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:d9a2730917299336fb3a4d698d24481e4647f00f1138cf1a9196dda8d751df1c
+oid sha256:28aa4db7c337dbb302722490c4c431b83ff695de656efcc9b572425b5675d7f5
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdf757e43856d1c8e7684b581f34ace92db671de94efd24c524469a82ece760
+oid sha256:f00e470eede2c6a33f2a8d97f925a3333c550d85d8eb10fac542f69bee5d35ae
 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": 0.009809469911337484,
+  "epoch": 0.012576243476073697,
   "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": 0.6052,
       "step": 35
+    },
+    {
+      "epoch": 0.010060994780858958,
+      "grad_norm": 0.3224814534187317,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6067,
+      "step": 40
+    },
+    {
+      "epoch": 0.010060994780858958,
+      "eval_loss": 0.5825388431549072,
+      "eval_runtime": 115.6224,
+      "eval_samples_per_second": 14.487,
+      "eval_steps_per_second": 7.248,
+      "step": 40
+    },
+    {
+      "epoch": 0.011318619128466326,
+      "grad_norm": 0.3185206651687622,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5621,
+      "step": 45
+    },
+    {
+      "epoch": 0.012576243476073697,
+      "grad_norm": 0.3230144679546356,
+      "learning_rate": 0.0,
+      "loss": 0.5723,
+      "step": 50
+    },
+    {
+      "epoch": 0.012576243476073697,
+      "eval_loss": 0.580285370349884,
+      "eval_runtime": 115.6675,
+      "eval_samples_per_second": 14.481,
+      "eval_steps_per_second": 7.245,
+      "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