Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28fd10a7e2676ea0bd4248b7a979f0e23508d4313150482c0d3211f5ce5377a0
+oid sha256:2b70f2493beee8bd078f5b1b5b2c77f3440019e0687ab2208adf099b4faf3b3a
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a6debf3eedf44828e3d123bcacb605912e00dc78d8a4e14bb28259b8633cb0
+oid sha256:776391f97e1edf02aa789b96c16e6aa0332bd2097ac77de84204d8361688f43e
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c28d8d1307642efe947fe98f6f7e242467882f7ac03aafe16fdbd065e0dc84
+oid sha256:99d7e23ee04eea30ef5c1f7d79cd2d4c8c90396a4c48082de31095fad6fe6315
 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": 0.055201698513800426,
+  "epoch": 0.07077140835102619,
   "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": 1.4361,
       "step": 35
+    },
+    {
+      "epoch": 0.056617126680820945,
+      "grad_norm": 0.47925546765327454,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3996,
+      "step": 40
+    },
+    {
+      "epoch": 0.056617126680820945,
+      "eval_loss": 1.4192451238632202,
+      "eval_runtime": 20.92,
+      "eval_samples_per_second": 14.245,
+      "eval_steps_per_second": 7.122,
+      "step": 40
+    },
+    {
+      "epoch": 0.06369426751592357,
+      "grad_norm": 0.4749594032764435,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4199,
+      "step": 45
+    },
+    {
+      "epoch": 0.07077140835102619,
+      "grad_norm": 0.4592364430427551,
+      "learning_rate": 0.0,
+      "loss": 1.3922,
+      "step": 50
+    },
+    {
+      "epoch": 0.07077140835102619,
+      "eval_loss": 1.416690707206726,
+      "eval_runtime": 20.8865,
+      "eval_samples_per_second": 14.268,
+      "eval_steps_per_second": 7.134,
+      "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": 5426639756328960.0,
+  "total_flos": 6957230456832000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null