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:a1807764b23bf76e80febd2d547f6e5b7fef15330de7075a424a87523966cce5
+oid sha256:d17494129621df81420d39f3d13f03464d2b6733fe4922a359874f0b77cd6504
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7437003c5bae6203de0788ac3c06312a707671f74bd830aae756c655a0e953a1
+oid sha256:5fcd3bd50223f944d1b53ee50ab6c6fd66b65376c893b9855fe17f95fb89925d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1725e7293373c9cc3826b6840eeb6bb1ffadc4138562c0593100d93aa07a3e1
+oid sha256:271b6597ba8732f9b0ece36439cc3fe1cadd7c5450056d2934a564aa2b733ed1
 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": 0.03956378392087243,
+  "epoch": 0.0507227998985544,
   "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": 4.4263,
       "step": 35
+    },
+    {
+      "epoch": 0.04057823991884352,
+      "grad_norm": 6.083137512207031,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.3746,
+      "step": 40
+    },
+    {
+      "epoch": 0.04057823991884352,
+      "eval_loss": 1.1202702522277832,
+      "eval_runtime": 73.8313,
+      "eval_samples_per_second": 5.621,
+      "eval_steps_per_second": 2.817,
+      "step": 40
+    },
+    {
+      "epoch": 0.04565051990869896,
+      "grad_norm": 7.438549995422363,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.2389,
+      "step": 45
+    },
+    {
+      "epoch": 0.0507227998985544,
+      "grad_norm": 6.926421165466309,
+      "learning_rate": 0.0,
+      "loss": 4.2256,
+      "step": 50
+    },
+    {
+      "epoch": 0.0507227998985544,
+      "eval_loss": 1.1173491477966309,
+      "eval_runtime": 73.9264,
+      "eval_samples_per_second": 5.614,
+      "eval_steps_per_second": 2.814,
+      "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": 1.358319084109824e+16,
+  "total_flos": 1.7351430880886784e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null