Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4811d78b9dd78d9aebe7b80047f6217dcfdc6526595cda2721fecd638a5693d
+oid sha256:65d5f38476a15e610dbd801965d14fb6475cabef44e0de1387a556b1eb9f226d
 size 69839888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb20d043b220c3d5a39ce637102af1f6c75cf597f4b0132882fba06e001f6bd3
+oid sha256:1c9ddcc7ffff2bc65e5c37f014168fb955516f1664d6f4689b9b19c87829e77e
 size 139961199

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170c7959150cf68a6db943e8d36c0961729d2d4eb32726fb3dee9c6cff97c3e7
+oid sha256:776283c93da0fbe2c98754fb9dcafb2fe63451cf58bec777930992c40175a8b7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf6561675164f7b29c0db741edcb28bfc670b31565f97f608dc8729c5ab4465
+oid sha256:a17fb7f88a76c7ef223a7ecfb2899772ca222663e2f4f36c00fa936fd471f4de
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 175,
   "best_metric": 0.0012933596735820174,
   "best_model_checkpoint": "./c2c_gemma4_e4b_qlora_checkpoint/checkpoint-175",
-  "epoch": 1.75,
+  "epoch": 2.0,
   "eval_steps": 25,
-  "global_step": 175,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -225,6 +225,37 @@
       "eval_samples_per_second": 0.716,
       "eval_steps_per_second": 0.716,
       "step": 175
+    },
+    {
+      "entropy": 0.939991781488061,
+      "epoch": 1.8,
+      "grad_norm": 0.0037994384765625,
+      "learning_rate": 8.316151202749142e-05,
+      "loss": 0.003757506919403871,
+      "mean_token_accuracy": 0.9998926116774479,
+      "num_tokens": 323852.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.9397506633152565,
+      "epoch": 1.92,
+      "grad_norm": 0.002349853515625,
+      "learning_rate": 7.491408934707905e-05,
+      "loss": 0.002571452253808578,
+      "mean_token_accuracy": 0.9998891844103733,
+      "num_tokens": 345582.0,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.9420398616790772,
+      "eval_loss": 0.0013476534513756633,
+      "eval_mean_token_accuracy": 0.9996986410021782,
+      "eval_num_tokens": 359794.0,
+      "eval_runtime": 278.2063,
+      "eval_samples_per_second": 0.719,
+      "eval_steps_per_second": 0.719,
+      "step": 200
     }
   ],
   "logging_steps": 12,
@@ -244,7 +275,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8478070804454400.0,
+  "total_flos": 9684909217100160.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null