Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1071527821ce98f40652f60df4249abea70fce940f87d7ef6226f377282ae77
+oid sha256:dabadd77bc689da500c9b7eda73f22b5f0612bb18ac452eb71eaa547de6076b2
 size 69839888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdda95fc6cea85ee612917d9ca7cbe77103578ac1b08a4e9ae0e6fb54c5da36
+oid sha256:8ddcaf4b49e6ae3a3e6bfed2eabe642fbe9475c2d5427243583e2339ea0754d1
 size 139961199

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c411ba7c44ad93566d27c2dd70138d98e6d352d1ef0f5bd37c062a3ae885bfb7
+oid sha256:d45dcb26e076badfa1f9b7021eb697d18eae744725aec55db9cf2e55eb4872b0
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b414df4c202472a3852e19e94856c007474181cbfc2f5c445e0316c2ae6c07f
+oid sha256:624edc83d795c4b4c219a679dcf9a8467dd8fc40fd38a2415b413d6849e9b256
 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": 2.25,
+  "epoch": 2.5,
   "eval_steps": 25,
-  "global_step": 225,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,37 @@
       "eval_samples_per_second": 0.718,
       "eval_steps_per_second": 0.718,
       "step": 225
+    },
+    {
+      "entropy": 0.9435553016761938,
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.0019683837890625,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.000540799965771536,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 410073.0,
+      "step": 228
+    },
+    {
+      "entropy": 0.9341509019335111,
+      "epoch": 2.4,
+      "grad_norm": 0.00075531005859375,
+      "learning_rate": 4.1924398625429554e-05,
+      "loss": 0.00048237569474925596,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 431265.0,
+      "step": 240
+    },
+    {
+      "epoch": 2.5,
+      "eval_entropy": 0.9396904742717743,
+      "eval_loss": 0.001355790183879435,
+      "eval_mean_token_accuracy": 0.9996986410021782,
+      "eval_num_tokens": 448995.0,
+      "eval_runtime": 278.5353,
+      "eval_samples_per_second": 0.718,
+      "eval_steps_per_second": 0.718,
+      "step": 250
     }
   ],
   "logging_steps": 12,
@@ -306,7 +337,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.08961083341856e+16,
+  "total_flos": 1.20860153697168e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null