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:f7993f88f7251226c437872b38bacf0801d0125b0634ca83caafa4f54c9bb919
+oid sha256:7ed9739a2decd73aa553b2fbb7190b62d45fe1e3525227d7cd49398557692eca
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0331c090d5012246a3c1d051654f29d1c63adb1e659c8db8199d80c62ea81e7e
+oid sha256:b0cea767900058dd1661d5d2b07a8fecc9992a5463d38fb3f2d15b1ddd931f00
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1039e96a4ec12087edaa8ab2d18eba7c359b91687856664d415beaa872acc5
+oid sha256:19a5c3c72e60ff810542ede55f7b859d77b4dd5935294cc01a9f9bf4d605e2e8
 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": 0.047619047619047616,
+  "epoch": 0.06105006105006105,
   "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": 11.9316,
       "step": 35
+    },
+    {
+      "epoch": 0.04884004884004884,
+      "grad_norm": 0.014119105413556099,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9326,
+      "step": 40
+    },
+    {
+      "epoch": 0.04884004884004884,
+      "eval_loss": 11.934100151062012,
+      "eval_runtime": 6.0973,
+      "eval_samples_per_second": 56.582,
+      "eval_steps_per_second": 28.373,
+      "step": 40
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "grad_norm": 0.00930514745414257,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9322,
+      "step": 45
+    },
+    {
+      "epoch": 0.06105006105006105,
+      "grad_norm": 0.010311778634786606,
+      "learning_rate": 0.0,
+      "loss": 11.9343,
+      "step": 50
+    },
+    {
+      "epoch": 0.06105006105006105,
+      "eval_loss": 11.934097290039062,
+      "eval_runtime": 6.0342,
+      "eval_samples_per_second": 57.174,
+      "eval_steps_per_second": 28.67,
+      "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": 4608294912.0,
+  "total_flos": 5908070400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null