Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19cecfb6a0546c7757dfde05bce6d4e731a624c69ec294eceff9bdc6993372ab
+oid sha256:5d590483546eb966180199ffb0eb71b937d13d7fa5cc7eafd607f9e3450abf6f
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0497cbe1290c0f77de99d44becd4eecdb1052611ef4933eed463be7a7cb548
+oid sha256:1795fe04261a29582dcf3ac53e21af54a63ad68a3ba22c3f0beb6aad1ba11586
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb705fb038ef589c04f9d60dffa4b4e1ba7d2e143ae1484a41c1b820c5d2dd2d
+oid sha256:055e431d087cf1a8744f18bec296ccc8adbb2a09905a587018cd7843e43783c1
 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": 0.0010735077554053867,
+  "epoch": 0.0013762919941094703,
   "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": 0.4738,
       "step": 35
+    },
+    {
+      "epoch": 0.0011010335952875761,
+      "grad_norm": 0.4435214400291443,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5267,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011010335952875761,
+      "eval_loss": 0.5785387754440308,
+      "eval_runtime": 550.425,
+      "eval_samples_per_second": 27.791,
+      "eval_steps_per_second": 13.897,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012386627946985233,
+      "grad_norm": 0.3839089870452881,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4424,
+      "step": 45
+    },
+    {
+      "epoch": 0.0013762919941094703,
+      "grad_norm": 0.4666566252708435,
+      "learning_rate": 0.0,
+      "loss": 0.7067,
+      "step": 50
+    },
+    {
+      "epoch": 0.0013762919941094703,
+      "eval_loss": 0.5770589709281921,
+      "eval_runtime": 560.8567,
+      "eval_samples_per_second": 27.274,
+      "eval_steps_per_second": 13.638,
+      "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": 462260910686208.0,
+  "total_flos": 592691375112192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null