Training in progress, step 125, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be3302cf576b47e9a1504e53b3126aabaa5138d21b3980d8feda34748cc5c6bb
+oid sha256:7fe5f4401515e7f8c04702f29139103b362d4b72459b914907c6a4beeac13a8c
 size 69839888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1db7e0a193e70c561eef7d43df1fa5f629eea09f568c64a32b28e813f0fea3c9
+oid sha256:97633cc78b6f5944566b39074c35f615d1189957d3c37bcfd1d701e02d9be687
 size 139961199

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c2073fddb911b507a7d0d37ba1c1035adea36355a18167691ee43733fb41a3
+oid sha256:754399d1834ff01f9450ef44b2e14df008190846354d1ef70746aae4591d4ea6
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c10c5ead0eacca08e8bf2135902a537d641281f4ab768a9fb4d0a618964122f
+oid sha256:d8a4d7a648c7af1e6ae060ef7b768cb4a152a53bf12caf8e299dd53248f81d43
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 75,
   "best_metric": 0.002200173679739237,
   "best_model_checkpoint": "./c2c_gemma4_e4b_qlora_checkpoint/checkpoint-75",
-  "epoch": 1.0,
+  "epoch": 1.25,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -132,6 +132,37 @@
       "eval_samples_per_second": 0.716,
       "eval_steps_per_second": 0.716,
       "step": 100
+    },
+    {
+      "entropy": 0.9496191050857306,
+      "epoch": 1.08,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00013264604810996563,
+      "loss": 0.021368369460105896,
+      "mean_token_accuracy": 0.9992247764021158,
+      "num_tokens": 194463.0,
+      "step": 108
+    },
+    {
+      "entropy": 0.951437915985783,
+      "epoch": 1.2,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00012439862542955326,
+      "loss": 0.005873216316103935,
+      "mean_token_accuracy": 0.9998891844103733,
+      "num_tokens": 216005.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.25,
+      "eval_entropy": 0.9553235971927643,
+      "eval_loss": 0.0023568905889987946,
+      "eval_mean_token_accuracy": 0.9995862373709679,
+      "eval_num_tokens": 224431.0,
+      "eval_runtime": 278.9364,
+      "eval_samples_per_second": 0.717,
+      "eval_steps_per_second": 0.717,
+      "step": 125
     }
   ],
   "logging_steps": 12,
@@ -151,7 +182,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4842454608550080.0,
+  "total_flos": 6041217642603840.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null