Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68db4985fa2c3fe5a01662f6f0560e43202375cc372dfd01ecd92ba54881a636
+oid sha256:08bfb172e028878b82bf4ec5187aaf722e4bec3860799555061f1008f19f20f7
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60457c106e9b6191d2152fa0198dc1146be1c786c3cbbc773edf528ad7e0a27c
+oid sha256:d740bdbbfa4affe63ecdfc6adb0a1a0247749568f6b53ba828c23b9d9a152cc1
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89125b381bd706e47d0969ca57bde232385b184bb6fee985c4b095b282bae7af
+oid sha256:3f04944917c15f265951392f0ad036c49b2e1d3572ae924179abc0eb1dc0ce1c
 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": 0.017844886753603295,
+  "epoch": 0.022878059940517045,
   "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": 0.0851,
       "step": 35
+    },
+    {
+      "epoch": 0.018302447952413637,
+      "grad_norm": 3.478883981704712,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1406,
+      "step": 40
+    },
+    {
+      "epoch": 0.018302447952413637,
+      "eval_loss": 0.1899276077747345,
+      "eval_runtime": 192.6298,
+      "eval_samples_per_second": 4.781,
+      "eval_steps_per_second": 2.393,
+      "step": 40
+    },
+    {
+      "epoch": 0.02059025394646534,
+      "grad_norm": 0.8011217713356018,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2482,
+      "step": 45
+    },
+    {
+      "epoch": 0.022878059940517045,
+      "grad_norm": 6.223889350891113,
+      "learning_rate": 0.0,
+      "loss": 0.246,
+      "step": 50
+    },
+    {
+      "epoch": 0.022878059940517045,
+      "eval_loss": 0.18310397863388062,
+      "eval_runtime": 198.8909,
+      "eval_samples_per_second": 4.631,
+      "eval_steps_per_second": 2.318,
+      "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": 7453256523448320.0,
+  "total_flos": 9555457081344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null