Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:121e81de5e37517985eaa376beeebdd7dcae5c67893850a776304e35b7134234
+oid sha256:43f4ea3789698115ad6c0375e731154e2972da877f6f249391a6f03e1f358527
 size 21253080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc88de44d7b87fac0a740aaea8c8509282e07873d732b305166f21733b73e6b
+oid sha256:d7ee3a2d7a862885c80b2d33b73d3ddc7cf32d51a51964eda42acd98f3b7c015
 size 10952634

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e83e788d272231b5f4da6f65fe3fb1d2929a43992231d6cf856f9bcd17cb890
+oid sha256:11544d4aff0bcf97bef50ba09543f43078e26edf5c76678d675b6625cbd17148
 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": 0.10070493454179255,
+  "epoch": 0.1342732460557234,
   "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": 98.459,
       "eval_steps_per_second": 49.23,
       "step": 150
+    },
+    {
+      "epoch": 0.10741859684457872,
+      "grad_norm": 0.8945415616035461,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 3.4655,
+      "step": 160
+    },
+    {
+      "epoch": 0.11413225914736488,
+      "grad_norm": 0.8643715381622314,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 3.3762,
+      "step": 170
+    },
+    {
+      "epoch": 0.12084592145015106,
+      "grad_norm": 0.8482128977775574,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 3.5946,
+      "step": 180
+    },
+    {
+      "epoch": 0.12755958375293722,
+      "grad_norm": 0.7966582775115967,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 3.4324,
+      "step": 190
+    },
+    {
+      "epoch": 0.1342732460557234,
+      "grad_norm": 0.7980437278747559,
+      "learning_rate": 0.0,
+      "loss": 3.5701,
+      "step": 200
+    },
+    {
+      "epoch": 0.1342732460557234,
+      "eval_loss": 1.690674066543579,
+      "eval_runtime": 3.1729,
+      "eval_samples_per_second": 98.965,
+      "eval_steps_per_second": 49.482,
+      "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": 331352374247424.0,
+  "total_flos": 442358194765824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null