Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8685ff629a34869c8d5eb22b3521c725184d3150239cee97f3eb49ee80d47381
+oid sha256:a0f0e2666ad7e0cb7fb0eb625dcaf977ae8fff84786b4a4318444a4e36f13437
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e85141c3ffe11c0988ae800cdc85957a2e936879e02f3d9685e781bbe6de3d7
+oid sha256:9877d1f4c1ff9a8ae75daa72900e8d0fc829e63feebe35ef748c85937b1f697b
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac62bace84129b1f59df2d2cdbf4780ec266f325b6f48c5bdeb90f98f6608355
+oid sha256:b956f62da7139d3f4858fad60add5a2c46a4a02ebd5eb322a02efcc280e59796
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15670910871694418,
+  "epoch": 0.1762977473065622,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 35.844,
       "eval_steps_per_second": 4.501,
       "step": 40
+    },
+    {
+      "epoch": 0.16454456415279137,
+      "grad_norm": 0.5927110910415649,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3451,
+      "step": 42
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "grad_norm": 0.5226899981498718,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2873,
+      "step": 45
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "eval_loss": 0.3025428354740143,
+      "eval_runtime": 11.995,
+      "eval_samples_per_second": 35.848,
+      "eval_steps_per_second": 4.502,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.08857892274176e+16,
+  "total_flos": 1.22465128808448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null