Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3909bf399c9a0567734c90631db8490c6fef8e4137802230e483adb34099146c
+oid sha256:f2a2b31604d6c6730e9101598a113ccdc8626fd68222fb35139cacd015d2a1c4
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:750abeb6a036f68f971f74a56e7601860c00995b29898ab3a1fc5e1bf1b1f181
+oid sha256:8d3d08a855b9668dcdce76a8ae320b2cbc616a4a4861231bb80e91cdc0442385
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec2ddbaa8bba775edf415d96dfe5570dd34c0cd61b7fa5167b0e0c1db7bd35f1
+oid sha256:57e412899acc108f67d82e3e7c22d62e4cc76020baca6b6a6ee2ab4ea57903ad
 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": 0.14917951268025859,
+  "epoch": 0.19890601690701143,
   "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": 24.7,
       "eval_steps_per_second": 12.35,
       "step": 150
+    },
+    {
+      "epoch": 0.15912481352560914,
+      "grad_norm": 0.000430845539085567,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.16907011437095973,
+      "grad_norm": 0.00024463460431434214,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.1790154152163103,
+      "grad_norm": 0.007861273363232613,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.0039,
+      "step": 180
+    },
+    {
+      "epoch": 0.18896071606166087,
+      "grad_norm": 0.00012755903298966587,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.0021,
+      "step": 190
+    },
+    {
+      "epoch": 0.19890601690701143,
+      "grad_norm": 0.0007723955204710364,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.19890601690701143,
+      "eval_loss": 0.0003575802256818861,
+      "eval_runtime": 17.1979,
+      "eval_samples_per_second": 24.654,
+      "eval_steps_per_second": 12.327,
+      "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": 4.86285395361792e+16,
+  "total_flos": 6.494263021928448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null