Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bea48aba2aad91e78bc15f23d5537e2ad0060957d3294b18164393a2fc910a
+oid sha256:ea7c6bd4abb116f85eabb7d425ebeee3cecf453fe3bde4ccf450bac2d6a78256
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba85f9efd58a0a8e29115d46ba14fbb5e4623464bbaebc85b98151304236f607
+oid sha256:14bfd9c4505f5ed5b8d03a628d7bf6ab3f9bfb30a541f3e36753a90c872bf2f9
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c84b76c59750ef4e237e1da0c263fb3126af7a888577f95cb7cabb95d1f5e079
+oid sha256:349e97e26ee9ce521c42b5e00150b770b606828ce0ab9238826dbf5b8529d2d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01656754460492778,
+  "epoch": 0.021240441801189464,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 5.8663,
       "step": 35
+    },
+    {
+      "epoch": 0.016992353440951572,
+      "grad_norm": 1.592289924621582,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.8633,
+      "step": 40
+    },
+    {
+      "epoch": 0.016992353440951572,
+      "eval_loss": 1.4971717596054077,
+      "eval_runtime": 53.2016,
+      "eval_samples_per_second": 18.646,
+      "eval_steps_per_second": 9.323,
+      "step": 40
+    },
+    {
+      "epoch": 0.019116397621070518,
+      "grad_norm": 1.5609835386276245,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.2107,
+      "step": 45
+    },
+    {
+      "epoch": 0.021240441801189464,
+      "grad_norm": 1.4892950057983398,
+      "learning_rate": 0.0,
+      "loss": 5.9187,
+      "step": 50
+    },
+    {
+      "epoch": 0.021240441801189464,
+      "eval_loss": 1.4925423860549927,
+      "eval_runtime": 53.0127,
+      "eval_samples_per_second": 18.713,
+      "eval_steps_per_second": 9.356,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3970148358684672.0,
+  "total_flos": 5025794743074816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null