Training in progress, step 77, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7e9d3c3e74148fcbe3d1504ece756be6c3c6fe0d872ef0635623b925b7b3fb
+oid sha256:f7b95e136cd383ff83a7fda7bce3f8d53c1f6228c6ca6113f38ec12331a42d32
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214e3967dd76a65f1ee4e67fa3feb439083185eb59fbb68630ee9333c94d3e8d
+oid sha256:1dea7e4397d798a0d3605b4fe8bdc6a65d3a5f84c31a429d5720772de4b001d2
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d461e68a163c787fff150b87639893e5b81a899f6f8be260318c9e2277a5f4
+oid sha256:725ee499aaa0bc04b490ac3af0c734c514c976dd8cd2f204b00fdb43d2a90bf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20027434842249658,
+  "epoch": 0.2112482853223594,
   "eval_steps": 500,
-  "global_step": 73,
+  "global_step": 77,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -518,6 +518,34 @@
       "learning_rate": 0.000146,
       "loss": 1.3128,
       "step": 73
+    },
+    {
+      "epoch": 0.2030178326474623,
+      "grad_norm": 0.08815225213766098,
+      "learning_rate": 0.000148,
+      "loss": 1.3321,
+      "step": 74
+    },
+    {
+      "epoch": 0.205761316872428,
+      "grad_norm": 0.09394700825214386,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.3341,
+      "step": 75
+    },
+    {
+      "epoch": 0.2085048010973937,
+      "grad_norm": 0.10041660070419312,
+      "learning_rate": 0.000152,
+      "loss": 1.2944,
+      "step": 76
+    },
+    {
+      "epoch": 0.2112482853223594,
+      "grad_norm": 0.09344102442264557,
+      "learning_rate": 0.000154,
+      "loss": 1.3226,
+      "step": 77
     }
   ],
   "logging_steps": 1,
@@ -537,7 +565,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.034931398791168e+16,
+  "total_flos": 9.536105939440435e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null