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:bd1579a423bb2426741942c15f7114435e135938c146d5a5acf912720dd9c1bd
+oid sha256:937a132b892b0dca318592f823471f809dacf84a4ca507234b9254870b003d34
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f7407a4edcd393f511608ce1b042197d89d1b71ff621f90f69e11e2c06f49b
+oid sha256:8a9ba1437e58d6a750b8daf98692b37af29d38e10c2d0543f7a974999c7094ef
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbfbff5445caae9f2668acaf55142bb15a402c199154485e79ab39da1e78943
+oid sha256:7092244c60798e1ab03d4fe68ee97ba243124819620dca59a1f7c2ad2682481a
 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": 0.004781902338840695,
+  "epoch": 0.0061306440241547374,
   "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": 0.0999,
       "step": 35
+    },
+    {
+      "epoch": 0.00490451521932379,
+      "grad_norm": 0.4097394049167633,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0207,
+      "step": 40
+    },
+    {
+      "epoch": 0.00490451521932379,
+      "eval_loss": 0.06025295704603195,
+      "eval_runtime": 130.3145,
+      "eval_samples_per_second": 26.352,
+      "eval_steps_per_second": 13.176,
+      "step": 40
+    },
+    {
+      "epoch": 0.005517579621739264,
+      "grad_norm": 0.623701810836792,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0953,
+      "step": 45
+    },
+    {
+      "epoch": 0.0061306440241547374,
+      "grad_norm": 0.2647206783294678,
+      "learning_rate": 0.0,
+      "loss": 0.0859,
+      "step": 50
+    },
+    {
+      "epoch": 0.0061306440241547374,
+      "eval_loss": 0.05916808918118477,
+      "eval_runtime": 128.125,
+      "eval_samples_per_second": 26.802,
+      "eval_steps_per_second": 13.401,
+      "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": 1264763208204288.0,
+  "total_flos": 1621491292569600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null