Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bd5b4f66cffd94ec5d5f8bdec87721ea6b52b6664960ef38aecc1f285a4ce5
+oid sha256:ceb01e6f00c167c9cb083d1beb8619be2123294d01fa098833e5b1dee9ef5e7b
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1335a55f5025b1478abfc78ff6f0b6a3d7aaa94c8697959df1ae5522aa4133e9
+oid sha256:fc1e599055a2c4013aea284bd7bda345a59a9055ed97733db1291157d709c904
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359e8299abeae63a887c34c6e8aa0e184b4a8cf72c58dad08ef75b14732e6166
+oid sha256:4b42979da7ee25faa5b66ec1b4188e82a67e362e036a9fa08d5367ab35d15d3a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08236536430834214,
+  "epoch": 0.10559662090813093,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.8755,
       "step": 35
+    },
+    {
+      "epoch": 0.08447729672650475,
+      "grad_norm": 1.386352777481079,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8622,
+      "step": 40
+    },
+    {
+      "epoch": 0.08447729672650475,
+      "eval_loss": 1.8232667446136475,
+      "eval_runtime": 8.4123,
+      "eval_samples_per_second": 23.775,
+      "eval_steps_per_second": 11.887,
+      "step": 40
+    },
+    {
+      "epoch": 0.09503695881731784,
+      "grad_norm": 1.1782969236373901,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8325,
+      "step": 45
+    },
+    {
+      "epoch": 0.10559662090813093,
+      "grad_norm": 0.8375657796859741,
+      "learning_rate": 0.0,
+      "loss": 1.9179,
+      "step": 50
+    },
+    {
+      "epoch": 0.10559662090813093,
+      "eval_loss": 1.8123703002929688,
+      "eval_runtime": 8.2834,
+      "eval_samples_per_second": 24.145,
+      "eval_steps_per_second": 12.072,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3423703176314880.0,
+  "total_flos": 4469265224171520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null