Training in progress, step 6480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4edb15d0e1b52d3bdcfb17044d4d5c2d1bc11a9b89494c965b286c71d0b836fb
+oid sha256:9a30a008dae072195fc28eccb26ab5bd9eb4cd09d5723d01bd5eef06c2f548cc
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ef6fc0399c4259225d888ed2a17fdb3c50a5cc0882ff3768013ef0d4c4d8dd
+oid sha256:f4c548ed51d455157bc66ff27bbdf7cc0ece0b25d6b6583885fd9166381cfa1f
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3530b4cc0dc079d6d7d3f5eab27538955528f7a1c8ce95515130807a04042a5c
+oid sha256:ab96dece0057048172e676099e7a2287bdd92408cbb9619002ab46488332801f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b967ab9913addda1efeba2ec99f16fcff83f1b776c306d39cf95d5b4425c3f06
+oid sha256:f067d06bd847c479f71bde77c89318403c2c2dbcdb7f1dd86724b30b9fac060c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5168,
+  "epoch": 0.5184,
   "eval_steps": 500,
-  "global_step": 6460,
+  "global_step": 6480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2268,6 +2268,13 @@
       "learning_rate": 2.3737988124226834e-05,
       "loss": 3.422,
       "step": 6460
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 28.162084579467773,
+      "learning_rate": 2.3698455101245052e-05,
+      "loss": 3.5403,
+      "step": 6480
     }
   ],
   "logging_steps": 20,
@@ -2275,7 +2282,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5247728882548736e+16,
+  "total_flos": 1.5298774882516992e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null