Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283c9218103b83fa4eb24efb346320014ab9bce9a0c20a41ba705468edd04b45
+oid sha256:951472d114bd0e88585f2bb1264d71aea5ce1d73a31c3f89231b8b4dd429c4b7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76276f1217a05ddc39174905e0d60075a31d9af542b46311d48206d90824a5c
+oid sha256:7949722c2862fc9761df3613bd894ab5c056041f26b4ac5f0f9d67c4e4e69ba9
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc95f8ef66804917a60b19acbb3aaab5647926085d4ddb008103acb36348fb2
+oid sha256:2bc49e406d40d15d4c77a549f46af25554828e4ccf4a2549a6e443a9a7b138dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026302478502781994,
+  "epoch": 0.05260495700556399,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 8.709,
       "eval_steps_per_second": 4.375,
       "step": 10
+    },
+    {
+      "epoch": 0.030349013657056147,
+      "grad_norm": 0.9080146551132202,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.5644,
+      "step": 15
+    },
+    {
+      "epoch": 0.04046535154274153,
+      "grad_norm": 0.6127835512161255,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.3534,
+      "step": 20
+    },
+    {
+      "epoch": 0.04046535154274153,
+      "eval_loss": 0.32802435755729675,
+      "eval_runtime": 24.4681,
+      "eval_samples_per_second": 8.542,
+      "eval_steps_per_second": 4.291,
+      "step": 20
+    },
+    {
+      "epoch": 0.05058168942842691,
+      "grad_norm": 0.552888035774231,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.2888,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3295645846732800.0,
+  "total_flos": 6591291693465600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null