Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6df4a5d55ecc8c3adcbadcb2349717a837821cb6cec4ad04b157f5f626e67e
+oid sha256:81488fba895f6284bdb8c697b5a1f55b02221b8f951b9c447cc7238891da5638
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4fa3cc6a191c31ba5233bd2e0cf17bcf9f5c85eaeed8bbd22acf9442cfcf9d
+oid sha256:3b748ac7209212d66d230923c32217a52f5f90567fb227ab090660c131b8512e
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7458535a598eff19c9f56e9c654a6f3d6525c5476aca0e0ac50d69d1e2572b95
+oid sha256:91fdccfdcfe29a8b068ea427c402a7d6f2b96ff5e922e8bf946ff7dd3f6ae037
 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": 0.0024122840928420108,
+  "epoch": 0.003092671913900014,
   "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": 2.3391,
       "step": 35
+    },
+    {
+      "epoch": 0.002474137531120011,
+      "grad_norm": 3.2438924312591553,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2421,
+      "step": 40
+    },
+    {
+      "epoch": 0.002474137531120011,
+      "eval_loss": 2.263791799545288,
+      "eval_runtime": 969.6415,
+      "eval_samples_per_second": 7.021,
+      "eval_steps_per_second": 3.511,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027834047225100125,
+      "grad_norm": 3.466553211212158,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.28,
+      "step": 45
+    },
+    {
+      "epoch": 0.003092671913900014,
+      "grad_norm": 3.2413833141326904,
+      "learning_rate": 0.0,
+      "loss": 2.2653,
+      "step": 50
+    },
+    {
+      "epoch": 0.003092671913900014,
+      "eval_loss": 2.259215831756592,
+      "eval_runtime": 970.5443,
+      "eval_samples_per_second": 7.015,
+      "eval_steps_per_second": 3.507,
+      "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": 1.395096733876224e+16,
+  "total_flos": 1.772537288589312e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null