Training in progress, step 28, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bc2bc93174a85b9abba91ce61831280b2ef3a4324b66cd987106ade0cb40f0
+oid sha256:29224bf1041f09f6e7c2d9e0a44dfab51f6494985070725ef37636dadeba3810
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c6c709c306f35d17306a4d3161d342e0bc2a46284254a3af22c91e9e9a7b23
+oid sha256:3712724dd86148f5ba7c5e471ab0d26c44a9da928b871b730d33e34bb7100356
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d08e41ebbb66e79708b5de777505d052c85fac772c0f94d1232521b17b5cc165
+oid sha256:890ba72cf4c10aa73c7dc8ba7d8fdff2b076c6fc6e7d9e614b0d6db4aecb5104
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c7e21bc965f34fd3d72d9cb2881ca0e9f4bcb64151c1f8562417f8d5125510
+oid sha256:7ed58e5b5053e09a44cd1fe67ab0f07cc790b003abec6db1f957ea4f926e4423
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03708609271523179,
+  "epoch": 0.07417218543046358,
   "eval_steps": 14,
-  "global_step": 14,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 22.919,
       "eval_steps_per_second": 5.766,
       "step": 14
+    },
+    {
+      "epoch": 0.052980132450331126,
+      "grad_norm": 4.675541877746582,
+      "learning_rate": 0.0002,
+      "loss": 3.6315,
+      "step": 20
+    },
+    {
+      "epoch": 0.07417218543046358,
+      "eval_loss": 1.8080170154571533,
+      "eval_runtime": 6.9527,
+      "eval_samples_per_second": 22.869,
+      "eval_steps_per_second": 5.753,
+      "step": 28
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3094230419374080.0,
+  "total_flos": 6276867422158848.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null