Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c226fdcbc9ffc2d2dff86f9e53300ca9a3cd6240c6ba49d4ce2cafcf6e61bd
+oid sha256:b993dd2af9daed31abb2888318f7d2b0eba68b8fbd5cf84b92e19894043e51f0
 size 144805440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ecc9700960334617b0b947f87ebfa51d5076ee8f732b72714c3f05e33fd8eea
+oid sha256:7f7ae96288913baea91f046c94f287ec6b3a764aa3ac57992f4aadc0e4d5d2f3
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244572e920d4037637c527b6e37fa1608a341cc2df3c8bee2f11df8e9f8b09fc
+oid sha256:2393d4cef73d1db7b8c3f435415b255d6adf1501885725bc9e847ed753bc01c0
 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": 0.005915813424345847,
+  "epoch": 0.011831626848691695,
   "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": 4.791,
       "eval_steps_per_second": 2.396,
       "step": 10
+    },
+    {
+      "epoch": 0.006825938566552901,
+      "grad_norm": 9.969215393066406,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.3175,
+      "step": 15
+    },
+    {
+      "epoch": 0.009101251422070534,
+      "grad_norm": 0.0247463658452034,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.4614,
+      "step": 20
+    },
+    {
+      "epoch": 0.009101251422070534,
+      "eval_loss": 0.2140456885099411,
+      "eval_runtime": 193.1936,
+      "eval_samples_per_second": 4.793,
+      "eval_steps_per_second": 2.397,
+      "step": 20
+    },
+    {
+      "epoch": 0.011376564277588168,
+      "grad_norm": 0.7247423529624939,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1652,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4210375092338688.0,
+  "total_flos": 8420750184677376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null