Training in progress, step 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3835780fc1689b3612f8af23471f04a25358ec3f65b3d333aba425c378ef9991
+oid sha256:2e0b542ca6d0e75535c59d43f4c1434dc3fa64d480a16352dce2647e9b4ddc0a
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dabbd11ac2f357ab78521d5565e9cf3b042393656b8ddb82e6acd6b456852b5
+oid sha256:e731d7184683dee6f4d57117e28c2f5425ec1f570e1864f443cf442162e82646
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abedd40078bdae4cbde39b797b6e575c2db0d3277dbf649464d9e152e4357855
+oid sha256:5d93469df52a68b6829e2991063037b777683cdcf55700bd143ca4fe3646b2dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc75f52135f05d6a7eece7c1642cd12df115223afda2588adac0da7bde4ebbb
+oid sha256:5bace611bec546b6196769d18099d0892bded57db054c98eceb3962aefa06a10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7619047619047619,
+  "epoch": 1.1428571428571428,
   "eval_steps": 1,
-  "global_step": 2,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,14 @@
       "eval_samples_per_second": 491.159,
       "eval_steps_per_second": 81.86,
       "step": 2
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "eval_loss": 10.373238563537598,
+      "eval_runtime": 0.0371,
+      "eval_samples_per_second": 485.034,
+      "eval_steps_per_second": 80.839,
+      "step": 3
     }
   ],
   "logging_steps": 10,
@@ -37,12 +45,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 413789061120.0,
+  "total_flos": 614218137600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null