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:b9447666ca4486e63364af3def806f5a468a764489741bf3ab3933cacd3b0c12
+oid sha256:a60227b7cae7ea11dc04889fcd490e03b49e1acc9103d490277cea20a40250a0
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139b259d1fca9b555605742eb4779825516a882c6b6ad85c5b3c09e5c99571c4
+oid sha256:2fb2046fec8b8e044e3ec9a557819bfe4ff77296299f810f8866ea8b1178fca6
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e84a92a389e8f8225a67e1edf059475566aba99fba047ec4f43babf6cf1df1
+oid sha256:3cdc474ae9c7c4c5dce8ee1b92fc582cc5a7070a8a041f336e8add72dd026f48
 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": 0.004988169086141843,
+  "epoch": 0.006395088571976722,
   "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": 7.1707,
       "step": 35
+    },
+    {
+      "epoch": 0.005116070857581378,
+      "grad_norm": 8.697281837463379,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.0684,
+      "step": 40
+    },
+    {
+      "epoch": 0.005116070857581378,
+      "eval_loss": 1.7659326791763306,
+      "eval_runtime": 83.0156,
+      "eval_samples_per_second": 39.655,
+      "eval_steps_per_second": 19.828,
+      "step": 40
+    },
+    {
+      "epoch": 0.00575557971477905,
+      "grad_norm": 7.536022186279297,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.0319,
+      "step": 45
+    },
+    {
+      "epoch": 0.006395088571976722,
+      "grad_norm": 8.265710830688477,
+      "learning_rate": 0.0,
+      "loss": 6.9004,
+      "step": 50
+    },
+    {
+      "epoch": 0.006395088571976722,
+      "eval_loss": 1.761187195777893,
+      "eval_runtime": 82.7895,
+      "eval_samples_per_second": 39.763,
+      "eval_steps_per_second": 19.882,
+      "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": 1164432239493120.0,
+  "total_flos": 1492861845504000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null