Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33948ba980e3873ae3e943d0d79c9fb2fd33fb499a29143f593cf4086453638b
+oid sha256:207448c682d4d58ee2096d2e0c0cb6a7b61da867a7d4d6644c858d2d20599e79
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458c02bef5d870075515422f49396beeca0bbfa11ac577605c99efee4ce071c5
+oid sha256:9a059d394e131d2fd993dca1e75266b0f0773e0d3fdd1250c685fe60c9a94ab8
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8d766a2c89ca827fd88604c04645a44e7deecf9ec62a527d0adcbef8aac440
+oid sha256:9f6c4b7c059825c4bc8cb721af1bd8b0f04e3482c208d61c6dee52f9e48a542b
 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": 0.0008617689464874629,
+  "epoch": 0.0011048319826762346,
   "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": 2.3429,
       "step": 35
+    },
+    {
+      "epoch": 0.0008838655861409876,
+      "grad_norm": 5.065801620483398,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3131,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008838655861409876,
+      "eval_loss": 2.3334805965423584,
+      "eval_runtime": 1824.2071,
+      "eval_samples_per_second": 10.446,
+      "eval_steps_per_second": 5.223,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009943487844086111,
+      "grad_norm": 4.786803722381592,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3686,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011048319826762346,
+      "grad_norm": 5.302400588989258,
+      "learning_rate": 0.0,
+      "loss": 2.3433,
+      "step": 50
+    },
+    {
+      "epoch": 0.0011048319826762346,
+      "eval_loss": 2.3163483142852783,
+      "eval_runtime": 1826.4633,
+      "eval_samples_per_second": 10.433,
+      "eval_steps_per_second": 5.217,
+      "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": 8004335107571712.0,
+  "total_flos": 1.02619680866304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null