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:a08dcff9c548338d03f0d168ca2cd53f3a0706a3037fc3e149165eec05747fdf
+oid sha256:875ea0201173c25eb8c7ea9f9a5c9c0f1f1ecae3ae7f3944256d88018cb0dfb2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365747b2184e910a05736d1568b7451523338c0dc407e0c6999e3bd92d63922b
+oid sha256:a3923fdc691d714edfc7d5cb0704aaf0bb76ff2e1724c7f8bfb53a07a36fbe22
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df4452b6ca42236c2bcd52b5df9f8e63ebc61625217e8356d9a4e2cc7327676
+oid sha256:89b38edf16e00970afb593efd87e2a583d3afe78398f0ae48ffeddd0350e5bc3
 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": 2.0384,
       "step": 35
+    },
+    {
+      "epoch": 0.022743425728500355,
+      "grad_norm": 1.055640697479248,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8456,
+      "step": 40
+    },
+    {
+      "epoch": 0.022743425728500355,
+      "eval_loss": 1.8406403064727783,
+      "eval_runtime": 53.5759,
+      "eval_samples_per_second": 13.831,
+      "eval_steps_per_second": 6.925,
+      "step": 40
+    },
+    {
+      "epoch": 0.0255863539445629,
+      "grad_norm": 1.4639087915420532,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9405,
+      "step": 45
+    },
+    {
+      "epoch": 0.028429282160625444,
+      "grad_norm": 1.3342856168746948,
+      "learning_rate": 0.0,
+      "loss": 1.8875,
+      "step": 50
+    },
+    {
+      "epoch": 0.028429282160625444,
+      "eval_loss": 1.8367289304733276,
+      "eval_runtime": 53.4983,
+      "eval_samples_per_second": 13.851,
+      "eval_steps_per_second": 6.935,
+      "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": 7675691629805568.0,
+  "total_flos": 9895168727580672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null