Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6065a88c721f9b65ba124ab1da58630b66dcc4eaf91111902879302cdcc120fc
+oid sha256:707a5fd3802e9753483e41ae21be791bb5a900bbb71a65254753eb9d100fd7a8
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0709cbafc73b6dbad8c4563e817a21d1fc40fd78b42f600e4fc7bf85278568f6
+oid sha256:aba75d9ad5c459625c627492414eba5d45a37ce1f961ef8d6bc0ea306e1a63a5
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
+oid sha256:fdedc6314c9f75a198e58bac1038c3adc8fc2a5f73e82a6a71a371fdac27e199
 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": 0.029635258358662615,
+  "epoch": 0.037993920972644375,
   "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": 7.9935,
       "step": 35
+    },
+    {
+      "epoch": 0.030395136778115502,
+      "grad_norm": 2.944188356399536,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.1376,
+      "step": 40
+    },
+    {
+      "epoch": 0.030395136778115502,
+      "eval_loss": 8.18637752532959,
+      "eval_runtime": 7.9085,
+      "eval_samples_per_second": 70.177,
+      "eval_steps_per_second": 35.152,
+      "step": 40
+    },
+    {
+      "epoch": 0.03419452887537994,
+      "grad_norm": 2.2056612968444824,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.1537,
+      "step": 45
+    },
+    {
+      "epoch": 0.037993920972644375,
+      "grad_norm": 2.681415319442749,
+      "learning_rate": 0.0,
+      "loss": 8.181,
+      "step": 50
+    },
+    {
+      "epoch": 0.037993920972644375,
+      "eval_loss": 8.177650451660156,
+      "eval_runtime": 7.6687,
+      "eval_samples_per_second": 72.372,
+      "eval_steps_per_second": 36.251,
+      "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": 4867721920512.0,
+  "total_flos": 6178892808192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null