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:af7228f2f7f7c0bd02e410e8792a3a9a248b5c3b30105ff92560843fb0256ac6
+oid sha256:73d733fd92b0a74857e23ebb5e3d55887433356054b7da6fb1ea90aa48a9170a
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37c6fadc733fb68c680e6428db145c1fcbe10677c173fc250bad8daa59298145
+oid sha256:0292a8456d6f7677404cdaee9bac9654b6a6f32ea3e709f2a12c9df757130773
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1542c12b1c38878d0bf713af077c56cb60e0f19147c5c8f6f20fb0942baee8b8
+oid sha256:b72cf74d489e5841ae4de8ec493255d408573406e6792be6bc5adc1ae2332f80
 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": 0.09955328653477984,
+  "epoch": 0.1276324186343331,
   "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": 2.6019,
       "step": 35
+    },
+    {
+      "epoch": 0.1021059349074665,
+      "grad_norm": 0.6996490359306335,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.7452,
+      "step": 40
+    },
+    {
+      "epoch": 0.1021059349074665,
+      "eval_loss": 2.7188756465911865,
+      "eval_runtime": 9.4298,
+      "eval_samples_per_second": 17.498,
+      "eval_steps_per_second": 8.802,
+      "step": 40
+    },
+    {
+      "epoch": 0.1148691767708998,
+      "grad_norm": 0.6797233819961548,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.7534,
+      "step": 45
+    },
+    {
+      "epoch": 0.1276324186343331,
+      "grad_norm": 0.6642326712608337,
+      "learning_rate": 0.0,
+      "loss": 2.6603,
+      "step": 50
+    },
+    {
+      "epoch": 0.1276324186343331,
+      "eval_loss": 2.717184543609619,
+      "eval_runtime": 9.3197,
+      "eval_samples_per_second": 17.704,
+      "eval_steps_per_second": 8.906,
+      "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": 3722118294405120.0,
+  "total_flos": 4713523634503680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null