "eval_loss": 0.0021258138585835695,
+      "eval_mean_token_accuracy": 0.9996193596720695,
+      "eval_num_tokens": 269172.0,
+      "eval_runtime": 279.1751,
+      "eval_samples_per_second": 0.716,
+      "eval_steps_per_second": 0.716,
+      "step": 150
     }
   ],
   "logging_steps": 12,
@@ -182,7 +213,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6041217642603840.0,
+  "total_flos": 7245552687886080.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null