Training in progress, step 6280, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5f6360dfa9c2a789402315eb51b17d5c5437a5e36f3a7f4a8ff1180c978bd7
+oid sha256:4952d07d35404125ac82a69ff1d2b691b555ce36f8f5e2491332621aa761003d
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef67c02a39ed9ea9db9f9f9072b9280130156e0f2c168f6d3433e11a691906a0
+oid sha256:8dfa581ec2b543e12a4d9e7daa6a74d185441160dd1412bf1875fce58548b340
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059a6e0450ff9489b2174c9501bf25eb13b58d453dbd5dc4fed1c213de807539
+oid sha256:c20249241b6c1615d63c46164c68a0aefa907c40365a5dc082bbe417fdd12bf6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1291563f0ece66a71bc509a68887ccf6e08065ec53a4ab16c369d685623ef0fa
+oid sha256:2ac175a77f9ab524825431337f25ea7bdd98b98a7ae16ff30a1d8c19f59c4b3f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4928,
+  "epoch": 0.5024,
   "eval_steps": 500,
-  "global_step": 6160,
+  "global_step": 6280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2163,6 +2163,48 @@
       "learning_rate": 2.431975467831853e-05,
       "loss": 3.4445,
       "step": 6160
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 39.8357048034668,
+      "learning_rate": 2.4281639511169457e-05,
+      "loss": 3.5702,
+      "step": 6180
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 31.746124267578125,
+      "learning_rate": 2.424342698401391e-05,
+      "loss": 3.4539,
+      "step": 6200
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 53.038482666015625,
+      "learning_rate": 2.4205117497683213e-05,
+      "loss": 3.5491,
+      "step": 6220
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 28.155752182006836,
+      "learning_rate": 2.4166711454025754e-05,
+      "loss": 3.4353,
+      "step": 6240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 42.623130798339844,
+      "learning_rate": 2.4128209255902753e-05,
+      "loss": 3.4348,
+      "step": 6260
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 44.352596282958984,
+      "learning_rate": 2.408961130718405e-05,
+      "loss": 3.4637,
+      "step": 6280
     }
   ],
   "logging_steps": 20,
@@ -2170,7 +2212,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.4563889634902016e+16,
+  "total_flos": 1.4845134723416064e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null