Training in progress, step 225, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d5f38476a15e610dbd801965d14fb6475cabef44e0de1387a556b1eb9f226d
+oid sha256:c1071527821ce98f40652f60df4249abea70fce940f87d7ef6226f377282ae77
 size 69839888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c9ddcc7ffff2bc65e5c37f014168fb955516f1664d6f4689b9b19c87829e77e
+oid sha256:afdda95fc6cea85ee612917d9ca7cbe77103578ac1b08a4e9ae0e6fb54c5da36
 size 139961199

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776283c93da0fbe2c98754fb9dcafb2fe63451cf58bec777930992c40175a8b7
+oid sha256:c411ba7c44ad93566d27c2dd70138d98e6d352d1ef0f5bd37c062a3ae885bfb7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a17fb7f88a76c7ef223a7ecfb2899772ca222663e2f4f36c00fa936fd471f4de
+oid sha256:2b414df4c202472a3852e19e94856c007474181cbfc2f5c445e0316c2ae6c07f
 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": 2.0,
+  "epoch": 2.25,
   "eval_steps": 25,
-  "global_step": 200,
+  "global_step": 225,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -256,6 +256,37 @@
       "eval_samples_per_second": 0.719,
       "eval_steps_per_second": 0.719,
       "step": 200
+    },
+    {
+      "entropy": 0.946158512805899,
+      "epoch": 2.04,
+      "grad_norm": 0.0019378662109375,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0006203272302324573,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 366521.0,
+      "step": 204
+    },
+    {
+      "entropy": 0.9271950218826532,
+      "epoch": 2.16,
+      "grad_norm": 0.00189208984375,
+      "learning_rate": 5.84192439862543e-05,
+      "loss": 0.0006873769840846459,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 388482.0,
+      "step": 216
+    },
+    {
+      "epoch": 2.25,
+      "eval_entropy": 0.9353397011756897,
+      "eval_loss": 0.0013332690577954054,
+      "eval_mean_token_accuracy": 0.9996986410021782,
+      "eval_num_tokens": 404790.0,
+      "eval_runtime": 278.3647,
+      "eval_samples_per_second": 0.718,
+      "eval_steps_per_second": 0.718,
+      "step": 225
     }
   ],
   "logging_steps": 12,
@@ -275,7 +306,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9684909217100160.0,
+  "total_flos": 1.08961083341856e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null