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:df2f5e4234a5d82fc6363febb18f82cb8ad0a8406c7471f11ec652a7de92190f
+oid sha256:38e906e1a82519e09edc5ba4fb537a934ee6a6d78e7a18dcbf80fc317dc166c6
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae059cc95149f6958d58b2a33881ea11c42dc2a15e92bed9a21e1f62f40a42d8
+oid sha256:34578dfb7b4e698738a64b689c3c04b8043589b4f9514782475630cb23612b74
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
+oid sha256:fdedc6314c9f75a198e58bac1038c3adc8fc2a5f73e82a6a71a371fdac27e199
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0480295566502463,
+  "epoch": 0.06157635467980296,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 620.864,
       "eval_steps_per_second": 77.622,
       "step": 30
+    },
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": 0.4270021617412567,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 166.0356,
+      "step": 40
+    },
+    {
+      "epoch": 0.04926108374384237,
+      "eval_loss": 10.377579689025879,
+      "eval_runtime": 8.7993,
+      "eval_samples_per_second": 621.757,
+      "eval_steps_per_second": 77.734,
+      "step": 40
+    },
+    {
+      "epoch": 0.06157635467980296,
+      "grad_norm": 0.40548381209373474,
+      "learning_rate": 0.0,
+      "loss": 166.0338,
+      "step": 50
+    },
+    {
+      "epoch": 0.06157635467980296,
+      "eval_loss": 10.37756061553955,
+      "eval_runtime": 8.898,
+      "eval_samples_per_second": 614.858,
+      "eval_steps_per_second": 76.871,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 16168833515520.0,
+  "total_flos": 20737170604032.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null