Training in progress, step 4500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3000b7996e979fe5e10b75ca419a0002c06bf1cd72c9859e9c117fa5cdbd9a
+oid sha256:636a21267d0126c025ae1bfe3794215d12ccaf1c05c9a8820a523c0110824d38
 size 1656902648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f52ce62615be2326def5ac27604e56fee1826cb2d76f3a6373775e651c68025
+oid sha256:32ec073ba4425abdc152e9b574cec3d58e59e1cdc86f6f05a4b9198b12e7bb29
 size 842634836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c0b77b75b104d52df7208449e713d15585ed674305a174ce34842d80400b09
+oid sha256:ee92eb46fa92334cd0695596a0005ba047370328e120afcbe0600b3db0d3cf32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615ec8b9d433097b55947e7c0c4acd8510126ab494bf7d22fbfee31fce53b305
+oid sha256:f151d06bc41f4b059ae9624e4a4277d9aaf5318557f7b4d4466e6f43b6858c39
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.8,
+  "epoch": 9.0,
   "eval_steps": 100,
-  "global_step": 4400,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -667,6 +667,21 @@
       "eval_samples_per_second": 0.645,
       "eval_steps_per_second": 0.645,
       "step": 4400
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.017702901735901833,
+      "learning_rate": 5.102040816326531e-05,
+      "loss": 0.0026,
+      "step": 4500
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.34417256712913513,
+      "eval_runtime": 220.1881,
+      "eval_samples_per_second": 0.645,
+      "eval_steps_per_second": 0.645,
+      "step": 4500
     }
   ],
   "logging_steps": 100,
@@ -686,7 +701,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3734079929886409e+19,
+  "total_flos": 1.403026689660597e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null