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:b799d4a8b1513acb5d49ab8640608c56263bfe37a23048a51282bc314823504e
+oid sha256:3c5194b2328bed14504b6896c5828588637385ef4799e3c4957ae10de24fec58
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc65514a6a016348da951c4f066047cadcb4187e8380dc5728db6c17c0d96c1
+oid sha256:f2f9b5eaa24756f8d04238bbaf94fe66e9bd1ee4febc57c1e4158dd7d88f309b
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f75c5d1de79fa8d130bf453a0e1b1047ff784c6b921ee1d2efd0d34aa6b721f
+oid sha256:fdff381365340d705a30e6abfb5bfb06fe4eaa8124b03dd10088311a51313193
 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": 0.02079722703639515,
+  "epoch": 0.026663111585121985,
   "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": 0.0098,
       "step": 35
+    },
+    {
+      "epoch": 0.021330489268097587,
+      "grad_norm": 0.025620242580771446,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0064,
+      "step": 40
+    },
+    {
+      "epoch": 0.021330489268097587,
+      "eval_loss": 0.011297364719212055,
+      "eval_runtime": 83.5257,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 4.729,
+      "step": 40
+    },
+    {
+      "epoch": 0.023996800426609784,
+      "grad_norm": 0.018756398931145668,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0026,
+      "step": 45
+    },
+    {
+      "epoch": 0.026663111585121985,
+      "grad_norm": 0.4856107831001282,
+      "learning_rate": 0.0,
+      "loss": 0.0082,
+      "step": 50
+    },
+    {
+      "epoch": 0.026663111585121985,
+      "eval_loss": 0.010740067809820175,
+      "eval_runtime": 83.5173,
+      "eval_samples_per_second": 9.459,
+      "eval_steps_per_second": 4.73,
+      "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": 1.23758343880704e+16,
+  "total_flos": 1.586645434368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null