Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:879311a4aebc17b4fafcb549aa97630288d831fabf9f2b7c29c0be0e3f4d6cd9
+oid sha256:7f6a55ad0be753e29269e2f185df91f0be0e84bbc37972098c62a3986236bb65
 size 864368280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3307f49c2895af38b46962aea4ec72240ac1ecffff0a114178a9d05df44a3d28
+oid sha256:c095a9c2de308e133a689b07cc4cdf84b91e74a79283411211fad3e64d594cc4
 size 1729074742

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b98c21a6c7c3c92fc68e617bba8fd566712396b2134a20b6aff6e47927480b
+oid sha256:dd01e813cc343537008d77625d57e124afc6747a7069b071d8b63f835a36e499
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d44c0ecfb16f05885a8478afdaa40e988069bb6891bbc6c82185a9b1533b4c7
+oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6363636363636362,
+  "epoch": 3.0454545454545454,
   "eval_steps": 1,
-  "global_step": 7,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,14 @@
       "eval_samples_per_second": 7.791,
       "eval_steps_per_second": 3.116,
       "step": 7
+    },
+    {
+      "epoch": 3.0454545454545454,
+      "eval_loss": 0.00037194820470176637,
+      "eval_runtime": 0.6402,
+      "eval_samples_per_second": 7.811,
+      "eval_steps_per_second": 3.124,
+      "step": 8
     }
   ],
   "logging_steps": 3,
@@ -91,12 +99,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1753603576365056e+16,
+  "total_flos": 1.3432689801560064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null