Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b942157819bda8dc8c32c7297040f1db3d8afa75bb952ecb09741b3bc9464cf
+oid sha256:da84791aa290bdc526c7f38306c4b46e485786d577dec47fd82b00bec0063541
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ea78a6d5eb74a420c09d767d16719ee7ad97048fc6f078bd5e72a37bb2736b
+oid sha256:6588ef4e42aec1cf29087bb0aa88ad7881b65b86d2bef8b7cc342a2bc5a80582
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1db1ef9e1011c0eeedbf37aea4e8a667ddd929bb523dd8dfbcf12a11e586e6a
+oid sha256:6cf15000f9ed57d18af02e2199a203d3e25437f95b930f188d458be18ee6f08e
 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": 0.156312625250501,
+  "epoch": 0.20040080160320642,
   "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": 1.1218,
       "step": 35
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.9221222996711731,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0054,
+      "step": 40
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "eval_loss": 1.0704418420791626,
+      "eval_runtime": 6.0328,
+      "eval_samples_per_second": 17.405,
+      "eval_steps_per_second": 8.785,
+      "step": 40
+    },
+    {
+      "epoch": 0.18036072144288579,
+      "grad_norm": 1.3219908475875854,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1622,
+      "step": 45
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 1.2495200634002686,
+      "learning_rate": 0.0,
+      "loss": 1.2338,
+      "step": 50
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "eval_loss": 1.0661646127700806,
+      "eval_runtime": 5.9793,
+      "eval_samples_per_second": 17.561,
+      "eval_steps_per_second": 8.864,
+      "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": 2814497311948800.0,
+  "total_flos": 3658846505533440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null