Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c772efa6a965fdf363e3f48b40900b7eda4835f652ef07821944d20c7c91aa4
+oid sha256:c29a7e4a72e14e1c42b6f533c778179d53902e9f0d732b2f9f1c42a7ce693290
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61dd4c9f9f64ad9f14fac2f963922225b3223c40ae710cd2867da7bdd9ebb92
+oid sha256:da369b9a8332ce9cda2e322707c49f8d541b14fbeb11db82fb5c66d080caabbb
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f4b31686c0cedd38423c5b629e0087858f84314e65539fb958b27e9aef543f
+oid sha256:fda5f7675164b2dcdea7007367fd7f639a20ab36e08ab7645900e0bdb82d2012
 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": 0.1259710266638673,
+  "epoch": 0.16796136888515642,
   "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": 10.871,
       "eval_steps_per_second": 5.435,
       "step": 150
+    },
+    {
+      "epoch": 0.13436909510812514,
+      "grad_norm": 1.3660070896148682,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 1.5439,
+      "step": 160
+    },
+    {
+      "epoch": 0.14276716355238295,
+      "grad_norm": 1.4630749225616455,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.5289,
+      "step": 170
+    },
+    {
+      "epoch": 0.15116523199664078,
+      "grad_norm": 1.5646495819091797,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.5129,
+      "step": 180
+    },
+    {
+      "epoch": 0.1595633004408986,
+      "grad_norm": 1.5474354028701782,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 1.5284,
+      "step": 190
+    },
+    {
+      "epoch": 0.16796136888515642,
+      "grad_norm": 1.5290640592575073,
+      "learning_rate": 0.0,
+      "loss": 1.5622,
+      "step": 200
+    },
+    {
+      "epoch": 0.16796136888515642,
+      "eval_loss": 0.3818550407886505,
+      "eval_runtime": 46.14,
+      "eval_samples_per_second": 10.88,
+      "eval_steps_per_second": 5.44,
+      "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": 9.4986125180928e+16,
+  "total_flos": 1.26648166907904e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null