Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12dfebe2ebc3d3d86f49ad8af7de1d1742fdd66c5035bf8ebeb3c70a23f4eda8
+oid sha256:9645a82d6194512785c123862495b38bafcc452b25d066291d92de1593a7ab04
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18009903aeaccf43b9772682889440d18ed8d1d8eb87408aa77309fc3cbf4766
+oid sha256:f06968e64b4927e4490dfbcfeae9f24f5ecdb0e6a18a01f1c5da039b92458e2d
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1650f09948b4ca5c34c8acf8bd0dadcc1d4bbda8a8b1879761e650714aff18b8
+oid sha256:0f5f51fcdc1863ce78ca50d10ce957861b6b2cb962a78304a1f8d3fd9bd36974
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007877806468554422,
+  "epoch": 0.008753118298393803,
   "eval_steps": 5,
-  "global_step": 45,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -192,6 +192,21 @@
       "eval_samples_per_second": 23.671,
       "eval_steps_per_second": 2.96,
       "step": 45
+    },
+    {
+      "epoch": 0.00840299356645805,
+      "grad_norm": 5.0879807472229,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.9486,
+      "step": 48
+    },
+    {
+      "epoch": 0.008753118298393803,
+      "eval_loss": 0.9580356478691101,
+      "eval_runtime": 406.5042,
+      "eval_samples_per_second": 23.668,
+      "eval_steps_per_second": 2.959,
+      "step": 50
     }
   ],
   "logging_steps": 3,
@@ -206,12 +221,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.9091673279627264e+16,
+  "total_flos": 2.1224821132099584e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null