Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40dacf58f87babf9e587aefbea5d2913a98bf126ce3ce01d941c4b6cb0c4fc2c
+oid sha256:b7e8e4853442ba786d9b3b877049a6f117b4e17397391375c74de9df3532a2c6
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f20386d7efd462617444ea8994b042e72b9ce790e8be0e26220641157c52823
+oid sha256:11e7d3a16cc4497223ae15ca7d222e7f185544fc38e620dacf0e7a3949a16ea8
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4106140a90399a5aa18445704413059de472d755eeaec5f211b2d85edf5079f5
+oid sha256:4fccc43566068c1ab93ab0c228fdcf45b6f6fe60d4fd5c69ed6913b61b92c475
 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": 0.10351692103516921,
+  "epoch": 0.13271400132714,
   "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": 1.527,
       "step": 35
+    },
+    {
+      "epoch": 0.10617120106171202,
+      "grad_norm": 0.509976327419281,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4292,
+      "step": 40
+    },
+    {
+      "epoch": 0.10617120106171202,
+      "eval_loss": 1.392396330833435,
+      "eval_runtime": 6.3791,
+      "eval_samples_per_second": 24.925,
+      "eval_steps_per_second": 12.541,
+      "step": 40
+    },
+    {
+      "epoch": 0.11944260119442601,
+      "grad_norm": 0.5357011556625366,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3748,
+      "step": 45
+    },
+    {
+      "epoch": 0.13271400132714,
+      "grad_norm": 0.518661618232727,
+      "learning_rate": 0.0,
+      "loss": 1.3027,
+      "step": 50
+    },
+    {
+      "epoch": 0.13271400132714,
+      "eval_loss": 1.3914920091629028,
+      "eval_runtime": 6.2888,
+      "eval_samples_per_second": 25.283,
+      "eval_steps_per_second": 12.721,
+      "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": 685593861292032.0,
+  "total_flos": 877025913470976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null