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:b154abd3441833c7443da1f77ff6860e90ef8fad231b76f33eb124bda6aed7c4
+oid sha256:f7d04fcfa660e161b9860d914612d0f365ee1798f67fbe691cba72bfdec585d3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638caa18771c095c4cc960fe980cbb31b5c144bcc3f4c3af4043d69bf271686f
+oid sha256:14322ab0bd037e11f978804a37a9e67d2cc96497671ab1d7e01e07bb6bb74348
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89be65360c462d9c4812bfee4e603b36894408ac274af51796d35fb242819f3e
+oid sha256:c8c07670ce8c13a1c573ebda1e138b9cdd20b7c958607701a00698c7027abc81
 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": 0.0007612912671107532,
+  "epoch": 0.0009760144450137862,
   "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": 1.5097,
       "step": 35
+    },
+    {
+      "epoch": 0.000780811556011029,
+      "grad_norm": 1.4106273651123047,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5349,
+      "step": 40
+    },
+    {
+      "epoch": 0.000780811556011029,
+      "eval_loss": 1.5933020114898682,
+      "eval_runtime": 1587.888,
+      "eval_samples_per_second": 13.584,
+      "eval_steps_per_second": 6.792,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008784130005124076,
+      "grad_norm": 1.8581594228744507,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5793,
+      "step": 45
+    },
+    {
+      "epoch": 0.0009760144450137862,
+      "grad_norm": 1.2158750295639038,
+      "learning_rate": 0.0,
+      "loss": 1.5234,
+      "step": 50
+    },
+    {
+      "epoch": 0.0009760144450137862,
+      "eval_loss": 1.587828516960144,
+      "eval_runtime": 1585.3929,
+      "eval_samples_per_second": 13.605,
+      "eval_steps_per_second": 6.803,
+      "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": 7999365373231104.0,
+  "total_flos": 1.0218842471006208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null