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:d5e3b5e5fdffa60c9d25fe5320732a3aa46b9a69dfd22451ea0dfb641a379973
+oid sha256:1b21d4c633fb528151238ad3207f3de7351b7b6e1ff204d5f4beb22157757d66
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23e00943162e790c1fd02c0f2cae46d8e53b549244d6309f5a2e618c4ee3589
+oid sha256:dea4a730c21d9d974f51a849027eeb6ec542a435375f77f0bed5869f8c4f3dfe
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923a732a6319030690e5b3cb8df0ce5fe735e4a9a540d158907f92c9d1f819dc
+oid sha256:a0e62aef34d5da844ac0c9a34196fe8197cdc1feece530f5842990c93c7005a9
 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": 0.002683409305925862,
+  "epoch": 0.0034402683409305926,
   "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": 0.4433,
       "step": 35
+    },
+    {
+      "epoch": 0.002752214672744474,
+      "grad_norm": 15.033890724182129,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4186,
+      "step": 40
+    },
+    {
+      "epoch": 0.002752214672744474,
+      "eval_loss": 0.13489258289337158,
+      "eval_runtime": 320.4852,
+      "eval_samples_per_second": 19.096,
+      "eval_steps_per_second": 9.548,
+      "step": 40
+    },
+    {
+      "epoch": 0.0030962415068375333,
+      "grad_norm": 3.6657726764678955,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5887,
+      "step": 45
+    },
+    {
+      "epoch": 0.0034402683409305926,
+      "grad_norm": 4.438101291656494,
+      "learning_rate": 0.0,
+      "loss": 0.4394,
+      "step": 50
+    },
+    {
+      "epoch": 0.0034402683409305926,
+      "eval_loss": 0.09722831845283508,
+      "eval_runtime": 319.637,
+      "eval_samples_per_second": 19.147,
+      "eval_steps_per_second": 9.573,
+      "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": 3580018173149184.0,
+  "total_flos": 4589766888652800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null