Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210ca9eea5ee7b1425ec6ad79a8d400a9a64a82b597bf7a055c93b27ebabcdcb
+oid sha256:e21f02bb850843b69d2507156c1a7ee63d6b8d121e741e44c31537c329c4ccee
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6497575efdaa2391e26be953dc3c2c782b0aa41791d55bf3a384df3a5b0ec14
+oid sha256:77c72150fb9ace7622bba00456093b5aa148a92b7ce19322a5021cdf7aa0c026
 size 63974

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": 0.012267044114177872,
+  "epoch": 0.015726979633561376,
   "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": 10.3722,
       "step": 35
+    },
+    {
+      "epoch": 0.0125815837068491,
+      "grad_norm": 0.025938261300325394,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3755,
+      "step": 40
+    },
+    {
+      "epoch": 0.0125815837068491,
+      "eval_loss": 10.373275756835938,
+      "eval_runtime": 6.9404,
+      "eval_samples_per_second": 192.928,
+      "eval_steps_per_second": 96.536,
+      "step": 40
+    },
+    {
+      "epoch": 0.014154281670205236,
+      "grad_norm": 0.01970183476805687,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3752,
+      "step": 45
+    },
+    {
+      "epoch": 0.015726979633561376,
+      "grad_norm": 0.027188651263713837,
+      "learning_rate": 0.0,
+      "loss": 10.3741,
+      "step": 50
+    },
+    {
+      "epoch": 0.015726979633561376,
+      "eval_loss": 10.373248100280762,
+      "eval_runtime": 6.9038,
+      "eval_samples_per_second": 193.952,
+      "eval_steps_per_second": 97.048,
+      "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": 601287229440.0,
+  "total_flos": 762923581440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null