Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffbe581814a91bc96f67a98a7640d5e60305824d192888379be2f625240e6907
+oid sha256:be3302cf576b47e9a1504e53b3126aabaa5138d21b3980d8feda34748cc5c6bb
 size 69839888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778aa3e43dd136445e87fee61794e3e1df83f58433e5a7981e86145b6647cfe6
+oid sha256:1db7e0a193e70c561eef7d43df1fa5f629eea09f568c64a32b28e813f0fea3c9
 size 139961199

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b27703e5a4b9cad8b1a1ad28013fb48cf214afa17622ce64fd5bd9d5c55d04b
+oid sha256:00c2073fddb911b507a7d0d37ba1c1035adea36355a18167691ee43733fb41a3
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3028579e4560eb6751d53608fd9a425d36e7979991b91eee7eabefa089a31b
+oid sha256:7c10c5ead0eacca08e8bf2135902a537d641281f4ab768a9fb4d0a618964122f
 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": 0.75,
+  "epoch": 1.0,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,37 @@
       "eval_samples_per_second": 0.716,
       "eval_steps_per_second": 0.716,
       "step": 75
+    },
+    {
+      "entropy": 0.9606282946964105,
+      "epoch": 0.84,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00014914089347079038,
+      "loss": 0.01685357342163722,
+      "mean_token_accuracy": 0.9992394285897414,
+      "num_tokens": 151176.0,
+      "step": 84
+    },
+    {
+      "entropy": 0.9429992654671272,
+      "epoch": 0.96,
+      "grad_norm": 0.00141143798828125,
+      "learning_rate": 0.00014089347079037802,
+      "loss": 0.014461403091748556,
+      "mean_token_accuracy": 0.9996106904000044,
+      "num_tokens": 172959.0,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.9499474939703941,
+      "eval_loss": 0.003532835515215993,
+      "eval_mean_token_accuracy": 0.9992225003242493,
+      "eval_num_tokens": 179897.0,
+      "eval_runtime": 279.1849,
+      "eval_samples_per_second": 0.716,
+      "eval_steps_per_second": 0.716,
+      "step": 100
     }
   ],
   "logging_steps": 12,
@@ -120,7 +151,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3634458724972800.0,
+  "total_flos": 4842454608550080.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null