Training in progress, step 25000, checkpoint

last-checkpoint/README.md

@@ -1523,6 +1523,10 @@ You can finetune this model on your own dataset.
 | 0.4365 | 24700 | 0.3474        |
 | 0.4373 | 24750 | 0.3116        |
 | 0.4382 | 24800 | 0.2733        |
+| 0.4391 | 24850 | 0.3046        |
+| 0.4400 | 24900 | 0.3627        |
+| 0.4409 | 24950 | 0.3403        |
+| 0.4418 | 25000 | 0.349         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a6814f8b5ec1634bc957286eb983b49496dec8c06da38d5b609edfe4943162
+oid sha256:8c918763161ef97595d842f5ece99f90f7e2d5c63553b5885b1b713c586346cb
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5014e7c824b5bba9795a3854afd07633842628a9cdcb9a54a06ad696e1b4f903
+oid sha256:0c2d4c0d01edfc84864109bdf63e9e6759160821e7f74bce54c3dd8f76c5c354
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdc511f69d97de8443ad30f266ce1fb3539b806724de4144228eaca4248f565
+oid sha256:8ff90076aa78d50e354ece849a9ec75faaeba4749aa46cf87013a8cdd9500738
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335a5fd15f36238bc16955df172a43171379880e3bcb88eb14202c50efca1486
+oid sha256:91f230a75508cfcca80f84ab75240887cadf7dc70757ef443e6fd51570573208
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25f886cbcef3624ee21fe280a14d945057b01ddf68ca3820604e9ccd990e8d3
+oid sha256:564986836922b13667f6dbb900106ce5d9e6e89596249b3bb5bd3d5d4f5e8480
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4382322277393932,
+  "epoch": 0.44176635860825925,
   "eval_steps": 500,
-  "global_step": 24800,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3480,6 +3480,34 @@
       "learning_rate": 3.121772594294242e-05,
       "loss": 0.2733,
       "step": 24800
+    },
+    {
+      "epoch": 0.4391157604566097,
+      "grad_norm": 1.5642348527908325,
+      "learning_rate": 3.116863992460388e-05,
+      "loss": 0.3046,
+      "step": 24850
+    },
+    {
+      "epoch": 0.43999929317382624,
+      "grad_norm": 1.5843394994735718,
+      "learning_rate": 3.111955390626534e-05,
+      "loss": 0.3627,
+      "step": 24900
+    },
+    {
+      "epoch": 0.4408828258910427,
+      "grad_norm": 1.6260349750518799,
+      "learning_rate": 3.10704678879268e-05,
+      "loss": 0.3403,
+      "step": 24950
+    },
+    {
+      "epoch": 0.44176635860825925,
+      "grad_norm": 1.7742459774017334,
+      "learning_rate": 3.1021381869588265e-05,
+      "loss": 0.349,
+      "step": 25000
     }
   ],
   "logging_steps": 50,