Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819076a6491070f25f68462834d5b39a0f3c0be4afbf8f305a197fe55d6b3625
+oid sha256:c9fb3eac6acb87cd94ddb54de5df6b442f16235dec4e4eaaa3e9f60fad12deb8
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba48c9d0093a74ac9cec740174f1f88ca134b9546c697ea1db55a60867fa16dd
+oid sha256:b59b927bb29ff5e76c9211dcb55c8a82808aa247293935df2104bdc452f5f1e6
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6cd3789a603cc9db1f0b416612fba074ab96fe35f4ad309fac449135e2f22d
+oid sha256:15c0eeda3a62034479ea787479fb6c3516b246ee5930ba976a4814c1c12227b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000922668819560579,
+  "epoch": 0.0013840032293408685,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 7.708,
       "eval_steps_per_second": 3.855,
       "step": 20
+    },
+    {
+      "epoch": 0.0009688022605386079,
+      "grad_norm": 37.27873229980469,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.5777,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011072025834726947,
+      "grad_norm": 182.59519958496094,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.4011,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011533360244507238,
+      "eval_loss": 1.360875129699707,
+      "eval_runtime": 1221.0327,
+      "eval_samples_per_second": 7.475,
+      "eval_steps_per_second": 3.738,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012456029064067816,
+      "grad_norm": 168.9602508544922,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.5717,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013840032293408685,
+      "grad_norm": 153.65328979492188,
+      "learning_rate": 0.0,
+      "loss": 5.3508,
+      "step": 30
+    },
+    {
+      "epoch": 0.0013840032293408685,
+      "eval_loss": 1.3646162748336792,
+      "eval_runtime": 1189.2128,
+      "eval_samples_per_second": 7.675,
+      "eval_steps_per_second": 3.838,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5777796587520000.0,
+  "total_flos": 8666694881280000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null