Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b93cb694ad5e68f7b9914dddaf47c16de7503697ac76309bd1a6d0724915ac
+oid sha256:5c08af196c5c83ee8d59289648d7cfe1be1825be899c6b37ee3368fb5bcc7409
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034255435833dcef31fda9ad6e232016a88714c5894193468e3b04108a31e096
+oid sha256:ffb6895c9863c73ae48ee000ce64176d12bd59b2dc6e52c28bf2b8bfe29ff672
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
+oid sha256:2f3dfab2f15c077a3bfe1d57e8f4dfb9954e3c582cff3d86c56d618335c8d869
 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": 0.004189719073964656,
+  "epoch": 0.005371434710211097,
   "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": 0.656,
       "step": 35
+    },
+    {
+      "epoch": 0.004297147768168878,
+      "grad_norm": 5.748566627502441,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7073,
+      "step": 40
+    },
+    {
+      "epoch": 0.004297147768168878,
+      "eval_loss": 0.6386785507202148,
+      "eval_runtime": 726.7173,
+      "eval_samples_per_second": 5.394,
+      "eval_steps_per_second": 2.697,
+      "step": 40
+    },
+    {
+      "epoch": 0.004834291239189987,
+      "grad_norm": 3.4865448474884033,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4824,
+      "step": 45
+    },
+    {
+      "epoch": 0.005371434710211097,
+      "grad_norm": 3.769179344177246,
+      "learning_rate": 0.0,
+      "loss": 0.6635,
+      "step": 50
+    },
+    {
+      "epoch": 0.005371434710211097,
+      "eval_loss": 0.6112967133522034,
+      "eval_runtime": 726.6473,
+      "eval_samples_per_second": 5.395,
+      "eval_steps_per_second": 2.697,
+      "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": 1.4426852391124992e+16,
+  "total_flos": 1.84959646040064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null