Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4280cc2fc703a448b8f0a3a5a205812ef17ddf863e4227d679ad116c5b82a0
+oid sha256:88918d33c6b9e829fcedced53ef4bf8d669811d10db70af4ca1dd4d0b68eb605
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c744d9017ee13bc4bb385b685cab02094b45b09582c25bfa8653dfd29837a4
+oid sha256:80082608d553958b039b12bc3f3c2ff092a389bc1ef4c5ad78dd5ca9805e690c
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e42607aaf2b08cc1be57429f31b6b866a05506b7fcde9f5bdb47ba4e1674a95
+oid sha256:4c9579a5a350008f339603dd9a4a0a778297222eb1d0606862d955f8ddd19716
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01576320168140818,
+  "epoch": 0.018915842017689814,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 27.862,
       "eval_steps_per_second": 3.483,
       "step": 45
+    },
+    {
+      "epoch": 0.016814081793502057,
+      "grad_norm": 0.24442023038864136,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.1128,
+      "step": 48
+    },
+    {
+      "epoch": 0.017864961905595937,
+      "grad_norm": 0.23531076312065125,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.0972,
+      "step": 51
+    },
+    {
+      "epoch": 0.018915842017689814,
+      "grad_norm": 0.2517203390598297,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.1432,
+      "step": 54
+    },
+    {
+      "epoch": 0.018915842017689814,
+      "eval_loss": 1.0988001823425293,
+      "eval_runtime": 172.5963,
+      "eval_samples_per_second": 27.857,
+      "eval_steps_per_second": 3.482,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.852863789662208e+16,
+  "total_flos": 2.2234365475946496e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null