Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c7b2238c2340ecde4e88ad71c71f4a828d882fb9ab4f2cad4f37f91cb971a6
+oid sha256:4e8a477348b02b6f2971bbed09e7262a7a6fd49ca3e93095ac54e31e023693ad
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a98825702221c198980c5ce3bd04acc8ff994db1e3f6c0a6055e55c04dc6ce3
+oid sha256:1341b9d6b5c9e5e41b638bf384ed4424a4beaab1e8e27c97257c24d5b3055fc7
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64a0060ff8061e9a05daabce94dadd58dcfe702b74d356d47d28e78b0037fb5
+oid sha256:14724dc6b4118722f0780aae51012b2af45174622fd9a7b766ca4cfb34adc9ce
 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": 0.022174840085287847,
+  "epoch": 0.028429282160625444,
   "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": 5.5755,
       "step": 35
+    },
+    {
+      "epoch": 0.022743425728500355,
+      "grad_norm": 17.608741760253906,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.4154,
+      "step": 40
+    },
+    {
+      "epoch": 0.022743425728500355,
+      "eval_loss": 1.5208227634429932,
+      "eval_runtime": 61.1128,
+      "eval_samples_per_second": 12.125,
+      "eval_steps_per_second": 6.071,
+      "step": 40
+    },
+    {
+      "epoch": 0.0255863539445629,
+      "grad_norm": 11.478259086608887,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.3918,
+      "step": 45
+    },
+    {
+      "epoch": 0.028429282160625444,
+      "grad_norm": 11.493557929992676,
+      "learning_rate": 0.0,
+      "loss": 5.6759,
+      "step": 50
+    },
+    {
+      "epoch": 0.028429282160625444,
+      "eval_loss": 1.5186352729797363,
+      "eval_runtime": 60.8233,
+      "eval_samples_per_second": 12.183,
+      "eval_steps_per_second": 6.1,
+      "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": 8982442970972160.0,
+  "total_flos": 1.1436183489871872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null