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:a932a0faac4b641bf72ce63748ddde2dd62fcaf2789e90f0d14249273ee7e352
+oid sha256:c75aea2cb6864ef76771888ea30ca51b7823e102dd0050fd5ea5fa1cae67064d
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e28fe608ae6053ba54c94c3375caaf9cf2499321d53b93bfafae7f3423f342e6
+oid sha256:fe436795477c2ac2e8b8987ca266618f4b59acddcb78d9db181303ebd5ab8ce2
 size 4830714

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016983c686e3f6559a80f761a5aee2d676a2ab199aac6efd1774aeda9637b12d
+oid sha256:639cadb2d5c8341c00ec24a9d5b07827b6952f480b2b56a327b15dcedfc3c4d1
 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": 0.020633750921149593,
+  "epoch": 0.023581429624170966,
   "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": 135.008,
       "eval_steps_per_second": 16.917,
       "step": 35
+    },
+    {
+      "epoch": 0.021223286661753868,
+      "grad_norm": 0.3654229938983917,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 11.8738,
+      "step": 36
+    },
+    {
+      "epoch": 0.02299189388356669,
+      "grad_norm": 0.3954028785228729,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 11.8702,
+      "step": 39
+    },
+    {
+      "epoch": 0.023581429624170966,
+      "eval_loss": 11.871051788330078,
+      "eval_runtime": 21.0709,
+      "eval_samples_per_second": 135.59,
+      "eval_steps_per_second": 16.99,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 38562693120000.0,
+  "total_flos": 44071649280000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null