Training in progress, step 38800, 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 |
 |:------:|:-----:|:-------------:|
 | 0.5946 | 33650 | 0.2952        |
@@ -1289,7 +1291,12 @@ You can finetune this model on your own dataset.
 | 0.6803 | 38500 | 0.3343        |
 | 0.6812 | 38550 | 0.2411        |
 | 0.6821 | 38600 | 0.2641        |
+| 0.6830 | 38650 | 0.3673        |
+| 0.6839 | 38700 | 0.3456        |
+| 0.6847 | 38750 | 0.2554        |
+| 0.6856 | 38800 | 0.2289        |
 
+</details>
 
 ### Framework Versions
 - Python: 3.11.13

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9411645577be70106bcbbb74c24716149dda56d2f3e7a581b79fdcdc3ed41249
+oid sha256:2ee25825aff4959fe5e0a2781134b9e96da88058dbf8690e35445a67610af73c
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e25051f1943dbef57f8ebb6e352941619afea10b29f67080e5c0e931b5bcec
+oid sha256:d050884a4252ba97d0bb88532a3164adec318594e47284644fd45a2c9c9a7cc4
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:383863d97b21487295b0694693e6eddac2a40d27317755b362907c5201542167
+oid sha256:0a8540dc3b35a3094fd45d5158b8f89bcbd7079e7ed16edbb02c263246cd8ebc
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c584d258d651b75cc67fda371e341a5dcb6a64a5f3ef27cdd2725022fe4132e
+oid sha256:64aa6796f2a5b524134346b6756db7d56f573132ef410dc4c37c3f8db2fcd06d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f4be9189e6431a4a4fa709ab0080899a72a8630fa75a31259beca939bff08e
+oid sha256:ac6c315739e8675a2e6e8b7f539ac0cd78a1153ea0c4434aeaf8094027721b1e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6820872576911523,
+  "epoch": 0.6856213885600184,
   "eval_steps": 500,
-  "global_step": 38600,
+  "global_step": 38800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5412,6 +5412,34 @@
       "learning_rate": 1.7675875203706975e-05,
       "loss": 0.2641,
       "step": 38600
+    },
+    {
+      "epoch": 0.6829707904083688,
+      "grad_norm": 1.6398324966430664,
+      "learning_rate": 1.762777090573521e-05,
+      "loss": 0.3673,
+      "step": 38650
+    },
+    {
+      "epoch": 0.6838543231255854,
+      "grad_norm": 1.5645078420639038,
+      "learning_rate": 1.7578684887396674e-05,
+      "loss": 0.3456,
+      "step": 38700
+    },
+    {
+      "epoch": 0.6847378558428019,
+      "grad_norm": 1.4957185983657837,
+      "learning_rate": 1.752959886905814e-05,
+      "loss": 0.2554,
+      "step": 38750
+    },
+    {
+      "epoch": 0.6856213885600184,
+      "grad_norm": 1.5689042806625366,
+      "learning_rate": 1.7480512850719603e-05,
+      "loss": 0.2289,
+      "step": 38800
     }
   ],
   "logging_steps": 50,