Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ba0086f03275f15146314cf8df1696afc732e95310b09fd9ab6322c0e175df
+oid sha256:d2b4d71f88a1c6dec85963bb1d58fa485e7835123b7ee5c093b5a88ff13760fe
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8e1bf0a4b7dbfddbd8c50cdb1066229dc31c2d35e3410f1613db7b2247bb06
+oid sha256:ea6bd7e43c6f9f92c7c7385538b17fa7531856b71f1a1ebf0dc1f1569b4eb039
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b826dd45cf5d494051837afd81ae5b880dac778302930e6748ae59820d1861
+oid sha256:6b67a8679a66f5d780affa53fa7107f5c9cd2d71d1c4ddbe218914b63028d16b
 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": 0.05662431941923775,
+  "epoch": 0.07259528130671507,
   "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": 1.8508,
       "step": 35
+    },
+    {
+      "epoch": 0.05807622504537205,
+      "grad_norm": 2.951900005340576,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5987,
+      "step": 40
+    },
+    {
+      "epoch": 0.05807622504537205,
+      "eval_loss": 1.776922345161438,
+      "eval_runtime": 35.2749,
+      "eval_samples_per_second": 8.221,
+      "eval_steps_per_second": 4.111,
+      "step": 40
+    },
+    {
+      "epoch": 0.06533575317604355,
+      "grad_norm": 2.383507251739502,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7098,
+      "step": 45
+    },
+    {
+      "epoch": 0.07259528130671507,
+      "grad_norm": 2.7600584030151367,
+      "learning_rate": 0.0,
+      "loss": 1.7854,
+      "step": 50
+    },
+    {
+      "epoch": 0.07259528130671507,
+      "eval_loss": 1.769264578819275,
+      "eval_runtime": 35.2817,
+      "eval_samples_per_second": 8.22,
+      "eval_steps_per_second": 4.11,
+      "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": 1.4010449179705344e+16,
+  "total_flos": 1.803325141942272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null