Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5aee7aecd283f8674263498ed3b5848d03c74fe00609e375d73f8841b28b43
+oid sha256:f2be51699dce6d0966fb1dcdef49aa62eb605ee4abd39441946914910bdc1f24
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c743d82648288a5303848f7fca3db5a78a32ccdf0ad12dd807bf47cd9d75502
+oid sha256:6de9268b8a7a307f01bcff3cdeee39f65df89bc82c98d15cc527af840197ea09
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a4b404b2f718e4760b85a9d4524024371d3145138fb5bbfbef7e27c53fe48c
+oid sha256:7c8d4edaf3cbdd098403097c0492d7c28ca0777a8becf6d77956ec217939c6de
 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": 0.035214446952595936,
+  "epoch": 0.045146726862302484,
   "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": 3.4754,
       "step": 35
+    },
+    {
+      "epoch": 0.03611738148984198,
+      "grad_norm": 1.1155290603637695,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2733,
+      "step": 40
+    },
+    {
+      "epoch": 0.03611738148984198,
+      "eval_loss": 3.4100918769836426,
+      "eval_runtime": 31.9061,
+      "eval_samples_per_second": 14.637,
+      "eval_steps_per_second": 7.334,
+      "step": 40
+    },
+    {
+      "epoch": 0.040632054176072234,
+      "grad_norm": 1.4393564462661743,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.4991,
+      "step": 45
+    },
+    {
+      "epoch": 0.045146726862302484,
+      "grad_norm": 1.4681293964385986,
+      "learning_rate": 0.0,
+      "loss": 3.382,
+      "step": 50
+    },
+    {
+      "epoch": 0.045146726862302484,
+      "eval_loss": 3.3911728858947754,
+      "eval_runtime": 31.99,
+      "eval_samples_per_second": 14.598,
+      "eval_steps_per_second": 7.315,
+      "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": 7188373690122240.0,
+  "total_flos": 9235971044278272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null