Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8286dfe5a3504b65ceff979114d71cc10dd4ab5134cdbf9d5046d7eda7bffb
+oid sha256:bb912c37e2654177ac5d55d8df5393e9bdaf6b90743a23383af8dcd7fed03bf2
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:758a22879752f14721adc565e6b1599549d2a758d2d2cc99fada22c42e5e9d7b
+oid sha256:7bf866637723d12705049ae2bb77ca0b5cbd8a042bb4434a5f483987fb693f9b
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83351b88c80b2a400d087eab433088b953ead1a486a42fbe821f2fdbcd222dde
+oid sha256:d1a14eaf4dd0c35ab5c5558d4fbacc96b9c94dd1cd25e58ee86abeb718adf51f
 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": 0.0014606604807071094,
+  "epoch": 0.0018726416419321916,
   "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": 1.129,
       "step": 35
+    },
+    {
+      "epoch": 0.0014981133135457533,
+      "grad_norm": 0.15191663801670074,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1597,
+      "step": 40
+    },
+    {
+      "epoch": 0.0014981133135457533,
+      "eval_loss": 1.2657493352890015,
+      "eval_runtime": 355.0176,
+      "eval_samples_per_second": 31.669,
+      "eval_steps_per_second": 15.836,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016853774777389726,
+      "grad_norm": 0.13715489208698273,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1048,
+      "step": 45
+    },
+    {
+      "epoch": 0.0018726416419321916,
+      "grad_norm": 0.1600838303565979,
+      "learning_rate": 0.0,
+      "loss": 1.0763,
+      "step": 50
+    },
+    {
+      "epoch": 0.0018726416419321916,
+      "eval_loss": 1.2651302814483643,
+      "eval_runtime": 362.5534,
+      "eval_samples_per_second": 31.011,
+      "eval_steps_per_second": 15.507,
+      "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": 1739385452101632.0,
+  "total_flos": 2244574609145856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null