Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850d08c0b5b47e4e107b4ede3a5e2cf7614121cd4020bbf615335082c1b407ec
+oid sha256:0b8cb19ec64ff49fcd8f4cd7afd0eb394a8627690fe08f2ff739c507bff2e1b8
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55cdaa202d979a301fdc89c38f1de0df70821444024657e10e9fb1f0fdcbdbe
+oid sha256:e6e4a0e3723e6e875ac0da10b839e26a795a08b78cddcb7b4217a3f81ecef5a0
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
+oid sha256:70bb08e79cd87e26411515d4cfe540a1dfafd998745c321dfb4680b9ed334a58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06379585326953748,
+  "epoch": 0.08506113769271664,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 309.608,
       "eval_steps_per_second": 154.804,
       "step": 150
+    },
+    {
+      "epoch": 0.0659223817118554,
+      "grad_norm": 0.03459914028644562,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 10.3752,
+      "step": 155
+    },
+    {
+      "epoch": 0.06804891015417332,
+      "grad_norm": 0.026126541197299957,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 10.3767,
+      "step": 160
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.02168152667582035,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 10.3748,
+      "step": 165
+    },
+    {
+      "epoch": 0.07230196703880915,
+      "grad_norm": 0.030395662412047386,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 10.3775,
+      "step": 170
+    },
+    {
+      "epoch": 0.07442849548112707,
+      "grad_norm": 0.02148647978901863,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 10.3768,
+      "step": 175
+    },
+    {
+      "epoch": 0.07655502392344497,
+      "grad_norm": 0.027581162750720978,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 10.3745,
+      "step": 180
+    },
+    {
+      "epoch": 0.0786815523657629,
+      "grad_norm": 0.019557451829314232,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 10.3774,
+      "step": 185
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.0335659459233284,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 10.3748,
+      "step": 190
+    },
+    {
+      "epoch": 0.08293460925039872,
+      "grad_norm": 0.018269188702106476,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 10.3759,
+      "step": 195
+    },
+    {
+      "epoch": 0.08506113769271664,
+      "grad_norm": 0.025745518505573273,
+      "learning_rate": 0.0,
+      "loss": 10.3751,
+      "step": 200
+    },
+    {
+      "epoch": 0.08506113769271664,
+      "eval_loss": 10.376242637634277,
+      "eval_runtime": 3.2404,
+      "eval_samples_per_second": 305.514,
+      "eval_steps_per_second": 152.757,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -263,12 +341,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4066770616320.0,
+  "total_flos": 5437446881280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null