Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189466a215f15d663b8d82d72c933eb9f21c8f09d909193fabc1e53f0cc07ac6
+oid sha256:c339d3a1e8e1a901d5123afad022e3d80690dd6689409e5ced54e56123aea575
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e91dc90f3251d1b3ddbbd52a76c9cedb1cb37b9ed070785c0e5561178a4396a9
+oid sha256:37e0970d4cbd1c0909c75124d259d2a3679fa6867295682c8aa5b12a9c274093
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48387a63bde87dc1fe3c98a1e6ea341819380eedccc04e7d52e113dc6afcad0
+oid sha256:75219908cab893389539c52964b82b96272ed58e4d8f4524d7186c2f76979023
 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": 0.01606425702811245,
+  "epoch": 0.020595201318092886,
   "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": 0.182,
       "step": 35
+    },
+    {
+      "epoch": 0.016476161054474307,
+      "grad_norm": 1.5621275901794434,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2306,
+      "step": 40
+    },
+    {
+      "epoch": 0.016476161054474307,
+      "eval_loss": 0.05220469459891319,
+      "eval_runtime": 164.0723,
+      "eval_samples_per_second": 6.235,
+      "eval_steps_per_second": 3.121,
+      "step": 40
+    },
+    {
+      "epoch": 0.018535681186283594,
+      "grad_norm": 1.3377180099487305,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1967,
+      "step": 45
+    },
+    {
+      "epoch": 0.020595201318092886,
+      "grad_norm": 0.8603113889694214,
+      "learning_rate": 0.0,
+      "loss": 0.1678,
+      "step": 50
+    },
+    {
+      "epoch": 0.020595201318092886,
+      "eval_loss": 0.05157728120684624,
+      "eval_runtime": 163.8604,
+      "eval_samples_per_second": 6.243,
+      "eval_steps_per_second": 3.125,
+      "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": 1.2186428016427008e+16,
+  "total_flos": 1.5517969488543744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null