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:e5fbd8953c3306f2d212e4252226f7e416a27c8180e9361805d371b03171298d
+oid sha256:382138452f60adbd1e9acafd4b6a76de9c982d37522befef79db4020638ac9a0
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc9bb236566d88db3c5d38ce37ef9d64343439f367505a8f7480544c16ff145
+oid sha256:fd9d25c5841408acb031f6d09d4d7aca6dd9f8aef1794a40ebbb250fcf64a147
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045ecf0ce94d29d10806883c558837f183a4fc3ef7c6dbbe4cc8e4b9141e090e
+oid sha256:04ab54c26c8cda51ddabe84d65acc5a7b69a8319b3c84694846690018cfc4072
 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": 0.0017523167649536647,
+  "epoch": 0.002246559955068801,
   "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": 3.3125,
       "step": 35
+    },
+    {
+      "epoch": 0.0017972479640550407,
+      "grad_norm": 5.792168140411377,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.9318,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017972479640550407,
+      "eval_loss": 3.112304925918579,
+      "eval_runtime": 610.8208,
+      "eval_samples_per_second": 15.343,
+      "eval_steps_per_second": 7.672,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020219039595619206,
+      "grad_norm": 7.447405815124512,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.0419,
+      "step": 45
+    },
+    {
+      "epoch": 0.002246559955068801,
+      "grad_norm": 5.79746150970459,
+      "learning_rate": 0.0,
+      "loss": 3.0246,
+      "step": 50
+    },
+    {
+      "epoch": 0.002246559955068801,
+      "eval_loss": 3.1021504402160645,
+      "eval_runtime": 609.5075,
+      "eval_samples_per_second": 15.376,
+      "eval_steps_per_second": 7.688,
+      "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": 3609898726195200.0,
+  "total_flos": 4662275981967360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null