Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fece400e016089aee6c2890fc63429fcda5f43cd6a6831f603181f25ad75918
+oid sha256:286c8f3049bf2d7d5230cfd5820298459f16a3f865a5d00cd3f779c2834597cf
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9532fa14ac9141e7a9f4b431e42ea2c02e4792467ae83eee19980130e995410
+oid sha256:8b3cd861620b8809c7093fe4a58b037e4db56d3fc418cffd2289e7f3c619b626
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc0e116c12cf30acafae2063f6bf889a62b08e09f95b38821d8a5d4b95ee8a83
+oid sha256:99ce551a2c413675f09ba21d11dea55e90add6f1824e780707a8c09073babc6c
 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": 0.015172145496985022,
+  "epoch": 0.019451468585878234,
   "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": 2.0909,
       "step": 35
+    },
+    {
+      "epoch": 0.015561174868702588,
+      "grad_norm": 0.424358606338501,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1651,
+      "step": 40
+    },
+    {
+      "epoch": 0.015561174868702588,
+      "eval_loss": 2.0750739574432373,
+      "eval_runtime": 113.0128,
+      "eval_samples_per_second": 9.583,
+      "eval_steps_per_second": 4.796,
+      "step": 40
+    },
+    {
+      "epoch": 0.01750632172729041,
+      "grad_norm": 0.486756831407547,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.107,
+      "step": 45
+    },
+    {
+      "epoch": 0.019451468585878234,
+      "grad_norm": 0.4951198697090149,
+      "learning_rate": 0.0,
+      "loss": 2.0594,
+      "step": 50
+    },
+    {
+      "epoch": 0.019451468585878234,
+      "eval_loss": 2.0739192962646484,
+      "eval_runtime": 104.7943,
+      "eval_samples_per_second": 10.335,
+      "eval_steps_per_second": 5.172,
+      "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": 2529526416408576.0,
+  "total_flos": 3242982585139200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null