Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24369009a46fb122f84f816d6221895337242516c17073ae12d127d85138a3b5
+oid sha256:4516049e17f41a15b4829536d25def8f22fc78575118c3cefacd520a4fc781fd
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a3245a3a4b9f264bb41cada7474fb83398dfd4c1d3672c92cae926d19c828c4
+oid sha256:a7e0d0d9547202b50e9a8d096491eefcc9ee2a554cf3725b431068efffe37c47
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee089b8eda3d2f03579660229909140f9bb3bc7af0a9129bb3775da6328a203
+oid sha256:6beb92e82d89b74efdd456fb9bf2b41610797ca90b007f020dc4fb8145708801
 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": 0.0029412319236788026,
+  "epoch": 0.003770810158562567,
   "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": 0.569,
       "step": 35
+    },
+    {
+      "epoch": 0.0030166481268500537,
+      "grad_norm": 1.476067066192627,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5314,
+      "step": 40
+    },
+    {
+      "epoch": 0.0030166481268500537,
+      "eval_loss": 0.5157779455184937,
+      "eval_runtime": 664.516,
+      "eval_samples_per_second": 8.403,
+      "eval_steps_per_second": 4.202,
+      "step": 40
+    },
+    {
+      "epoch": 0.0033937291427063106,
+      "grad_norm": 1.6906317472457886,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4455,
+      "step": 45
+    },
+    {
+      "epoch": 0.003770810158562567,
+      "grad_norm": 1.3468632698059082,
+      "learning_rate": 0.0,
+      "loss": 0.4905,
+      "step": 50
+    },
+    {
+      "epoch": 0.003770810158562567,
+      "eval_loss": 0.5104564428329468,
+      "eval_runtime": 667.6626,
+      "eval_samples_per_second": 8.364,
+      "eval_steps_per_second": 4.182,
+      "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": 1.3964210073501696e+16,
+  "total_flos": 1.780205588840448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null