Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bd610804e17dd481e589023dba4294cd51f198c19f7a8f3c769ee982c374deb
+oid sha256:ca432e679f8a3e880c3aa7573365a176a4a42fedd1a4019c37d5db9f46f70c1c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3181ef93cfabb37b409b5773517392859e6bdf1e21d779ec7196d88120180c8e
+oid sha256:963794912210a463999c40779e995aca3bbdce9220f7c1b6b8695934697c0549
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9954cba04c3dc6992b14a4d57747ae9e20729d78654175da8d9cfa94c83c25e
+oid sha256:cb0b29821d8c3fb50b70bea0ad4ae6e320cb0247ce153bb264fbea6e9f2c08b2
 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": 0.0025356370788160525,
+  "epoch": 0.0032508167677128877,
   "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": 7.3993,
       "step": 35
+    },
+    {
+      "epoch": 0.00260065341417031,
+      "grad_norm": 15.47500228881836,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.9907,
+      "step": 40
+    },
+    {
+      "epoch": 0.00260065341417031,
+      "eval_loss": 1.8122162818908691,
+      "eval_runtime": 498.3665,
+      "eval_samples_per_second": 12.996,
+      "eval_steps_per_second": 6.499,
+      "step": 40
+    },
+    {
+      "epoch": 0.002925735090941599,
+      "grad_norm": 19.3575496673584,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.0011,
+      "step": 45
+    },
+    {
+      "epoch": 0.0032508167677128877,
+      "grad_norm": 15.406116485595703,
+      "learning_rate": 0.0,
+      "loss": 7.6624,
+      "step": 50
+    },
+    {
+      "epoch": 0.0032508167677128877,
+      "eval_loss": 1.8033350706100464,
+      "eval_runtime": 499.5132,
+      "eval_samples_per_second": 12.967,
+      "eval_steps_per_second": 6.484,
+      "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": 8237557456306176.0,
+  "total_flos": 1.0340763615363072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null