Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62684bf0eec044fb0a9a60709738b246e464592f15969ca36cbd206f6a65b9ba
+oid sha256:2453b22f077c9e633155bde5a44c5a5c92ddb254cf0fe9e618e76bbd38133b08
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba68244a466bdf0b5d267bb6e43fc63894926d785d1e87c91c9b950737d9101
+oid sha256:e79d76de3a27d79eb105caffe8c2ea0c9c2c134159ec637025bffdd723a230d4
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60379b7ec7fc50400ed25c0728f72548d8aacb996c92794cc4fa8f2026f83ce9
+oid sha256:ade06f0db401bf7db7e4bf579716041b8a433a97a601335efdecad97edb03945
 size 14244

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": 0.006502694403468103,
+  "epoch": 0.007586476804046121,
   "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": 7.035,
       "eval_steps_per_second": 0.88,
       "step": 54
+    },
+    {
+      "epoch": 0.006863955203660776,
+      "grad_norm": 14.141239166259766,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 5.6544,
+      "step": 57
+    },
+    {
+      "epoch": 0.007225216003853448,
+      "grad_norm": 13.24157428741455,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 5.7787,
+      "step": 60
+    },
+    {
+      "epoch": 0.007586476804046121,
+      "grad_norm": 13.354693412780762,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 5.9927,
+      "step": 63
+    },
+    {
+      "epoch": 0.007586476804046121,
+      "eval_loss": 1.4332555532455444,
+      "eval_runtime": 1985.8578,
+      "eval_samples_per_second": 7.043,
+      "eval_steps_per_second": 0.881,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.518761456613458e+17,
+  "total_flos": 1.7718883660490342e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null