Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a1f11dc4ba20dbf66062992b5e16c8148254697644a3dac2a641c0f0bf80ada
+oid sha256:d847ebcfcc53f0ef1124e6aca7279725f9aca50186e00f793d1db9769ce766e6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06b1eede5305ad47241c3855f50fe14eddecf8c34d154695cebd0c9227a69be
+oid sha256:2142d3692f1d3dccfc9b0a79467dada72aa55509229ec94d32f11279fbd3b992
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049c306a67a9bf5a5c55385c4c3d8c96f923249cec6471081b080d3935493ea9
+oid sha256:1e541f7aee48cc7ed448f7f7a74ac3c336f54829308a589e6265d77e6e70e6da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.64,
   "eval_steps": 3,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 15.261,
       "eval_steps_per_second": 7.631,
       "step": 3
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 10.887984275817871,
+      "learning_rate": 5e-05,
+      "loss": 6.0911,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 5.283447742462158,
+      "eval_runtime": 0.4178,
+      "eval_samples_per_second": 14.361,
+      "eval_steps_per_second": 7.18,
+      "step": 6
     }
   ],
   "logging_steps": 5,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 739825699258368.0,
+  "total_flos": 1479651398516736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null