Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb2784033ccd88befe32574c3c7881d1312ef0e0c27644a9f4a0e52fe42d021
+oid sha256:87259d88b72451596adec15ee1f2f4471ba5b07072f49b781d5efc3cd87816c1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2053596bc7d8b06e5204f6060335d19aa57eec55cd5d35241ad9880af4a5e47
+oid sha256:44e054abbb17ea828d90457221e604a645e33455abf66169006765f87c6b3136
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876b7dc2581f63355a670dba66a29209f3957c2f8937f10358860aabf2b1554e
+oid sha256:e8aec46d98bf5a217207cd5fe499aabae4365d63931e807380a3663afe4724f8
 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": 0.001247032302932924,
+  "epoch": 0.001598759362734518,
   "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": 4.2171,
       "step": 35
+    },
+    {
+      "epoch": 0.0012790074901876144,
+      "grad_norm": 79.1338882446289,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.1407,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012790074901876144,
+      "eval_loss": 1.0463610887527466,
+      "eval_runtime": 1112.7704,
+      "eval_samples_per_second": 11.834,
+      "eval_steps_per_second": 5.918,
+      "step": 40
+    },
+    {
+      "epoch": 0.0014388834264610663,
+      "grad_norm": 35.42249298095703,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.6337,
+      "step": 45
+    },
+    {
+      "epoch": 0.001598759362734518,
+      "grad_norm": 36.018646240234375,
+      "learning_rate": 0.0,
+      "loss": 4.7524,
+      "step": 50
+    },
+    {
+      "epoch": 0.001598759362734518,
+      "eval_loss": 1.0200668573379517,
+      "eval_runtime": 1113.115,
+      "eval_samples_per_second": 11.831,
+      "eval_steps_per_second": 5.916,
+      "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": 9380919408328704.0,
+  "total_flos": 1.2405608376434688e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null