Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e6ddaf11da8a9da6f7c907ad6f64b6354fb52b72e0f14141127c5bbdd92717
+oid sha256:2f34b85fa1e719916212998c01e25fdcbdb6c6f49e275a456a0dac8edcb90c7e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e79cac7be291f93ad869b2e3d82925b2e242254e3b6096c0a11e7e8ed4fb78
+oid sha256:a5a2d669783a612fd0afa501c5300dab4569147e9eff1f7710478b3894c2fe31
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4354521c2092ad7a21b56230fbe72d6846ab1c72092965f7eb5cebfbbf30a51
+oid sha256:bbeb344358c5b2fc3427ec40a46912a0f05a8b64159d1e85af690dec1f30ebc6
 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": 0.0012083936884668119,
+  "epoch": 0.0015492226775215535,
   "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": 0.9954,
       "step": 35
+    },
+    {
+      "epoch": 0.0012393781420172428,
+      "grad_norm": 0.26686355471611023,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8849,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012393781420172428,
+      "eval_loss": 0.9477787017822266,
+      "eval_runtime": 1466.3979,
+      "eval_samples_per_second": 9.268,
+      "eval_steps_per_second": 4.634,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013943004097693981,
+      "grad_norm": 0.26942411065101624,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9229,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015492226775215535,
+      "grad_norm": 0.3074963688850403,
+      "learning_rate": 0.0,
+      "loss": 0.9729,
+      "step": 50
+    },
+    {
+      "epoch": 0.0015492226775215535,
+      "eval_loss": 0.9452804327011108,
+      "eval_runtime": 1463.3929,
+      "eval_samples_per_second": 9.287,
+      "eval_steps_per_second": 4.643,
+      "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": 1.268823650992128e+16,
+  "total_flos": 1.631344694132736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null