Training in progress, step 15600, checkpoint

last-checkpoint/README.md

@@ -1335,6 +1335,10 @@ You can finetune this model on your own dataset.
 | 0.2704 | 15300 | 0.3625        |
 | 0.2712 | 15350 | 0.4088        |
 | 0.2721 | 15400 | 0.4126        |
+| 0.2730 | 15450 | 0.4662        |
+| 0.2739 | 15500 | 0.3889        |
+| 0.2748 | 15550 | 0.3618        |
+| 0.2757 | 15600 | 0.4126        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b7cbbd38574c6f644e5905e423ba3800976ac9f64a45f988dc986784e2d3c3
+oid sha256:36f741855bfd9ab9855541a5740f7ebf89eb5ff81a18f782d3409b6a6441f247
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59832a48408250a010ff3eb06e85c9c23c780a3bb973e06cb22542561bf9a69f
+oid sha256:f354c3d85cd72229183ba1225666edf02dbe0f02e60066712ba24c7167587d87
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6316675c87304b6a869a973492a1f7d1ddc0dc21462eba7caa9df8741680bf41
+oid sha256:ece4d2ab35a1b635eb36bee8c77e304be4a94349bd773a556811f31851337605
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2c8f643d81596fc9fb1ef1c4a6a6344df33962576f180d2561ffde1db918fd
+oid sha256:ab0c87524374314917bf4b3aa26c95868e23e32a6021e3f7a331e9d46fadb1d1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e73f97c88ee773669644b85dc0a5424564108e9b40aaaed168c2d9eee5ed22d
+oid sha256:f7630ebf9456fffd04ad85b9111cf3e42b6fca916321363c383a4caf1724f287
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2721280769026877,
+  "epoch": 0.27566220777155376,
   "eval_steps": 500,
-  "global_step": 15400,
+  "global_step": 15600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2164,6 +2164,34 @@
       "learning_rate": 4.0441970509120186e-05,
       "loss": 0.4126,
       "step": 15400
+    },
+    {
+      "epoch": 0.2730116096199042,
+      "grad_norm": 1.7254865169525146,
+      "learning_rate": 4.0392884490781644e-05,
+      "loss": 0.4662,
+      "step": 15450
+    },
+    {
+      "epoch": 0.27389514233712076,
+      "grad_norm": 4.502954483032227,
+      "learning_rate": 4.034379847244311e-05,
+      "loss": 0.3889,
+      "step": 15500
+    },
+    {
+      "epoch": 0.2747786750543373,
+      "grad_norm": 2.4406206607818604,
+      "learning_rate": 4.029471245410458e-05,
+      "loss": 0.3618,
+      "step": 15550
+    },
+    {
+      "epoch": 0.27566220777155376,
+      "grad_norm": 1.6272777318954468,
+      "learning_rate": 4.024562643576604e-05,
+      "loss": 0.4126,
+      "step": 15600
     }
   ],
   "logging_steps": 50,