Training in progress, step 275, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dabadd77bc689da500c9b7eda73f22b5f0612bb18ac452eb71eaa547de6076b2
-size 69839888
+oid sha256:a6ed9c25b5708706b6a0b740e4d5d39e9682269d0f82a597758060a5936fa63c
+size 139602808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ddcaf4b49e6ae3a3e6bfed2eabe642fbe9475c2d5427243583e2339ea0754d1
-size 139961199
+oid sha256:25c4e222a4f31bf8d495402f1c8374be1d28a65bcd0806628a3c6fab8f020a4b
+size 279487343

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45dcb26e076badfa1f9b7021eb697d18eae744725aec55db9cf2e55eb4872b0
+oid sha256:ffa976baf87291d9fceae2498519d21057391d04b22c9721a4b3f7f4c2877fff
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624edc83d795c4b4c219a679dcf9a8467dd8fc40fd38a2415b413d6849e9b256
+oid sha256:0e447966aa81e08b07c548e62a661f7d1a3227b13b3d4b1fdce5aa9ec131d06b
 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": 2.5,
+  "epoch": 2.75,
   "eval_steps": 25,
-  "global_step": 250,
+  "global_step": 275,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -318,12 +318,43 @@
       "eval_samples_per_second": 0.718,
       "eval_steps_per_second": 0.718,
       "step": 250
+    },
+    {
+      "entropy": 0.9087011106312275,
+      "epoch": 2.52,
+      "grad_norm": 0.002573611680418253,
+      "learning_rate": 3.920265780730897e-05,
+      "loss": 0.0007128582801669836,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3959.0,
+      "step": 252
+    },
+    {
+      "entropy": 0.924984677384297,
+      "epoch": 2.64,
+      "grad_norm": 0.0005084075382910669,
+      "learning_rate": 3.122923588039867e-05,
+      "loss": 0.0006440305539096395,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 26050.0,
+      "step": 264
+    },
+    {
+      "epoch": 2.75,
+      "eval_entropy": 0.9374615728855134,
+      "eval_loss": 0.001335766282863915,
+      "eval_mean_token_accuracy": 0.9996986410021782,
+      "eval_num_tokens": 45328.0,
+      "eval_runtime": 252.969,
+      "eval_samples_per_second": 0.791,
+      "eval_steps_per_second": 0.791,
+      "step": 275
     }
   ],
   "logging_steps": 12,
-  "max_steps": 300,
+  "max_steps": 310,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 4,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -337,7 +368,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.20860153697168e+16,
+  "total_flos": 1.330615123911072e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d120c92ba91ddf4ca0253a099ee22d2291712c5f091a4855f1d947cb6f6a6059
+oid sha256:7ce060488f05343f0437ad90e26b0a95fbf802432a19bd58f1082d6c190ec4c8
 size 5713