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:bc644f73fa250715eef05eda2c671c1877b0bf0c75fa1e6637b16eb1ab8b2a3f
+oid sha256:f3c9b5e19f4f4d2022c3e98a4d79041e18ebc4646db0048b7ea3ae60865bfa52
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0901872b1118ec006c7e4966ed0b01e206dba0bf32c14065e6cee54df8e110bc
+oid sha256:6c4efb051d2843fe533c10f1aaf21fa5ecfb627dc0c9992919da8962af59eb89
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35ceb9c66f290e6328f028acb8423e4e69632d64e5b94ac94b05c9d1045a6206
+oid sha256:b830a7c64ac89acee417f7da9ef09260f43345e5ff980a83b171f40a3bde88a7
 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": 0.03183023872679045,
+  "epoch": 0.03819628647214854,
   "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": 7.527,
       "eval_steps_per_second": 0.942,
       "step": 45
+    },
+    {
+      "epoch": 0.03395225464190981,
+      "grad_norm": 0.24335481226444244,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.2388,
+      "step": 48
+    },
+    {
+      "epoch": 0.03607427055702918,
+      "grad_norm": 0.19779016077518463,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.2253,
+      "step": 51
+    },
+    {
+      "epoch": 0.03819628647214854,
+      "grad_norm": 0.23507341742515564,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2155,
+      "step": 54
+    },
+    {
+      "epoch": 0.03819628647214854,
+      "eval_loss": 0.22180727124214172,
+      "eval_runtime": 316.2483,
+      "eval_samples_per_second": 7.529,
+      "eval_steps_per_second": 0.942,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1734305355490918e+17,
+  "total_flos": 1.4074574120209613e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null