Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49934e71750309922bfdaa48fb3b49174506bb970cc4d110080fffae80984c9e
+oid sha256:a064383e75adb57718d4da21d7e516b5cf34ddf6914d964261310f13adf30e7c
 size 144805440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8830bf56036bfe09509d6ad1c2a3de4f24fb0dd2b01d60fe7dabd1887dcda35d
+oid sha256:c583bc1118554fb67ff539ef6ecab96ff19c334277f916c4e11fdbd06badbb57
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cce00927943e545f38db920e14c68afdcbd9c32a13585978045f5eaff63d9c2
+oid sha256:b6fdb25d8aaba00761ed5aca09337bb966cfac27797928fea61ca14ae2db0cb4
 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": 0.022298456260720412,
+  "epoch": 0.02858776443682104,
   "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": 1.0478,
       "step": 35
+    },
+    {
+      "epoch": 0.022870211549456832,
+      "grad_norm": 5.570464611053467,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9933,
+      "step": 40
+    },
+    {
+      "epoch": 0.022870211549456832,
+      "eval_loss": 1.0566424131393433,
+      "eval_runtime": 107.1344,
+      "eval_samples_per_second": 6.879,
+      "eval_steps_per_second": 3.444,
+      "step": 40
+    },
+    {
+      "epoch": 0.025728987993138937,
+      "grad_norm": 3.7340707778930664,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.938,
+      "step": 45
+    },
+    {
+      "epoch": 0.02858776443682104,
+      "grad_norm": 5.016777992248535,
+      "learning_rate": 0.0,
+      "loss": 1.3119,
+      "step": 50
+    },
+    {
+      "epoch": 0.02858776443682104,
+      "eval_loss": 1.042315125465393,
+      "eval_runtime": 107.1672,
+      "eval_samples_per_second": 6.877,
+      "eval_steps_per_second": 3.443,
+      "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": 1.2631125277016064e+16,
+  "total_flos": 1.61937503551488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null