Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f287704ce4ebf2723f3cb77530d91e120091e1877fb36265728dd30e022a672b
+oid sha256:ce1f2b2c3eb9955e151699367342543142a011e31420da24957aacd58764e220
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8436a6ad617f54ee3426a5292c09564806ba8ee9afcfc38c72bd391511febbca
+oid sha256:b8f1b5919677129947b16d151ff5209c3511f9cd24bc34cbb1dc305c47de6727
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07fd69d00474f7452dfa2874201aa85c7ba86db9ba98cc2657ecdee75796730c
+oid sha256:25936d7c5564659764ea03391276bc1f2ec09b668311f6aed5a57a965d5055de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.061855670103092786,
+  "epoch": 0.09278350515463918,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 6.805,
       "eval_steps_per_second": 0.861,
       "step": 18
+    },
+    {
+      "epoch": 0.07216494845360824,
+      "grad_norm": 2.133312702178955,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 2.9592,
+      "step": 21
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 2.0654103755950928,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 3.2154,
+      "step": 24
+    },
+    {
+      "epoch": 0.09278350515463918,
+      "grad_norm": 1.8565651178359985,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.9275,
+      "step": 27
+    },
+    {
+      "epoch": 0.09278350515463918,
+      "eval_loss": 0.7440634965896606,
+      "eval_runtime": 72.0175,
+      "eval_samples_per_second": 6.804,
+      "eval_steps_per_second": 0.861,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.29002129637376e+16,
+  "total_flos": 9.606577979916288e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null