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:ea6c3af5a3c18730ee84bd3e09513f64a13553bf4e860fe49ab3aa77d0c22791
+oid sha256:2e97685a680e00eb243b2de6164e557cb4cbaae2aeaddcf05007c29a4870d9aa
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a855c6fdf138a6025c81fe0760745d20bea312d607c787d6badc6e44af35fa23
+oid sha256:ecb20e707a68acd451bf36505255106de04659955d35fb24ab09bf69f81228d6
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d27ce7a601cd78cb97963f63e9fbbcc61a8db9fb6cb91beeacdc669c7c402c
+oid sha256:5b7272202dc9e52e095afc89ac33aefc2356f157fa52f53e471a837339830a02
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8573817db109f46e2d57e1f657726178cbc11334aba71ff27744c0e4089d2623
+oid sha256:7cf140526b08395dbd0793ca343f0f70c5fb866a714c27208d9b9b1ce1a60172
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0022865542444163163,
+  "epoch": 0.0045731084888326326,
   "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": 26.068,
       "eval_steps_per_second": 13.034,
       "step": 14
+    },
+    {
+      "epoch": 0.0032665060634518802,
+      "grad_norm": 3.385493278503418,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 9.6198,
+      "step": 20
+    },
+    {
+      "epoch": 0.0045731084888326326,
+      "eval_loss": 2.3797528743743896,
+      "eval_runtime": 98.9153,
+      "eval_samples_per_second": 26.063,
+      "eval_steps_per_second": 13.031,
+      "step": 28
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2605998787264512.0,
+  "total_flos": 5049122650324992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null