Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628adda072197ff2a68dabb6f7e2bfa9ab072d99971aa03f3e98f3822a4f72a2
+oid sha256:900c6f64f89019d37f80d02b57e353f7162072bbe240514e3f652ba3d5aab3e5
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9e82e2c0cdac866825a274031c9ad26bd1ce0d427a34e4cbfb62591699d5fb
+oid sha256:c29fd75fca5ed71c380b5a354cc30da9451a86435d550e88d79ad73335b4d17a
 size 39398

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:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0046557463549385825,
+  "epoch": 0.006207661806584777,
   "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": 203.737,
       "eval_steps_per_second": 101.868,
       "step": 150
+    },
+    {
+      "epoch": 0.004966129445267821,
+      "grad_norm": 0.11091376096010208,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 11.893,
+      "step": 160
+    },
+    {
+      "epoch": 0.00527651253559706,
+      "grad_norm": 0.10149168968200684,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 11.8918,
+      "step": 170
+    },
+    {
+      "epoch": 0.005586895625926299,
+      "grad_norm": 0.1267317533493042,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 11.8906,
+      "step": 180
+    },
+    {
+      "epoch": 0.005897278716255538,
+      "grad_norm": 0.11293170601129532,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 11.8895,
+      "step": 190
+    },
+    {
+      "epoch": 0.006207661806584777,
+      "grad_norm": 0.11377740651369095,
+      "learning_rate": 0.0,
+      "loss": 11.8913,
+      "step": 200
+    },
+    {
+      "epoch": 0.006207661806584777,
+      "eval_loss": 11.890507698059082,
+      "eval_runtime": 66.7086,
+      "eval_samples_per_second": 203.362,
+      "eval_steps_per_second": 101.681,
+      "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": 32376225792.0,
+  "total_flos": 42892591104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null