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:b19f95a899149c30c7ca235e82e850a68027ca43963c7d9310fc9cd55542bc80
+oid sha256:c3d7a01c5d98cd82c4bbc53058bcbf3f3192c550d39603208ffda7f291b62eef
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9448859e5fe0413b3db7a0108b94a27e9471243aedd0720584e091a226a09df1
+oid sha256:24d33a9a97170c8a1ef56f0e0986a276cf542c8fac661cb39fc86a7c070ee662
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997e7c1d312304d6db082e529a5743f300a2d03998e95102110b6455bc8caa27
+oid sha256:5ee1883642eddb3441f643eb93629dae66cf823ec18890ef543c95041a1339d1
 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": 0.004799114009721282,
+  "epoch": 0.006152710268873439,
   "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": 0.003,
       "step": 35
+    },
+    {
+      "epoch": 0.004922168215098751,
+      "grad_norm": 0.20382502675056458,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0033,
+      "step": 40
+    },
+    {
+      "epoch": 0.004922168215098751,
+      "eval_loss": 0.0027782993856817484,
+      "eval_runtime": 356.133,
+      "eval_samples_per_second": 9.609,
+      "eval_steps_per_second": 4.804,
+      "step": 40
+    },
+    {
+      "epoch": 0.005537439241986095,
+      "grad_norm": 0.0018468789057806134,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.002,
+      "step": 45
+    },
+    {
+      "epoch": 0.006152710268873439,
+      "grad_norm": 0.001503033796325326,
+      "learning_rate": 0.0,
+      "loss": 0.0015,
+      "step": 50
+    },
+    {
+      "epoch": 0.006152710268873439,
+      "eval_loss": 0.0016344909090548754,
+      "eval_runtime": 354.8835,
+      "eval_samples_per_second": 9.643,
+      "eval_steps_per_second": 4.821,
+      "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": 9412125225123840.0,
+  "total_flos": 1.208765320790016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null