Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38aebc8839e71c822cce4fd7ecb6138e4a6812b716afed06fffab2983314804
+oid sha256:a834fd1483ad83f8c0c70d7d8bfa44d6776ea5e3ac71f875d6f945e872289c56
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656e3c9eca30c87801bd66aed3ca92cd3df619fd42416f8d458b6f1ddeaa5c84
+oid sha256:20c9acdc0f910469b351a806d676f16542285dfd13621121cd170bff9e2e9882
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e96b31999edd85c2cb037a7393b204a41975c1632139f4f06d6e05e5f188ae
+oid sha256:4ea8b51e35881ab579a6293996173fcb614aaf154e1048c45664ea9d80e8998e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01495793081956996,
+  "epoch": 0.01869741352446245,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 23.37,
       "eval_steps_per_second": 2.923,
       "step": 36
+    },
+    {
+      "epoch": 0.016204425054534122,
+      "grad_norm": 0.7994734048843384,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 1.3122,
+      "step": 39
+    },
+    {
+      "epoch": 0.017450919289498285,
+      "grad_norm": 0.7998748421669006,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 1.3337,
+      "step": 42
+    },
+    {
+      "epoch": 0.01869741352446245,
+      "grad_norm": 0.7622133493423462,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 1.3281,
+      "step": 45
+    },
+    {
+      "epoch": 0.01869741352446245,
+      "eval_loss": 1.2758731842041016,
+      "eval_runtime": 173.596,
+      "eval_samples_per_second": 23.353,
+      "eval_steps_per_second": 2.921,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4476295383547904e+16,
+  "total_flos": 1.809536922943488e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null