Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b59452504c3e271034e78c816db6cf99a84774463251869d09373476cc9080
+oid sha256:dbc73c5726867b182f43473b51f04ed0af598e7da13db500aec5cb1a6b3a0cdb
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db10837bf46901470af8e0e723970a33a8b219925955bb68a8483cde56d07e2
+oid sha256:64e85fc1dad91650d901b61ffed2886be35abf5fa0d957334bbc8f3b2b45516f
 size 55549892

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d450d193668b66a7586116c28777a937fbe4fabb5b5885faa4cc0fd228aea9
+oid sha256:50970e9fb90cfa56732e765cbce53b3cd942cd9b292e3b6340cb78bcea19854b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843950f67c89726280cda91c084cda3566c875749772f0ecd792f273113afdcb
+oid sha256:0d751f405682dc926f52678a89a4ce3753e34109a84782e08f0714b31251593a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5862ff18425a4e47db5aff0f2ad6cc32aa5584d1b7e42a8390fba8386baaa76
+oid sha256:66fbdfba6a8c5b067e977c7d6c6af1a11f8d5ad597c9a36ce475193fdbf76e5f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb770715b2374c3f57eeaa9b0d65a6aabd47d4ec277eb9c9cf88ba4f09de3b1
+oid sha256:e17cda9b1087abfb13edf0de1c5fdf6243e94d300987afb534dac6658f1a5958
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 1.0666666666666667,
   "eval_steps": 2,
-  "global_step": 6,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,14 @@
       "eval_samples_per_second": 54.875,
       "eval_steps_per_second": 8.442,
       "step": 6
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "eval_loss": 0.08227913081645966,
+      "eval_runtime": 0.2328,
+      "eval_samples_per_second": 55.836,
+      "eval_steps_per_second": 8.59,
+      "step": 8
     }
   ],
   "logging_steps": 5,
@@ -60,12 +68,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4925744580919296.0,
+  "total_flos": 6567659441225728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null