Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630939c9cbb85d354f3765d1dddc485d21b2c1498805103443d3bbd445d582f0
+oid sha256:7900ac658afcfa6ad60c476c4e3258850750213543a806564cc837002528d6f2
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4345b9fa431415b0a1e9b27cb09b46f10e2394b7d04d4aea43ff4c662d1e4fc9
+oid sha256:29db5167c23b7f8e770193987439d8e8b4a58e0f953de091469763172eb76cb5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c8ddabe315c0fa1febafc1c0530a018ec54acc652b2ec29db8346758a9bef0a
+oid sha256:ca99dc3225ffa9c38bac0d86aab8a17bd923b157dabe3df37abbe4e7d9cabc90
 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": 0.026698613725825774,
+  "epoch": 0.03422899195618689,
   "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": 0.8522,
       "step": 35
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "grad_norm": 0.2444952130317688,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8376,
+      "step": 40
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "eval_loss": 0.8780837059020996,
+      "eval_runtime": 45.8267,
+      "eval_samples_per_second": 13.42,
+      "eval_steps_per_second": 6.721,
+      "step": 40
+    },
+    {
+      "epoch": 0.030806092760568202,
+      "grad_norm": 0.5582700371742249,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8487,
+      "step": 45
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "grad_norm": 0.22252710163593292,
+      "learning_rate": 0.0,
+      "loss": 0.8872,
+      "step": 50
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "eval_loss": 0.8764206767082214,
+      "eval_runtime": 45.5862,
+      "eval_samples_per_second": 13.491,
+      "eval_steps_per_second": 6.756,
+      "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": 8347339865456640.0,
+  "total_flos": 1.058687007326208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null