Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c32d6e93c65a9829c430d3010e3d0cf76fc326d4d00858e56a7bccd7336fd03
+oid sha256:b462fa6b90ee8aa41cdcb817969f69412fd9073e3b79a7860595893b4570436e
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0189ebae6c87ad298de80847bee2ec2f2bbf0c64d940cc20a3adf96f9120233
+oid sha256:6b5c8205f0ffedb61b97b75d7af894c0726835db65155b4976937117e1d018e2
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2778f11e01680d148bae3ad73e47fc3eeecdef31f506566b44d27d14bbdd0cb3
+oid sha256:1ad30ac47097af40828a09f9a43d6f06d675ca443c64afa20a38795f419018ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4334705075445816,
+  "epoch": 0.438957475994513,
   "eval_steps": 500,
-  "global_step": 158,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1113,6 +1113,20 @@
       "learning_rate": 0.00015606060606060607,
       "loss": 1.3144,
       "step": 158
+    },
+    {
+      "epoch": 0.43621399176954734,
+      "grad_norm": 0.14858128130435944,
+      "learning_rate": 0.0001553030303030303,
+      "loss": 1.262,
+      "step": 159
+    },
+    {
+      "epoch": 0.438957475994513,
+      "grad_norm": 0.16517716646194458,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 1.2895,
+      "step": 160
     }
   ],
   "logging_steps": 1,
@@ -1132,7 +1146,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9590666619552973e+17,
+  "total_flos": 1.9852396600762368e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null