Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef374d3fe73aa999467d1128baacc374ba01737d6cf572894cf41c93310efcc
+oid sha256:b9548be918a76964a521458a2e9ed3011caca9853666e90e206f4dcba73d0784
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3815439df283b4fd2e14687524debf23fc769786b24546cd6d84e34ab1a201e
+oid sha256:23d783730b5ca8bf7f39fa6ac47bd8918bc77016beb37fc646fcab53059f45e5
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8daed718fea013cdb528d1985afb8df17afb47a94059b22927f669508f3a08
+oid sha256:37630be80c2425b6ac33bd2111314b135f5ac722f8a350523e1183f23b3e5231
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3340f7450dfdcc50bc6d0d4bdc92576c596624d9dcaaa9f3897735b5ae5c8995
+oid sha256:472aa51ea417ec2f8d7088b0675b82474cb1937368e568b322f10f11cc431156
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fa739c7e2b2fa1210957930f1a841de61df31689db1101ecfa386d28aaa886
+oid sha256:f36aa6f1e331ca717ce0e8beaea8098f41984f60917e891708be3c61b7094e45
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77564156cb82864d91dae341bd260a8bf1eb8fe26265ef0a219dec782a8541de
+oid sha256:6542abae196e2321703ec880950100720e1c13106a6e47d2df2999a1022eca87
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01944684528954192,
+  "epoch": 0.023336214347450302,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 118.016,
       "eval_steps_per_second": 3.694,
       "step": 45
+    },
+    {
+      "epoch": 0.020743301642178046,
+      "grad_norm": 0.9587317705154419,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.5692,
+      "step": 48
+    },
+    {
+      "epoch": 0.022039757994814176,
+      "grad_norm": 0.9989524483680725,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.5135,
+      "step": 51
+    },
+    {
+      "epoch": 0.023336214347450302,
+      "grad_norm": 1.1253865957260132,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.5211,
+      "step": 54
+    },
+    {
+      "epoch": 0.023336214347450302,
+      "eval_loss": 1.503990888595581,
+      "eval_runtime": 132.1403,
+      "eval_samples_per_second": 117.973,
+      "eval_steps_per_second": 3.693,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4235024213252506e+17,
+  "total_flos": 1.708001838843822e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null