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:d1bb8df2fdb0e04a8f8703a934bb03b07b6f0d0cf91a7b7d61fbc1b30329ba72
+oid sha256:e9892c7c5db6fc3f184a6ab79cf98dbfcd9cb666c8b4536daae5f83907e0a36b
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681ed008e251ac20e83778071c528d85dc8ed8ce8e2d2a4cbb5090f64aa80517
+oid sha256:6d9293fdc488b427cd4c0e38f4186ac7ffc6096cefa85ddf2569fa32701d04b8
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbba3e37f3da5eebd20241eda5b6317a6fa8037aef8c40511f6d82de78527891
+oid sha256:fada5e344878f23dd097d459027d43e07f5d3ae885d86019aeb3993928c4dea4
 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": 0.006687242798353909,
+  "epoch": 0.008573388203017833,
   "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": 15.0597,
       "step": 35
+    },
+    {
+      "epoch": 0.006858710562414266,
+      "grad_norm": 76.97616577148438,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 15.509,
+      "step": 40
+    },
+    {
+      "epoch": 0.006858710562414266,
+      "eval_loss": 3.654423236846924,
+      "eval_runtime": 43.4661,
+      "eval_samples_per_second": 56.504,
+      "eval_steps_per_second": 28.252,
+      "step": 40
+    },
+    {
+      "epoch": 0.007716049382716049,
+      "grad_norm": 61.45713806152344,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 15.0919,
+      "step": 45
+    },
+    {
+      "epoch": 0.008573388203017833,
+      "grad_norm": 93.86244201660156,
+      "learning_rate": 0.0,
+      "loss": 15.2501,
+      "step": 50
+    },
+    {
+      "epoch": 0.008573388203017833,
+      "eval_loss": 3.6407275199890137,
+      "eval_runtime": 43.3062,
+      "eval_samples_per_second": 56.712,
+      "eval_steps_per_second": 28.356,
+      "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": 342141406543872.0,
+  "total_flos": 438642828902400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null