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:b13c203d4db1c2b0b1f28feb189626b182195af12e4fcdadbdf4f70f9a68ac56
+oid sha256:000c4d12a548ca4e8a4a980ce7f2abd762fb49b6e17d8f6eab3e1c89ef46bb92
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b67102e35457945c1fe28a47762ec97ae2540e8d2bbe0995d7241841cb04d89f
+oid sha256:4db145cd6c4064163ff30497f2c1e5f76654c4021faeb62b0aa3053ecc359984
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89125b381bd706e47d0969ca57bde232385b184bb6fee985c4b095b282bae7af
+oid sha256:3f04944917c15f265951392f0ad036c49b2e1d3572ae924179abc0eb1dc0ce1c
 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": 0.02759596674332213,
+  "epoch": 0.03537944454272068,
   "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": 0.2384,
       "step": 35
+    },
+    {
+      "epoch": 0.028303555634176542,
+      "grad_norm": 12.801621437072754,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2437,
+      "step": 40
+    },
+    {
+      "epoch": 0.028303555634176542,
+      "eval_loss": 0.1584031879901886,
+      "eval_runtime": 48.0401,
+      "eval_samples_per_second": 12.385,
+      "eval_steps_per_second": 6.203,
+      "step": 40
+    },
+    {
+      "epoch": 0.03184150008844861,
+      "grad_norm": 5.449904441833496,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1927,
+      "step": 45
+    },
+    {
+      "epoch": 0.03537944454272068,
+      "grad_norm": 7.277150630950928,
+      "learning_rate": 0.0,
+      "loss": 0.2981,
+      "step": 50
+    },
+    {
+      "epoch": 0.03537944454272068,
+      "eval_loss": 0.13875603675842285,
+      "eval_runtime": 47.7713,
+      "eval_samples_per_second": 12.455,
+      "eval_steps_per_second": 6.238,
+      "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": 7453256523448320.0,
+  "total_flos": 9555457081344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null