Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1831e0075b7e225174ac540989359463710dd6e5952612baa87b434f559a5e27
+oid sha256:189702eb1f86cf046dc06c7804c9d29c79b0b2f09207f9d2c576de2fb32dff4b
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab284e395324a339b3f911b01806e07bf343a39cedc14db91a422b5145e8fc2c
+oid sha256:1d48c1dff4ae161de072e1b9a9a51e6021844afaa07b2c0b02cbf93c09a614e8
 size 173094

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:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.45112781954887216,
+  "epoch": 0.6015037593984962,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 300.117,
       "eval_steps_per_second": 150.058,
       "step": 150
+    },
+    {
+      "epoch": 0.48120300751879697,
+      "grad_norm": 0.10884358733892441,
+      "learning_rate": 0.0002,
+      "loss": 10.6897,
+      "step": 160
+    },
+    {
+      "epoch": 0.5112781954887218,
+      "grad_norm": 0.08635402470827103,
+      "learning_rate": 0.0002,
+      "loss": 10.6819,
+      "step": 170
+    },
+    {
+      "epoch": 0.5413533834586466,
+      "grad_norm": 0.11650286614894867,
+      "learning_rate": 0.0002,
+      "loss": 10.6761,
+      "step": 180
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.08204352855682373,
+      "learning_rate": 0.0002,
+      "loss": 10.6727,
+      "step": 190
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 0.10318433493375778,
+      "learning_rate": 0.0002,
+      "loss": 10.6705,
+      "step": 200
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "eval_loss": 10.65206527709961,
+      "eval_runtime": 0.4867,
+      "eval_samples_per_second": 287.665,
+      "eval_steps_per_second": 143.833,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 24608872857600.0,
+  "total_flos": 32811830476800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null