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:f1944e47942c218972333feb96386ac590ccbab9c1b172cf7a03157564173fd8
+oid sha256:f364041d74a6b18c1222de33050331ec212ff451d126ad977e126d6bfc525048
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e15bbb46f44f242648e7fb0592255bfd24fc8ae10f738335d788285eaab9659
+oid sha256:a8a783d62aa936bb476a9db652628be2ef9d33e65a7cdd1ca1d609802a76eb52
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957a2501fd314a074e8723019089ed2725d79483046accce0537090de50d6ccf
+oid sha256:a7f17263b79b22c1f081ec3830fd9aaab682bc92742ef006c65a38ed537b5c09
 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": 0.036228518346493266,
+  "epoch": 0.046446818392940084,
   "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": 0.2646,
       "step": 35
+    },
+    {
+      "epoch": 0.03715745471435207,
+      "grad_norm": 0.41087549924850464,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4314,
+      "step": 40
+    },
+    {
+      "epoch": 0.03715745471435207,
+      "eval_loss": 0.334094762802124,
+      "eval_runtime": 32.9726,
+      "eval_samples_per_second": 13.769,
+      "eval_steps_per_second": 6.885,
+      "step": 40
+    },
+    {
+      "epoch": 0.04180213655364608,
+      "grad_norm": 0.37770456075668335,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2254,
+      "step": 45
+    },
+    {
+      "epoch": 0.046446818392940084,
+      "grad_norm": 0.10671886801719666,
+      "learning_rate": 0.0,
+      "loss": 0.3868,
+      "step": 50
+    },
+    {
+      "epoch": 0.046446818392940084,
+      "eval_loss": 0.33325254917144775,
+      "eval_runtime": 32.9629,
+      "eval_samples_per_second": 13.773,
+      "eval_steps_per_second": 6.887,
+      "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": 3575695914565632.0,
+  "total_flos": 4588393009250304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null