Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:918b1cab71ebba90a428579a7564e639298e83e6761374483f49644704075e7f
+oid sha256:f2376eaccda4d880910e5930a99fa7a7b290c7cc289ccf3a0abde38ccebef511
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5ef7870af310ef229829711dae4b6f79456d9e6f9e1492bbe28b604211baa4
+oid sha256:71ea54e312f14bb4fd0b487cc196798a40bd997888fab2103109e536ce82603d
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e05343cded05c60740d6de4c4834260b4a342f6ca5ef008d7c59110070d517c
+oid sha256:7df23e03f3c3533698e583560c479b817273cd5ed4163a9984c58ecc560a679c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e2b5d9560191cd8cd454fd2be1d438284aac8617273afc89cbf21659e669ae
+oid sha256:e8eeea5c208aac12ca1d7588ccb40479c9754522c5504911db2e6c3df2af3627
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7710843373493976,
+  "epoch": 1.0602409638554218,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,14 @@
       "eval_samples_per_second": 32.006,
       "eval_steps_per_second": 4.268,
       "step": 12
+    },
+    {
+      "epoch": 1.0602409638554218,
+      "eval_loss": 1.1985491514205933,
+      "eval_runtime": 3.2919,
+      "eval_samples_per_second": 31.897,
+      "eval_steps_per_second": 4.253,
+      "step": 16
     }
   ],
   "logging_steps": 10,
@@ -60,12 +68,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9601868749602816.0,
+  "total_flos": 1.2802491666137088e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null