Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9058c24b9d8d1f986400e4556450eb103cc68da04b1bdde58420cc279656ad52
+oid sha256:cc021c1dc17698ec773fbc2ba53a805f0c6845be592384865bd529d8fde571bc
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d508e13decc03060dafd2e0947ba33ab5e7652518bf66f2b6ab89ba74ffdb2cd
+oid sha256:1bc144030867c5e039beb4b8bd67fd8db01f80ab3b86d3566172fd8663bd4f8d
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23394f11c585caee6f023d3d27fbf169d72b7ba93e512d965e8d71c36f05c33
+oid sha256:b7f60dafcba70d0bd4269d6a1aae646bfb15f5cb4cf04d0bc35a1f3053348114
 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": 0.08133472367049009,
+  "epoch": 0.10427528675703858,
   "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": 1.9681,
       "step": 35
+    },
+    {
+      "epoch": 0.08342022940563086,
+      "grad_norm": 1.0751326084136963,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8917,
+      "step": 40
+    },
+    {
+      "epoch": 0.08342022940563086,
+      "eval_loss": 1.8614988327026367,
+      "eval_runtime": 11.3927,
+      "eval_samples_per_second": 17.731,
+      "eval_steps_per_second": 8.865,
+      "step": 40
+    },
+    {
+      "epoch": 0.09384775808133472,
+      "grad_norm": 1.260564923286438,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6922,
+      "step": 45
+    },
+    {
+      "epoch": 0.10427528675703858,
+      "grad_norm": 0.9989824295043945,
+      "learning_rate": 0.0,
+      "loss": 1.8681,
+      "step": 50
+    },
+    {
+      "epoch": 0.10427528675703858,
+      "eval_loss": 1.8599786758422852,
+      "eval_runtime": 11.3163,
+      "eval_samples_per_second": 17.85,
+      "eval_steps_per_second": 8.925,
+      "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": 2162920955314176.0,
+  "total_flos": 2800545051967488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null