Training in progress, step 24600, checkpoint

last-checkpoint/README.md

@@ -1515,6 +1515,10 @@ You can finetune this model on your own dataset.
 | 0.4294 | 24300 | 0.3417        |
 | 0.4303 | 24350 | 0.2909        |
 | 0.4312 | 24400 | 0.2871        |
+| 0.4320 | 24450 | 0.3929        |
+| 0.4329 | 24500 | 0.278         |
+| 0.4338 | 24550 | 0.4386        |
+| 0.4347 | 24600 | 0.4193        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38d401f5ea89e305e6df80090c6dd502f091f942a1c6fd6198f15360577d242
+oid sha256:a5f521883c24fa0c5ef0d5496aed171da0d0aaf9518af226eda7a0624fd83f31
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee417ff7164269027bc0f8dbaecd3a447bcdaf2df6f366192998237eb82980f
+oid sha256:c7de91b8f4b5f9afea018786d14544bdbf97444a26a9894a6f78562cca048760
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84b0651531962a4d1fe7da7104f596909a3f9f4635a3127767128f052a6125b9
+oid sha256:c2902ca5c9eba1cc8519ae73c2f7885738abfe1dc8e6001f50fb19761dc55e0b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6968679df555ba9a784a9188bf0ef6e39006e81ae9b7d0ac31431b960b33cd5f
+oid sha256:12b33249ab6bab1e060a0a22477da48a7f7b43ecee2e64e0ef287ea0d9219a4d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983738f386fa95d07dae8b199fac4c31ae7f3aaf02a8d2d99fd9db8f93f6cabe
+oid sha256:074a86f28f57ef8a2c132a776cf6cef5fdfebd08cc63459240ea25fb180b3188
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.431163966001661,
+  "epoch": 0.43469809687052713,
   "eval_steps": 500,
-  "global_step": 24400,
+  "global_step": 24600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3424,6 +3424,34 @@
       "learning_rate": 3.16104140896507e-05,
       "loss": 0.2871,
       "step": 24400
+    },
+    {
+      "epoch": 0.43204749871887754,
+      "grad_norm": 1.5249110460281372,
+      "learning_rate": 3.156132807131217e-05,
+      "loss": 0.3929,
+      "step": 24450
+    },
+    {
+      "epoch": 0.43293103143609407,
+      "grad_norm": 1.2778598070144653,
+      "learning_rate": 3.151224205297363e-05,
+      "loss": 0.278,
+      "step": 24500
+    },
+    {
+      "epoch": 0.4338145641533106,
+      "grad_norm": 3.55033278465271,
+      "learning_rate": 3.1463156034635096e-05,
+      "loss": 0.4386,
+      "step": 24550
+    },
+    {
+      "epoch": 0.43469809687052713,
+      "grad_norm": 1.4700381755828857,
+      "learning_rate": 3.141407001629656e-05,
+      "loss": 0.4193,
+      "step": 24600
     }
   ],
   "logging_steps": 50,