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:b2c1ee116f611f726296717f21de81126e83247a8f2468b627fd502458362b35
+oid sha256:734939771792f475321ba36876a39c2e3939d477c92295c873505ad69d400c76
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4951c1973808446aa6d0c454e75e679e7ee385ec8148c373d541ed7b2fd2ee
+oid sha256:6e03c0a5af8337c737e88c8855f9eac63fea77290e6f3f1d427e52a81807c90a
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98afc215468fe49340fcc1e8d06e1a0e4426237e618a149fa37ce1204c3ce0e
+oid sha256:be8a0f455b08eb43e4bbf87a595cb3be3a091262695326052d0a7f317aaadfe1
 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": 0.00734982332155477,
+  "epoch": 0.009422850412249705,
   "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": 4.1496,
       "step": 35
+    },
+    {
+      "epoch": 0.007538280329799764,
+      "grad_norm": 2.438131332397461,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.7781,
+      "step": 40
+    },
+    {
+      "epoch": 0.007538280329799764,
+      "eval_loss": 0.9509055614471436,
+      "eval_runtime": 182.1245,
+      "eval_samples_per_second": 12.272,
+      "eval_steps_per_second": 6.139,
+      "step": 40
+    },
+    {
+      "epoch": 0.008480565371024734,
+      "grad_norm": 2.420114755630493,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.8176,
+      "step": 45
+    },
+    {
+      "epoch": 0.009422850412249705,
+      "grad_norm": 2.2501401901245117,
+      "learning_rate": 0.0,
+      "loss": 3.541,
+      "step": 50
+    },
+    {
+      "epoch": 0.009422850412249705,
+      "eval_loss": 0.9434703588485718,
+      "eval_runtime": 182.0373,
+      "eval_samples_per_second": 12.278,
+      "eval_steps_per_second": 6.142,
+      "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": 1.112594089771008e+16,
+  "total_flos": 1.4264026791936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null