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:d57929331eebeb0847490f87496fca25e1b0857209fa9559facfe779ac5def03
+oid sha256:661d23b959258cc89183b9a187847122810606e38d96719544af4f7a22ce6e9f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a2986d580641f4545021c2b06c6705b8a57b0521d395f2cd86e2d5cdcde102b
+oid sha256:d9a455bf9a24ccc90ccd3673387b8e0f63cc26a31a70021f23b7b274318ff4e7
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79860259ff731f0b1c006300fee3fbd1e0fb1cad375751b62eee5d8cabbc13f0
+oid sha256:8d67ec2502bdc1e0e180e8abf6116d9abc6b553d1b08b70fa10e367a53ed7cc9
 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": 0.047058823529411764,
+  "epoch": 0.06033182503770739,
   "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": 1.6278,
       "step": 35
+    },
+    {
+      "epoch": 0.048265460030165915,
+      "grad_norm": 0.8652676939964294,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.539,
+      "step": 40
+    },
+    {
+      "epoch": 0.048265460030165915,
+      "eval_loss": 1.575426459312439,
+      "eval_runtime": 25.0271,
+      "eval_samples_per_second": 13.945,
+      "eval_steps_per_second": 6.992,
+      "step": 40
+    },
+    {
+      "epoch": 0.05429864253393665,
+      "grad_norm": 0.9328100681304932,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5162,
+      "step": 45
+    },
+    {
+      "epoch": 0.06033182503770739,
+      "grad_norm": 1.0344215631484985,
+      "learning_rate": 0.0,
+      "loss": 1.5315,
+      "step": 50
+    },
+    {
+      "epoch": 0.06033182503770739,
+      "eval_loss": 1.5716311931610107,
+      "eval_runtime": 25.008,
+      "eval_samples_per_second": 13.956,
+      "eval_steps_per_second": 6.998,
+      "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": 7259539673972736.0,
+  "total_flos": 9432777665544192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null