Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5734c6d2f43730ba84305be1a484ececda16d9ba1d71f44a90e43fcff0e087
+oid sha256:1158193d1e4c32b2078f44caefc4d366071f148efc262b4a1f62b46d7c3a9cec
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5334fc9ace705748f9ae4b7fd27a39e7ed8cdf12f827ac59f2426c958b2f09d0
+oid sha256:ce352f8c6f9600353ab8a6bbc1ea972420d30f118e0b2876e7b24c292a3ea1b2
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c983d111d3ec56de2891ca6e215fae2e56304160ac9beb5771ed74d82290b3
+oid sha256:e31a7020ce39d331a4f66b0aac8c3c27ff765a90a9909d8192a4ae0ee079f71a
 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": 0.0032513472017340517,
+  "epoch": 0.004335129602312069,
   "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": 7.04,
       "eval_steps_per_second": 0.88,
       "step": 27
+    },
+    {
+      "epoch": 0.003612608001926724,
+      "grad_norm": 13.662860870361328,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 6.0724,
+      "step": 30
+    },
+    {
+      "epoch": 0.003973868802119396,
+      "grad_norm": 15.459967613220215,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 6.2818,
+      "step": 33
+    },
+    {
+      "epoch": 0.004335129602312069,
+      "grad_norm": 11.845706939697266,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 5.7472,
+      "step": 36
+    },
+    {
+      "epoch": 0.004335129602312069,
+      "eval_loss": 1.4950615167617798,
+      "eval_runtime": 1983.0961,
+      "eval_samples_per_second": 7.053,
+      "eval_steps_per_second": 0.882,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.59380728306729e+16,
+  "total_flos": 1.0125076377423053e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null