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:f56e8bb5c125fcff458d82cdb8c0ec84c5d582592ae772394df2af01fa1df0eb
+oid sha256:97b56057395db046e69174cd102ec05a8cef5fd60c3673fc8f7a9e69ae965661
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e69c2dd56bcd5db304d9f8af68291f35485aa4d160072e4c2d64999746de96c
+oid sha256:493c9a52a8d0978544996a306577fa3509897b69780d3df8df75651a614b9f65
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9df42a9d1501f6518540f2f97c2607aaa7a902f0945692ed6b6ad9ee3c0889b
+oid sha256:029c00b369e8e39599fcd073967debe547b02579df9318d5dd1b7d89f06fc09a
 size 14244

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": 0.1377551020408163,
+  "epoch": 0.1836734693877551,
   "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": 607.839,
       "eval_steps_per_second": 154.723,
       "step": 27
+    },
+    {
+      "epoch": 0.15306122448979592,
+      "grad_norm": 0.4325270652770996,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 6.8621,
+      "step": 30
+    },
+    {
+      "epoch": 0.1683673469387755,
+      "grad_norm": 0.3710213303565979,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 6.8547,
+      "step": 33
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 0.321429967880249,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 6.8474,
+      "step": 36
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "eval_loss": 6.846508979797363,
+      "eval_runtime": 0.2698,
+      "eval_samples_per_second": 611.451,
+      "eval_steps_per_second": 155.642,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 259504570368.0,
+  "total_flos": 346006093824.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null