Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be13dd30deabc91c7f1eef1ea22aab61332e961ca304f0aa8146e4813cfc895e
+oid sha256:4ee9b9d48f7bbef6bc7f6c71e6c1078205b351feb18a284cdb1fef4ad774860b
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ebf79a01fc9a02fad4f28b72dd1075124faa66205558b9ec484f91d21bd5a4b
+oid sha256:cba468c129d6d7f7e1dd218e7e198c6472f4d8ecafe34572f9937ffad9a6b50d
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8874dd5e607118e18f489ed9ad8aaab7c3de4c272a2acaa47fb9a2cd05a480a
+oid sha256:4fba7b3aa24187728c3eecfbdd90586f69803afe4ee661ac3d5463e4c2381ab0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605d23f463d574da26fdafa2a2fc396d0b00160053ea75ca175c5c8e6f2990e2
+oid sha256:20b6afe9f4b9513bda96be941880d24726826d6e0d0960bca314ae3f1d65fc06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00577838972530077,
+  "epoch": 0.008667584587951154,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,35 @@
       "eval_samples_per_second": 9.367,
       "eval_steps_per_second": 4.684,
       "step": 16
+    },
+    {
+      "epoch": 0.006500688440963366,
+      "grad_norm": 0.3276103436946869,
+      "learning_rate": 0.00018,
+      "loss": 2.2062,
+      "step": 18
+    },
+    {
+      "epoch": 0.007584136514457261,
+      "grad_norm": 0.33101603388786316,
+      "learning_rate": 0.00019989930665413147,
+      "loss": 2.2203,
+      "step": 21
+    },
+    {
+      "epoch": 0.008667584587951154,
+      "grad_norm": 0.29219868779182434,
+      "learning_rate": 0.00019839295885986296,
+      "loss": 2.1191,
+      "step": 24
+    },
+    {
+      "epoch": 0.008667584587951154,
+      "eval_loss": 2.177788496017456,
+      "eval_runtime": 996.3567,
+      "eval_samples_per_second": 9.361,
+      "eval_steps_per_second": 4.681,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -85,7 +114,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.512307353092096e+16,
+  "total_flos": 1.2768461029638144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null