Training in progress, step 5700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:551f265b0824afe04aca693b6dea37fd5b135be5b8dccb283b485991e4dad3cf
+oid sha256:59d1f0fae334930ed8079d00f44c27d89643fc0441c8182fd6c384af44315cb0
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57e143f333860daa20b388b6223f6ddf41f78b6f0260df5e7f84606866d22b2
+oid sha256:dbf70e69484ef4930af6adb3972e5d151c2e40923012c6e59178aa5b08fc0f62
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346e59e0611ec165950f793dc7bab0e7711af8e5091b452f221d2a71732c2269
+oid sha256:8e9d9c35639598e4263e7ecc7045b5427db463c314e637805772291b54322a1a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d2f36af1b7bb2b6336bf3a3f577dcb5c5a5a76d17401f059ff27c28f1ca2cc
+oid sha256:0d31553c5ae8347a198cb4d56280c26db3af2cfa5039328d122439d6a52e0f08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4496,
+  "epoch": 0.456,
   "eval_steps": 500,
-  "global_step": 5620,
+  "global_step": 5700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1974,6 +1974,34 @@
       "learning_rate": 2.5310626050032873e-05,
       "loss": 3.5598,
       "step": 5620
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 21.44734764099121,
+      "learning_rate": 2.527528728730582e-05,
+      "loss": 3.5189,
+      "step": 5640
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 26.825183868408203,
+      "learning_rate": 2.5239840741677307e-05,
+      "loss": 3.6052,
+      "step": 5660
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 29.19519805908203,
+      "learning_rate": 2.5204286784964823e-05,
+      "loss": 3.4724,
+      "step": 5680
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 37.9902229309082,
+      "learning_rate": 2.516862579011255e-05,
+      "loss": 3.3665,
+      "step": 5700
     }
   ],
   "logging_steps": 20,
@@ -1981,7 +2009,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3302567908179968e+16,
+  "total_flos": 1.3500387561013248e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null