Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0656072de66d47870b194263cb429f3415539654b838e0cc34f233cb42b64fa1
+oid sha256:333f01b7f3e0962d184cb2cb85440610ca1644c1bc58a05fdff87afb9e736712
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a06beea29c8db4ac02f7c6ab959239ab199b4390f86efe5e1c391838d1a35ea
+oid sha256:b7323c51b27fb2cd35b8237532a5f93d03508c162ca87ec168b2cc896324a6e6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f4d6bb4cc4e74c35f6a1360afa90540250a2e67956fb6d4004e4c1936bf578
+oid sha256:c657c5de501532a269e218c2c732a05c6d4ebc7fa4ff8f57ab61a6bd2711bd1c
 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": 0.0057338185025912446,
+  "epoch": 0.007351049362296468,
   "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": 0.9203,
       "step": 35
+    },
+    {
+      "epoch": 0.005880839489837174,
+      "grad_norm": 0.6683893799781799,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9582,
+      "step": 40
+    },
+    {
+      "epoch": 0.005880839489837174,
+      "eval_loss": 0.968965470790863,
+      "eval_runtime": 259.3011,
+      "eval_samples_per_second": 11.045,
+      "eval_steps_per_second": 5.523,
+      "step": 40
+    },
+    {
+      "epoch": 0.006615944426066821,
+      "grad_norm": 0.5291049480438232,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8854,
+      "step": 45
+    },
+    {
+      "epoch": 0.007351049362296468,
+      "grad_norm": 0.6103424429893494,
+      "learning_rate": 0.0,
+      "loss": 1.0441,
+      "step": 50
+    },
+    {
+      "epoch": 0.007351049362296468,
+      "eval_loss": 0.9678053855895996,
+      "eval_runtime": 259.4248,
+      "eval_samples_per_second": 11.04,
+      "eval_steps_per_second": 5.52,
+      "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": 1.0265081577209856e+16,
+  "total_flos": 1.3316862586650624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null