Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c73690605b211d1e8bfc5816ede40afff5cb1f0e2c7736a5d36e24cdb0911d
+oid sha256:28958dce75f806f1e94bd18a71bce6a321e314e2000d92595a1123ff909c46d1
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a57b67fad2a67fd6a3eaae77eb428b39ee659fc0d47fe6c60d5dbd37ba4dd8
+oid sha256:2e13c5c32ebd01477633dde0afbd97e7ddebbd938cae42bd9bbc700aeb88d4f8
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6427ffbd65b4be1b2f3fbb643f167933e7260181d95492a2b6d8cd2d25b75737
+oid sha256:dae2cff01f9b0fc3a44f22c10b61e1a8883cd6f6a47e470e57981350e6a19d5d
 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": 0.030063596068606667,
+  "epoch": 0.03854307188282906,
   "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": 6.9124,
       "step": 35
+    },
+    {
+      "epoch": 0.03083445750626325,
+      "grad_norm": 0.27636855840682983,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.9174,
+      "step": 40
+    },
+    {
+      "epoch": 0.03083445750626325,
+      "eval_loss": 6.910731792449951,
+      "eval_runtime": 10.2698,
+      "eval_samples_per_second": 53.263,
+      "eval_steps_per_second": 26.68,
+      "step": 40
+    },
+    {
+      "epoch": 0.034688764694546154,
+      "grad_norm": 0.29338952898979187,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.9162,
+      "step": 45
+    },
+    {
+      "epoch": 0.03854307188282906,
+      "grad_norm": 0.3097763955593109,
+      "learning_rate": 0.0,
+      "loss": 6.9151,
+      "step": 50
+    },
+    {
+      "epoch": 0.03854307188282906,
+      "eval_loss": 6.910257339477539,
+      "eval_runtime": 9.4458,
+      "eval_samples_per_second": 57.909,
+      "eval_steps_per_second": 29.008,
+      "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": 102829768704.0,
+  "total_flos": 131833036800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null