Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c238eed520e961bb6d0b95ac46e776ca2ef90ea482e04c6c16d135bec155b5
+oid sha256:4fb8bd350022ae6fe6b8e9d310b39a3730d14ff24717a7dea35e4179efe70c4a
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5bb2141c2cf99466b8e45330b10ab736c017dbea544812ad42fe12a5b3de820
+oid sha256:78d443e93799c8e3d5141650c340e3d9d2e93072c9fad8503191d6e64ea5c3c7
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.005980677810151817,
+  "epoch": 0.007667535654040792,
   "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": 10.3656,
       "step": 35
+    },
+    {
+      "epoch": 0.006134028523232633,
+      "grad_norm": 0.07906866073608398,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3739,
+      "step": 40
+    },
+    {
+      "epoch": 0.006134028523232633,
+      "eval_loss": 10.365830421447754,
+      "eval_runtime": 12.2379,
+      "eval_samples_per_second": 224.386,
+      "eval_steps_per_second": 112.193,
+      "step": 40
+    },
+    {
+      "epoch": 0.006900782088636712,
+      "grad_norm": 0.055559780448675156,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3649,
+      "step": 45
+    },
+    {
+      "epoch": 0.007667535654040792,
+      "grad_norm": 0.06306865811347961,
+      "learning_rate": 0.0,
+      "loss": 10.3684,
+      "step": 50
+    },
+    {
+      "epoch": 0.007667535654040792,
+      "eval_loss": 10.365800857543945,
+      "eval_runtime": 12.1527,
+      "eval_samples_per_second": 225.958,
+      "eval_steps_per_second": 112.979,
+      "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": 504305418240.0,
+  "total_flos": 646545408000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null