Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65f5641a3878409a50fd2003307bc282aa33e730c06f5c0475bc9f7078a53ec
+oid sha256:8685ff629a34869c8d5eb22b3521c725184d3150239cee97f3eb49ee80d47381
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332c5d0453b85d7f2cb4a4ea222289a3a1443e88882d07f4a6d3032659590f15
+oid sha256:2e85141c3ffe11c0988ae800cdc85957a2e936879e02f3d9685e781bbe6de3d7
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390cfa0e48621cb6efdad1de5fca72660b371d8ad0395431856a239156fe719f
+oid sha256:ac62bace84129b1f59df2d2cdbf4780ec266f325b6f48c5bdeb90f98f6608355
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13712047012732614,
+  "epoch": 0.15670910871694418,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 35.885,
       "eval_steps_per_second": 4.507,
       "step": 35
+    },
+    {
+      "epoch": 0.14103819784524976,
+      "grad_norm": 0.5592698454856873,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.294,
+      "step": 36
+    },
+    {
+      "epoch": 0.15279138099902057,
+      "grad_norm": 0.5278225541114807,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.2837,
+      "step": 39
+    },
+    {
+      "epoch": 0.15670910871694418,
+      "eval_loss": 0.30300983786582947,
+      "eval_runtime": 11.9966,
+      "eval_samples_per_second": 35.844,
+      "eval_steps_per_second": 4.501,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9525065573990400.0,
+  "total_flos": 1.08857892274176e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null