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:c38ec445cc0909fe5f71079b8d8a18bf3a3a09a6d2e88cd1c13e6a53df801499
+oid sha256:568e910be7eac26c76822c0d181b3d026cac9cd062ce61e78e25732d18080354
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f876fb90de89fafa26b20dd3d658ed8eb48ded58ee03678f782ab129c0fd55be
+oid sha256:af0af13cf65086d2e591176f2f827c64017b8923c6bbbde21872ff371ffda275
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbfd95051ee0b329c6f0a314fa883d27a94f47705d1e9935da3b653adde21a9
+oid sha256:91360298823c841d73d3d56e96b4232d400d33cf08b8e3cd1117d9b15185a7fb
 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": 0.03822592501837785,
+  "epoch": 0.0490075961774075,
   "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": 0.9208,
       "step": 35
+    },
+    {
+      "epoch": 0.039206076941926,
+      "grad_norm": 0.5775378346443176,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7803,
+      "step": 40
+    },
+    {
+      "epoch": 0.039206076941926,
+      "eval_loss": 0.7931650280952454,
+      "eval_runtime": 26.2018,
+      "eval_samples_per_second": 16.411,
+      "eval_steps_per_second": 8.206,
+      "step": 40
+    },
+    {
+      "epoch": 0.04410683655966675,
+      "grad_norm": 0.8775522708892822,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8029,
+      "step": 45
+    },
+    {
+      "epoch": 0.0490075961774075,
+      "grad_norm": 0.6940584778785706,
+      "learning_rate": 0.0,
+      "loss": 0.7945,
+      "step": 50
+    },
+    {
+      "epoch": 0.0490075961774075,
+      "eval_loss": 0.7870774865150452,
+      "eval_runtime": 25.6678,
+      "eval_samples_per_second": 16.752,
+      "eval_steps_per_second": 8.376,
+      "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": 6449419587158016.0,
+  "total_flos": 8256900235788288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null