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:cc4d4deb49aa8333893ed3fae6cbf6ac86fb0da41b737e45e7c73fd504f59138
+oid sha256:827015cb77fa0bf94d7a853fd2eb0392ca7cd59fa6bfac277a6ea82bda07f7f6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7adac44b78985ede53d4e11c45ccacfee7eda00a62fe3f87d2f7ee1d274bf1ee
+oid sha256:0015ffd0355302af67692ec2226b2ea0ea57772dec9fb0b4612a5c50f9a9be97
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df4452b6ca42236c2bcd52b5df9f8e63ebc61625217e8356d9a4e2cc7327676
+oid sha256:89b38edf16e00970afb593efd87e2a583d3afe78398f0ae48ffeddd0350e5bc3
 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": 0.01450623023991073,
+  "epoch": 0.018597731076808628,
   "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": 5.7182,
       "step": 35
+    },
+    {
+      "epoch": 0.014878184861446904,
+      "grad_norm": 32.54092025756836,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.8618,
+      "step": 40
+    },
+    {
+      "epoch": 0.014878184861446904,
+      "eval_loss": 1.6697747707366943,
+      "eval_runtime": 108.181,
+      "eval_samples_per_second": 10.464,
+      "eval_steps_per_second": 5.232,
+      "step": 40
+    },
+    {
+      "epoch": 0.016737957969127765,
+      "grad_norm": 23.594846725463867,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.3459,
+      "step": 45
+    },
+    {
+      "epoch": 0.018597731076808628,
+      "grad_norm": 24.871923446655273,
+      "learning_rate": 0.0,
+      "loss": 6.6075,
+      "step": 50
+    },
+    {
+      "epoch": 0.018597731076808628,
+      "eval_loss": 1.6488146781921387,
+      "eval_runtime": 108.2346,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 5.229,
+      "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": 7273587966738432.0,
+  "total_flos": 9376794125795328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null