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:afee915f87f2e94742bb550655633d8ec6b805de369250a7eda0ae6982551dd1
+oid sha256:12dfebe2ebc3d3d86f49ad8af7de1d1742fdd66c5035bf8ebeb3c70a23f4eda8
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b435f298829f2671d87292a611d9ba1c4086cc08ffaad0ae7300dd43cd92de0e
+oid sha256:18009903aeaccf43b9772682889440d18ed8d1d8eb87408aa77309fc3cbf4766
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d14899a6fda525c1e04dcf859ac7775e84db61bc829198793b3cea5eac3dba2
+oid sha256:1650f09948b4ca5c34c8acf8bd0dadcc1d4bbda8a8b1879761e650714aff18b8
 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": 0.007002494638715042,
+  "epoch": 0.007877806468554422,
   "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": 23.686,
       "eval_steps_per_second": 2.962,
       "step": 40
+    },
+    {
+      "epoch": 0.007352619370650794,
+      "grad_norm": 7.458286285400391,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.022,
+      "step": 42
+    },
+    {
+      "epoch": 0.007877806468554422,
+      "grad_norm": 5.143349647521973,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1537,
+      "step": 45
+    },
+    {
+      "epoch": 0.007877806468554422,
+      "eval_loss": 0.9653515815734863,
+      "eval_runtime": 406.4439,
+      "eval_samples_per_second": 23.671,
+      "eval_steps_per_second": 2.96,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7011854123466752e+16,
+  "total_flos": 1.9091673279627264e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null