Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5fd1bc231ddaa08e3b126ff7e991a61f69316f262668798920494e1cfd3eb74
+oid sha256:a3ac86204857a0a774035d333113808e7584e104373b0d35bb5b56ff994d2249
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb72dcf3db558b98338cf4438a4ae01dfa9fdb1e58f955536ef8ca0579409ec0
+oid sha256:b971e5d0b49df20bebeea825312012550371f73c1855a5d2141fba7fe9e5ee60
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3bee6e11761e71ad6005f6650cd86d99463f2e69e0f2e209868fa0b6569d716
+oid sha256:fdafc4e4214ad556e2269e242d02ee4f3daa32347c3db3d3f483712d3de6ff85
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23617619493908154,
+  "epoch": 0.26991565135895035,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 34.598,
       "eval_steps_per_second": 4.382,
       "step": 63
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 0.22800111770629883,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 1.9253,
+      "step": 66
+    },
+    {
+      "epoch": 0.25866916588566075,
+      "grad_norm": 0.21982352435588837,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 1.8411,
+      "step": 69
+    },
+    {
+      "epoch": 0.26991565135895035,
+      "grad_norm": 0.20461618900299072,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 1.955,
+      "step": 72
+    },
+    {
+      "epoch": 0.26991565135895035,
+      "eval_loss": 1.9237501621246338,
+      "eval_runtime": 13.0394,
+      "eval_samples_per_second": 34.511,
+      "eval_steps_per_second": 4.371,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0575118778433536e+16,
+  "total_flos": 2.361735423983616e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null