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:be22d011adcbef0cea503d6f1ccfaac1cf9de9fc405b50375ac1cfc4d6717fca
+oid sha256:9e12d5103fa75bb81d1e6963bd6848b308eac35129d81d2eba046c55ee955072
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a995303ede4d4e9f2d5474533649928ee32e0f833589bb86a2909aaac82c6bd
+oid sha256:eda994ba43debbb010af9f9fa65c1d92ed2228666b4b48f88433430d735a08fd
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b2b655181cbd20071e25a8c2ca5953708370f3dc36111fe4dce52cd2f9b572
+oid sha256:317794345936cd47f7a3a54e3f8c8b54036a873d685eff898bd380a2a827db47
 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": 0.006369686823731167,
+  "epoch": 0.0081662651586297,
   "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": 1.7852,
       "step": 35
+    },
+    {
+      "epoch": 0.0065330121269037604,
+      "grad_norm": 1.7885736227035522,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6991,
+      "step": 40
+    },
+    {
+      "epoch": 0.0065330121269037604,
+      "eval_loss": 1.8340213298797607,
+      "eval_runtime": 185.3213,
+      "eval_samples_per_second": 13.911,
+      "eval_steps_per_second": 6.955,
+      "step": 40
+    },
+    {
+      "epoch": 0.007349638642766731,
+      "grad_norm": 1.8472743034362793,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7551,
+      "step": 45
+    },
+    {
+      "epoch": 0.0081662651586297,
+      "grad_norm": 1.7605617046356201,
+      "learning_rate": 0.0,
+      "loss": 1.8875,
+      "step": 50
+    },
+    {
+      "epoch": 0.0081662651586297,
+      "eval_loss": 1.8290151357650757,
+      "eval_runtime": 184.3171,
+      "eval_samples_per_second": 13.987,
+      "eval_steps_per_second": 6.993,
+      "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": 7583213417398272.0,
+  "total_flos": 9710212302766080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null