Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a93b45fee8f786d8c9326dc8e2850af2d07685aa6ba814373c5eae19b4993a
+oid sha256:e16ade673c8f5f07db21eeb2df1bd6b8c3a313339f2a0dcd7c580c20a77b37ae
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a5ecd073af25c8d76e8ac0728fa1ae10ace79e3351a7cb599c45e6651c181c2
+oid sha256:4138935a2a704aa369f9ea5f68a24396b938d0f82bd6e275e3ff8915e5baedcf
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386ed867f47190adadf85344b4fecfccaff8d69044553dcdcb38251ec9a7e419
+oid sha256:31bdb696b574973895ff2b747377d3ffb8c746f630155b864dae9e45560ab2da
 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": 0.0006330115524608325,
+  "epoch": 0.0008115532723856826,
   "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": 1.0013,
       "step": 35
+    },
+    {
+      "epoch": 0.000649242617908546,
+      "grad_norm": 0.41298559308052063,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1422,
+      "step": 40
+    },
+    {
+      "epoch": 0.000649242617908546,
+      "eval_loss": 1.1447937488555908,
+      "eval_runtime": 1383.4283,
+      "eval_samples_per_second": 18.752,
+      "eval_steps_per_second": 9.376,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007303979451471144,
+      "grad_norm": 0.25260743498802185,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1584,
+      "step": 45
+    },
+    {
+      "epoch": 0.0008115532723856826,
+      "grad_norm": 0.2446519285440445,
+      "learning_rate": 0.0,
+      "loss": 0.9419,
+      "step": 50
+    },
+    {
+      "epoch": 0.0008115532723856826,
+      "eval_loss": 1.1432709693908691,
+      "eval_runtime": 1384.4885,
+      "eval_samples_per_second": 18.738,
+      "eval_steps_per_second": 9.369,
+      "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": 4981795639787520.0,
+  "total_flos": 6396379586887680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null