Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e3f155170b2e17057b7217e2bfeb8697e115cae6642ad212ff92fdd58b35a13
+oid sha256:5f26e2f86d865a262bfcd71af9f53dfaaa973d37131126550f382d62a3bd5d74
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7e70600e03400972f367ba4c0d573ac62fadd3ea2ed6e028bdb67aa41d0022
+oid sha256:696ac53100d0497e45e65e73e362c5146dacf3c3275f287e13d823eaddc66e38
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a69897655d6335f40565e13c6d562938736cf3824c45eb132524b68b5b2ee5
+oid sha256:1f3822bfdbd562745cef4aefdff46e5a448d68022fbeb06c433deb5cba76e0af
 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": 0.013455235466620665,
+  "epoch": 0.017250301880282905,
   "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": 0.721,
       "step": 35
+    },
+    {
+      "epoch": 0.013800241504226323,
+      "grad_norm": 1.2980700731277466,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4492,
+      "step": 40
+    },
+    {
+      "epoch": 0.013800241504226323,
+      "eval_loss": 0.4763771593570709,
+      "eval_runtime": 81.9288,
+      "eval_samples_per_second": 14.903,
+      "eval_steps_per_second": 7.458,
+      "step": 40
+    },
+    {
+      "epoch": 0.015525271692254615,
+      "grad_norm": 1.6496080160140991,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4418,
+      "step": 45
+    },
+    {
+      "epoch": 0.017250301880282905,
+      "grad_norm": 1.5776127576828003,
+      "learning_rate": 0.0,
+      "loss": 0.5057,
+      "step": 50
+    },
+    {
+      "epoch": 0.017250301880282905,
+      "eval_loss": 0.47041645646095276,
+      "eval_runtime": 82.0824,
+      "eval_samples_per_second": 14.875,
+      "eval_steps_per_second": 7.444,
+      "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": 3817926788382720.0,
+  "total_flos": 4894777933824000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null