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:a543ac9dc81d2b08ab1f285c4b0ddce8742ff4b5ebb4c9c343f0012398fa1c2a
+oid sha256:a2116a1a4e3b21bc5f77c2fed78347407beea6b5694bfd07c13eb0af8aa00ce9
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4c22cc0834c6e4466b679c38b3bb38c5014e13a6c6b169c1c6a31fcf531643
+oid sha256:2976a35a01e37b3ca30f55286b7e39c2b42bb742cfa281a3f36b876f030215ed
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b074dd7788a357c83e204bf182c8046b1383eb0a9ff02da64031fe764375a72b
+oid sha256:7f60ef2192d3634423e0b411609bc5f9c4f5e662023d73fd1a3f0d934e38f842
 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": 0.006192687864713589,
+  "epoch": 0.007939343416299472,
   "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": 1.1656,
       "step": 35
+    },
+    {
+      "epoch": 0.006351474733039578,
+      "grad_norm": 12.236564636230469,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8458,
+      "step": 40
+    },
+    {
+      "epoch": 0.006351474733039578,
+      "eval_loss": 0.24062801897525787,
+      "eval_runtime": 281.0159,
+      "eval_samples_per_second": 9.437,
+      "eval_steps_per_second": 4.719,
+      "step": 40
+    },
+    {
+      "epoch": 0.007145409074669525,
+      "grad_norm": 22.780681610107422,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8862,
+      "step": 45
+    },
+    {
+      "epoch": 0.007939343416299472,
+      "grad_norm": 17.021995544433594,
+      "learning_rate": 0.0,
+      "loss": 0.9225,
+      "step": 50
+    },
+    {
+      "epoch": 0.007939343416299472,
+      "eval_loss": 0.21980232000350952,
+      "eval_runtime": 281.0667,
+      "eval_samples_per_second": 9.435,
+      "eval_steps_per_second": 4.718,
+      "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": 1.2161961328902144e+16,
+  "total_flos": 1.571260104572928e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null