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:ad691ac6d2fc1e0e3a5201df708d4cfee6260fd89efca3634f07128ed442bc46
+oid sha256:2ff6567e44d62efedd7a29948e9e29bc123718c15e0b48a2ea0454f34fe46432
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e792bce28adb52a972d1da0fd894a4f9f0697ff068ac581b2abfba7acb0d982
+oid sha256:379d3b6a6df4904eb5e7be2cf76f0564c974102bc9be931b3842642c0d9b929e
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3c48c26b22b8eff8e3ac55a811b89695de14f630a8d517211346253708e53a
+oid sha256:75e62f15e8be6b8702c4f048c8417995011e93dbb157b35eaebb133af301fcd8
 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": 0.005745062836624776,
+  "epoch": 0.00718132854578097,
   "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": 23.074,
       "eval_steps_per_second": 2.886,
       "step": 36
+    },
+    {
+      "epoch": 0.006223818073010173,
+      "grad_norm": 0.480747789144516,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 1.6363,
+      "step": 39
+    },
+    {
+      "epoch": 0.0067025733093955715,
+      "grad_norm": 0.4569284915924072,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 1.6942,
+      "step": 42
+    },
+    {
+      "epoch": 0.00718132854578097,
+      "grad_norm": 0.5147221684455872,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 1.7732,
+      "step": 45
+    },
+    {
+      "epoch": 0.00718132854578097,
+      "eval_loss": 1.6826040744781494,
+      "eval_runtime": 457.1352,
+      "eval_samples_per_second": 23.087,
+      "eval_steps_per_second": 2.888,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.453055546064896e+16,
+  "total_flos": 3.095130487652352e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null