Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9548be918a76964a521458a2e9ed3011caca9853666e90e206f4dcba73d0784
+oid sha256:b585f2a60f2db3a35c0d7b7cc533c321f1df235a63ff3c82b5892c8d16188c51
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d783730b5ca8bf7f39fa6ac47bd8918bc77016beb37fc646fcab53059f45e5
+oid sha256:5f60ddfaa146a3789227d36e98a430fffae6ea0fb1e931abcf889f6b5d501ccc
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37630be80c2425b6ac33bd2111314b135f5ac722f8a350523e1183f23b3e5231
+oid sha256:4e63bb9f2bfa1d26eb38d32080d6d804f940903caf7fa15263f0ac5442895ee5
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472aa51ea417ec2f8d7088b0675b82474cb1937368e568b322f10f11cc431156
+oid sha256:e8a7ec145f15caf0713e5375f269873814104cd79c2cf739b59a1d8b677e03cc
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36aa6f1e331ca717ce0e8beaea8098f41984f60917e891708be3c61b7094e45
+oid sha256:78a2b5a020cad2f971834c7b14e4df7bf8045ecc127082d0c15aa487f90c66ba
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6542abae196e2321703ec880950100720e1c13106a6e47d2df2999a1022eca87
+oid sha256:bbc60d99c48012f47aad5c29906cfb3e860cd7524e751af181350f61e372b80f
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.023336214347450302,
+  "epoch": 0.027225583405358685,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 117.973,
       "eval_steps_per_second": 3.693,
       "step": 54
+    },
+    {
+      "epoch": 0.024632670700086432,
+      "grad_norm": 0.997772753238678,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.5019,
+      "step": 57
+    },
+    {
+      "epoch": 0.02592912705272256,
+      "grad_norm": 0.9458330869674683,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.4898,
+      "step": 60
+    },
+    {
+      "epoch": 0.027225583405358685,
+      "grad_norm": 0.9065344929695129,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.5003,
+      "step": 63
+    },
+    {
+      "epoch": 0.027225583405358685,
+      "eval_loss": 1.4908527135849,
+      "eval_runtime": 132.1066,
+      "eval_samples_per_second": 118.003,
+      "eval_steps_per_second": 3.694,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.708001838843822e+17,
+  "total_flos": 1.992501267099812e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null