Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:055e5b5ef94c766b6912391e0081f9fcd036e4025c0490aed2fd2cace885170c
+oid sha256:4b5a0ad7a4a75d7fa6f6384e2070738c1b462ff380b648a11bce5e9bc8fab545
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc8ca7c6d9229a07a6335fd703709165c4ad47e74fafa03affe9695f5813bf0
+oid sha256:3d17b129093ff55159a9025cfa1262c6641dba04e6ecbe818780e4e2f9529c27
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0faafb2ae711d4fd7df5493691d652c88f534d84da92ff77eb8863dda28af9a0
+oid sha256:c51036317a763c4852293ce56ccc83db4ad0fada6d0a3ec596ca30c09a83d490
 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": 0.39344262295081966,
+  "epoch": 0.4918032786885246,
   "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": 15.396,
       "eval_steps_per_second": 1.999,
       "step": 36
+    },
+    {
+      "epoch": 0.4262295081967213,
+      "grad_norm": 1.2684975862503052,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 7.5737,
+      "step": 39
+    },
+    {
+      "epoch": 0.45901639344262296,
+      "grad_norm": 1.303396224975586,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 7.6169,
+      "step": 42
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 1.1348557472229004,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 7.3236,
+      "step": 45
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "eval_loss": 1.8486707210540771,
+      "eval_runtime": 9.9999,
+      "eval_samples_per_second": 15.4,
+      "eval_steps_per_second": 2.0,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.770244873892659e+16,
+  "total_flos": 5.946469637318246e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null