Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ff63f8a8436c44ba862a6e257e1061f307bd88d8cee6479318c8957cc6369a
+oid sha256:850f38da525154b02b0c50b629dd972569204f348068f444fffc41d033041586
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d6355d60235a2d3b8b12b81b03c7308bd9c186aac1fab2ee7e1501697c7b3cc
+oid sha256:19a250e2ded2200a5984b930918517e26e606a9639ec31f32bfcc9e41b85565e
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18ca68f3c7f5320b8c12bfaa341eeb9926d2957be2b572aa4906c3b06ad3b29e
+oid sha256:90d9942664417fe4794df2072e38ccccc54f82bea9f304a83f0f0b65780ec94d
 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": 0.0009074357378441421,
+  "epoch": 0.0011633791510822335,
   "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": 2.5334,
       "step": 35
+    },
+    {
+      "epoch": 0.0009307033208657868,
+      "grad_norm": 3.685447931289673,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.5459,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009307033208657868,
+      "eval_loss": 2.1419756412506104,
+      "eval_runtime": 1106.9783,
+      "eval_samples_per_second": 16.348,
+      "eval_steps_per_second": 8.175,
+      "step": 40
+    },
+    {
+      "epoch": 0.0010470412359740102,
+      "grad_norm": 2.698432683944702,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.04,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011633791510822335,
+      "grad_norm": 3.505143404006958,
+      "learning_rate": 0.0,
+      "loss": 1.8153,
+      "step": 50
+    },
+    {
+      "epoch": 0.0011633791510822335,
+      "eval_loss": 2.1304948329925537,
+      "eval_runtime": 1105.9958,
+      "eval_samples_per_second": 16.363,
+      "eval_steps_per_second": 8.182,
+      "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": 6632487266549760.0,
+  "total_flos": 8486288055336960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null