Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d04bc45df4b3cba486cc45e2063279e0846f0c8df938b6f995b5dc99706092
+oid sha256:a7add5580f8199e8cb3ffd1942074c9ef66e100cea03dc75e1213f186cbcfb25
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366ee91d89db94a05da45409deef2ace46f614a21262ad65fe818248ddf64abe
+oid sha256:ba966691837b3189ee6219319d672883201fa57c16f5e704a63f97d6f4250677
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:895bc9637d2006530369fffe00fd60c01471aa1822b76fe15317578b06a982b9
+oid sha256:fd49b8784f8352ef56a66b33e4173e365b7ec64cc619f6a6d1606534dae5c72b
 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": 0.030796078632654107,
+  "epoch": 0.04106143817687215,
   "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": 23.804,
       "eval_steps_per_second": 11.908,
       "step": 150
+    },
+    {
+      "epoch": 0.032849150541497715,
+      "grad_norm": 0.4666227102279663,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.2773,
+      "step": 160
+    },
+    {
+      "epoch": 0.03490222245034132,
+      "grad_norm": 0.40914592146873474,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.2505,
+      "step": 170
+    },
+    {
+      "epoch": 0.03695529435918493,
+      "grad_norm": 0.4898912012577057,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.2766,
+      "step": 180
+    },
+    {
+      "epoch": 0.03900836626802854,
+      "grad_norm": 0.444612592458725,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.2722,
+      "step": 190
+    },
+    {
+      "epoch": 0.04106143817687215,
+      "grad_norm": 0.48914796113967896,
+      "learning_rate": 0.0,
+      "loss": 0.2969,
+      "step": 200
+    },
+    {
+      "epoch": 0.04106143817687215,
+      "eval_loss": 0.28439101576805115,
+      "eval_runtime": 86.2057,
+      "eval_samples_per_second": 23.792,
+      "eval_steps_per_second": 11.902,
+      "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": 3.384772789272576e+16,
+  "total_flos": 4.51479053795328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null