Training in progress, step 50000, checkpoint

last-checkpoint/README.md

@@ -1187,6 +1187,8 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
+<details><summary>Click to expand</summary>
+
 | Epoch  | Step  | Training Loss |
 |:------:|:-----:|:-------------:|
 | 0.7925 | 44850 | 0.25          |
@@ -1289,7 +1291,12 @@ You can finetune this model on your own dataset.
 | 0.8782 | 49700 | 0.267         |
 | 0.8791 | 49750 | 0.2599        |
 | 0.8800 | 49800 | 0.3226        |
+| 0.8809 | 49850 | 0.3516        |
+| 0.8818 | 49900 | 0.2912        |
+| 0.8826 | 49950 | 0.2853        |
+| 0.8835 | 50000 | 0.3212        |
 
+</details>
 
 ### Framework Versions
 - Python: 3.11.13

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2d369eb5785f37e695387aeb0f0e1b88aba7649dea47063848b806090ff91f
+oid sha256:f629f9c4d9b3dfe15298ca42cf535d9537f9d84496ead633516c3f55df659809
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c88873a80431132be5b9a6198db1d2eb68145fe27f94342674f074b433cbd62
+oid sha256:82a5e0de80f3319e9bcb41ff6fcaf27ef7f48f3c5947829a81867a4d0d22eced
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c031c47895ee65720a29aa486037b758096a0c008e8c7d3bf0a06b848dd598
+oid sha256:39be9337bc1edfc554e8e83920537fc1f1ac1fb64502256befd2c768cb7272f2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ce6fbeef0ab2e0cecf23435bfa5221dc56a6ce59fe8d9b84d1e42bcc5d69c4
+oid sha256:05900a01ed21b7d3fe65d7b48e29dc049394fbc9a57676739fac72875cfe1dad
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd200196e0f200dd4627f60d44a82669aaadc601edaa64b9c6e1ddba3c662c9
+oid sha256:f94f189d019244fe1bc7202740eb1c5db8cec176873eb287a31349f77949d54f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8799985863476525,
+  "epoch": 0.8835327172165185,
   "eval_steps": 500,
-  "global_step": 49800,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6980,6 +6980,34 @@
       "learning_rate": 6.686497418075435e-06,
       "loss": 0.3226,
       "step": 49800
+    },
+    {
+      "epoch": 0.880882119064869,
+      "grad_norm": 1.385986089706421,
+      "learning_rate": 6.6374113997369e-06,
+      "loss": 0.3516,
+      "step": 49850
+    },
+    {
+      "epoch": 0.8817656517820854,
+      "grad_norm": 1.4890649318695068,
+      "learning_rate": 6.588325381398362e-06,
+      "loss": 0.2912,
+      "step": 49900
+    },
+    {
+      "epoch": 0.882649184499302,
+      "grad_norm": 2.459829807281494,
+      "learning_rate": 6.5392393630598265e-06,
+      "loss": 0.2853,
+      "step": 49950
+    },
+    {
+      "epoch": 0.8835327172165185,
+      "grad_norm": 1.6274219751358032,
+      "learning_rate": 6.4901533447212895e-06,
+      "loss": 0.3212,
+      "step": 50000
     }
   ],
   "logging_steps": 50,