Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ed40ee86c78be8ec20743c79f6d0dbec96cd22ed836dda9a5e7bba0315a9d4
+oid sha256:b2cebfcf84eeb0f15b23b0a67e3e9dcbeac58989457628d4826fd6ee775335ef
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99cd3a8e8cf4238682bc567f5b2975ff02940040d5748c853fe76cc7ab97d5ce
+oid sha256:215c7332489869162d74eb03738ed2fc7d8967604bba143beaebdb94cfcb85e8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ad91e839915ec68fa8747689b041b7e3b30de1f2a830c80c95bae7a6bb103c
+oid sha256:fcec901e49ace76a0e9d218aa947c6d9415a649586ec2c28e0f7c405cafa1c07
 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": 0.00631911532385466,
+  "epoch": 0.00810142990237777,
   "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": 1.6467,
       "step": 35
+    },
+    {
+      "epoch": 0.006481143921902216,
+      "grad_norm": 3.41062593460083,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8136,
+      "step": 40
+    },
+    {
+      "epoch": 0.006481143921902216,
+      "eval_loss": 1.6066102981567383,
+      "eval_runtime": 319.9679,
+      "eval_samples_per_second": 8.123,
+      "eval_steps_per_second": 4.063,
+      "step": 40
+    },
+    {
+      "epoch": 0.007291286912139993,
+      "grad_norm": 2.4135866165161133,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5883,
+      "step": 45
+    },
+    {
+      "epoch": 0.00810142990237777,
+      "grad_norm": 2.768815040588379,
+      "learning_rate": 0.0,
+      "loss": 1.542,
+      "step": 50
+    },
+    {
+      "epoch": 0.00810142990237777,
+      "eval_loss": 1.595735788345337,
+      "eval_runtime": 320.2184,
+      "eval_samples_per_second": 8.116,
+      "eval_steps_per_second": 4.06,
+      "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": 1.4287883816927232e+16,
+  "total_flos": 1.8356925162848256e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null