Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b984f0adf252057f8a548186929e1bbaea041a474450fd99ea020dbce5509f
+oid sha256:47686864e957ee706f369f072d6ce24eae5ecc42e7a389f41b8974f0eac56030
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb192c0eccab3aeb6a94dc9aa18e42b51b805ac86f785afd216f5d76470132d
+oid sha256:8dffcf00886fa7c9cf215a1f4e28e06e2ba4f1a28df3e10404e306e7000f82e6
 size 51244020

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40ea77f018796dcf8ae76f21379caa245d6284be42f91ddb9f79d052af222a09
+oid sha256:c1b7b6d886eef1bf4ab31beb84dfcf019ec07b9e88083e9a70621987ae923d68
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a46a85e9822a83f7056a66ce5cf602266c078604815d20179f1946b51adceb
+oid sha256:f90a89efbece2c07e249cc9d3a2a6fcacf1d7c18124c63dee2985f2a170f8215
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7499df1e2b20e2bb9ca96b738f88bf92d10eade62a32613ebf1ba9483a67d8a6
+oid sha256:c9f95b136d8b161c8ae97583ab126b299499bf9befa3a60c257222272e45e393
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:816fd80ed6a88c86b5af4f882f2f1da364df6e8adfb262c3dda8840495f52257
+oid sha256:3d65771bcbe519a86a1b55f1a673240abc402d92830e3385f519bff68a8b7b18
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02891566265060241,
+  "epoch": 0.0321285140562249,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 84.244,
       "eval_steps_per_second": 10.611,
       "step": 9
+    },
+    {
+      "epoch": 0.0321285140562249,
+      "grad_norm": 13.10632610321045,
+      "learning_rate": 0.0002,
+      "loss": 1.7408,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7453256196292608.0,
+  "total_flos": 8265470012555264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null