Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ecbce72d3f6a26bdd43a7604972d94d4ec8f12a93e5cc059fc56628fa594974
+oid sha256:59492bebd2eceb8b1d2da61b266c6752a76da02ba5e9a657e55775de493aee63
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0696615033b7aba4e959bbf7081f1b4f00c92b16e9577ba43a156a4b7d2c2076
+oid sha256:650a9d5d2dc081c41299c9b499f796466e6a301672de70c0192d4fa7cea950f3
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c0c2adc975262f2df4c486df9e442410842d91213e05f1917c8f382c736c6cd
+oid sha256:a69e099fc1e9e37855af4ec955157cfddb348fee96f499abcd59bd5a30d159a7
 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": 0.009437386569872959,
+  "epoch": 0.012099213551119177,
   "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": 5.9487,
       "step": 35
+    },
+    {
+      "epoch": 0.009679370840895343,
+      "grad_norm": 4.990902900695801,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.1513,
+      "step": 40
+    },
+    {
+      "epoch": 0.009679370840895343,
+      "eval_loss": 1.4963432550430298,
+      "eval_runtime": 65.6257,
+      "eval_samples_per_second": 26.514,
+      "eval_steps_per_second": 13.257,
+      "step": 40
+    },
+    {
+      "epoch": 0.010889292196007259,
+      "grad_norm": 4.028073310852051,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.4428,
+      "step": 45
+    },
+    {
+      "epoch": 0.012099213551119177,
+      "grad_norm": 4.228430271148682,
+      "learning_rate": 0.0,
+      "loss": 5.9249,
+      "step": 50
+    },
+    {
+      "epoch": 0.012099213551119177,
+      "eval_loss": 1.4931994676589966,
+      "eval_runtime": 65.4925,
+      "eval_samples_per_second": 26.568,
+      "eval_steps_per_second": 13.284,
+      "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": 1492861845504000.0,
+  "total_flos": 1910863162245120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null