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:e4200c4461060a522df9d4b285543c59d6ad0ad62115b506d9eb517eedf1b70b
+oid sha256:f4a3380d29f4943e4f2f1b674ce1217082f60255a65077f10043a7783b71668f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1511b37df79bd00f1324c15f9d45123e0982fd6758b2deeea6dac424ed87924
+oid sha256:0ea9b5dfcafefd936d1f3daf2d8c781500efd0d2ec33e1344a378e604b73e66e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 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": 0.0007606008746910059,
+  "epoch": 0.0009751293265269306,
   "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": 7.1474,
       "step": 35
+    },
+    {
+      "epoch": 0.0007801034612215446,
+      "grad_norm": 21.884143829345703,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.7595,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007801034612215446,
+      "eval_loss": 1.8448659181594849,
+      "eval_runtime": 1361.7391,
+      "eval_samples_per_second": 15.855,
+      "eval_steps_per_second": 7.927,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008776163938742376,
+      "grad_norm": 20.621267318725586,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.2005,
+      "step": 45
+    },
+    {
+      "epoch": 0.0009751293265269306,
+      "grad_norm": 20.958507537841797,
+      "learning_rate": 0.0,
+      "loss": 7.2268,
+      "step": 50
+    },
+    {
+      "epoch": 0.0009751293265269306,
+      "eval_loss": 1.8370400667190552,
+      "eval_runtime": 1357.8052,
+      "eval_samples_per_second": 15.901,
+      "eval_steps_per_second": 7.95,
+      "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": 6835412165197824.0,
+  "total_flos": 8763348929740800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null