Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1dc1913dd69833ac675932f806fcb77197b505ec50e658bce34e079c29e1e89
+oid sha256:d441f1df1512c9f74f3867b2b0b4219d6dbe6bed8bbb7bd1580761a8aa339382
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c955cb1024478f31a651205525bf18d6a7f84c1758b26d236987faa838d570
+oid sha256:5e67e6dc009b50c2a8a83ee42fec782de9e665190738ce65feba6555bf550026
 size 253144

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc50706e2c700cad816fc6d64def52f075ebb861f2f615ec4a5726886b71843
+oid sha256:1bf5389f606fc2b1efbc13be6c76663698c76df7a91c80b41ba6f46ce3721ae3
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13950c1144fd634424a8cb721a96d2e61590b8a2653aeb357120e8d708010a3f
+oid sha256:f419a5bb6d3f280769f52fa3fa58d69ead31c1ffcdb7250968b609d69eb0e744
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f35161b8c5d1c73a9272bcf7fd56a70c048dbff30de12da69ff06cbedd1f02da
+oid sha256:3d16645c84b44201dc09483bf21ba5e5d20cb28423cfa7ee7a948c7f9e0aec92
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58802612c5bef628e3d95d1faaede0021c856a92b7dab6b2c46fa9289b9a173e
+oid sha256:5a27c6e170cddcda0c527c5f2fbfde684164ae3f293d89123f9e8e470cbb0333
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1291866028708134,
+  "epoch": 0.1722488038277512,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 762.643,
       "eval_steps_per_second": 23.85,
       "step": 27
+    },
+    {
+      "epoch": 0.14354066985645933,
+      "grad_norm": 0.20146459341049194,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3382,
+      "step": 30
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.1689472794532776,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3341,
+      "step": 33
+    },
+    {
+      "epoch": 0.1722488038277512,
+      "grad_norm": 0.1589594930410385,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3297,
+      "step": 36
+    },
+    {
+      "epoch": 0.1722488038277512,
+      "eval_loss": 10.327372550964355,
+      "eval_runtime": 1.8458,
+      "eval_samples_per_second": 762.288,
+      "eval_steps_per_second": 23.838,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 24094942691328.0,
+  "total_flos": 32126590255104.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null