Training in progress, step 50200, checkpoint

last-checkpoint/README.md

@@ -1295,6 +1295,10 @@ You can finetune this model on your own dataset.
 | 0.8818 | 49900 | 0.2912        |
 | 0.8826 | 49950 | 0.2853        |
 | 0.8835 | 50000 | 0.3212        |
+| 0.8844 | 50050 | 0.3399        |
+| 0.8853 | 50100 | 0.3104        |
+| 0.8862 | 50150 | 0.368         |
+| 0.8871 | 50200 | 0.2848        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f629f9c4d9b3dfe15298ca42cf535d9537f9d84496ead633516c3f55df659809
+oid sha256:832b902e0fe022fef9cf3e9c3121c2fef0fa24fcbf8488a9cdbb81608e3c7db7
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82a5e0de80f3319e9bcb41ff6fcaf27ef7f48f3c5947829a81867a4d0d22eced
+oid sha256:146ff956fa4854ee7e070302bc46d20219774de158993ea087895544f881af40
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39be9337bc1edfc554e8e83920537fc1f1ac1fb64502256befd2c768cb7272f2
+oid sha256:0a89f1ae855fe394d47db931fc0083ae8bdcb1b72bbe34b1c88a5de1f09827b7
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05900a01ed21b7d3fe65d7b48e29dc049394fbc9a57676739fac72875cfe1dad
+oid sha256:cbc8c4b0c63d5380ba075a90ba10318e03e7b9bf88808901ab396ecc55b1ae6b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f94f189d019244fe1bc7202740eb1c5db8cec176873eb287a31349f77949d54f
+oid sha256:c6400bb8657149255aa24266b64f7fcdf0a428df1c18993fd61a2168a5c57c5d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8835327172165185,
+  "epoch": 0.8870668480853846,
   "eval_steps": 500,
-  "global_step": 50000,
+  "global_step": 50200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7008,6 +7008,34 @@
       "learning_rate": 6.4901533447212895e-06,
       "loss": 0.3212,
       "step": 50000
+    },
+    {
+      "epoch": 0.884416249933735,
+      "grad_norm": 2.2164740562438965,
+      "learning_rate": 6.441067326382753e-06,
+      "loss": 0.3399,
+      "step": 50050
+    },
+    {
+      "epoch": 0.8852997826509515,
+      "grad_norm": 3.567988157272339,
+      "learning_rate": 6.391981308044218e-06,
+      "loss": 0.3104,
+      "step": 50100
+    },
+    {
+      "epoch": 0.8861833153681681,
+      "grad_norm": 1.5539664030075073,
+      "learning_rate": 6.34289528970568e-06,
+      "loss": 0.368,
+      "step": 50150
+    },
+    {
+      "epoch": 0.8870668480853846,
+      "grad_norm": 1.6674470901489258,
+      "learning_rate": 6.293809271367145e-06,
+      "loss": 0.2848,
+      "step": 50200
     }
   ],
   "logging_steps": 50,