Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b7404f3d4ce61490ad1b894c1ab76ae93fb71f7ff45d1d00dfef6b706fd0b2b
+oid sha256:ade96a55f0de78ca0baec55d15069b37e11758052a785489ae1edde312726088
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d064e8f44ef8536e3526dc7dd58266d7f0988e265cc192645df13f786ff07e80
+oid sha256:c777ff695bb34fc1f902e783d58f2e0d038ab80a0ae667f5e5796d3eb5f3e8d7
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6fa4c3006488197a10f4953ae691c0aa1c0892276bf84037a2a2d7ac9636df
+oid sha256:1c55fcb28b397a6b2791dd18f58cf8be5338c79cb200b03d537c935c294cabff
 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": 0.09324009324009325,
+  "epoch": 0.13986013986013987,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.6869,
       "step": 18
+    },
+    {
+      "epoch": 0.0979020979020979,
+      "grad_norm": 0.27399227023124695,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.6309,
+      "step": 21
+    },
+    {
+      "epoch": 0.11188811188811189,
+      "grad_norm": 0.2571362257003784,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.6143,
+      "step": 24
+    },
+    {
+      "epoch": 0.11188811188811189,
+      "eval_loss": 0.7011677026748657,
+      "eval_runtime": 24.8687,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 1.85,
+      "step": 24
+    },
+    {
+      "epoch": 0.1258741258741259,
+      "grad_norm": 0.29638007283210754,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.5993,
+      "step": 27
+    },
+    {
+      "epoch": 0.13986013986013987,
+      "grad_norm": 0.317417711019516,
+      "learning_rate": 0.0,
+      "loss": 0.7743,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6697946569506816.0,
+  "total_flos": 1.0373648955211776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null