Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e714f551456cb321e14da4aa4bfa30082097a1ed6617aec5ebf7161bccfe05e
+oid sha256:164607459d6b4b2af0dc3c94fcab35e79e9173d00eff65e421156b330ea1137a
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3551db152725e0318800a915ea3d6f03339d8ee9f7b2bcd2b14f5d9016495321
+oid sha256:c3a81fae5924df48fcf8ba5f327902de7f0ce606d74c75c6a3c7e2adb24d0151
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03e377c1380d240d43ba2d545f7f9a7f6e94581d4561c6de13cf0d3287942aef
+oid sha256:8fcdef6942fba6e364a62676041d1b0ebae96258bbe3cb886b5e35269ee3dc51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02307470435535045,
+  "epoch": 0.03461205653302567,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.32,
       "step": 18
+    },
+    {
+      "epoch": 0.02422843957311797,
+      "grad_norm": 0.23161785304546356,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.2829,
+      "step": 21
+    },
+    {
+      "epoch": 0.027689645226420537,
+      "grad_norm": 0.2098318636417389,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.2869,
+      "step": 24
+    },
+    {
+      "epoch": 0.027689645226420537,
+      "eval_loss": 0.2817035913467407,
+      "eval_runtime": 76.4839,
+      "eval_samples_per_second": 4.772,
+      "eval_steps_per_second": 2.393,
+      "step": 24
+    },
+    {
+      "epoch": 0.031150850879723104,
+      "grad_norm": 0.17820662260055542,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.2789,
+      "step": 27
+    },
+    {
+      "epoch": 0.03461205653302567,
+      "grad_norm": 0.20811568200588226,
+      "learning_rate": 0.0,
+      "loss": 0.2953,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.695099842985984e+16,
+  "total_flos": 2.542649764478976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null