Training in progress, step 25200, checkpoint

last-checkpoint/README.md

@@ -1527,6 +1527,10 @@ You can finetune this model on your own dataset.
 | 0.4400 | 24900 | 0.3627        |
 | 0.4409 | 24950 | 0.3403        |
 | 0.4418 | 25000 | 0.349         |
+| 0.4426 | 25050 | 0.3527        |
+| 0.4435 | 25100 | 0.3773        |
+| 0.4444 | 25150 | 0.3372        |
+| 0.4453 | 25200 | 0.3178        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c918763161ef97595d842f5ece99f90f7e2d5c63553b5885b1b713c586346cb
+oid sha256:841fdf3c58c8f29d1dbc4b6aa518d6d4f0e4c702d0d79eae99a7a6f05440afb8
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2d4c0d01edfc84864109bdf63e9e6759160821e7f74bce54c3dd8f76c5c354
+oid sha256:1d042b648040ac616e95ada7c18231cfcd360f4f2b7dea533dbe8440f0bfa84b
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff90076aa78d50e354ece849a9ec75faaeba4749aa46cf87013a8cdd9500738
+oid sha256:b3ad48efbb9bf93a84390a5aea5643acbd41bf262a8aa17ab3278f0f314a581a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91f230a75508cfcca80f84ab75240887cadf7dc70757ef443e6fd51570573208
+oid sha256:b8f8fa593fe1292958817d4226b917c242a5dd7ed49104de560771ecc5cb6968
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564986836922b13667f6dbb900106ce5d9e6e89596249b3bb5bd3d5d4f5e8480
+oid sha256:f8139c38e3bba457a10055977964d7aab9920cd7bb0ccf9d0c0ca174f5b19226
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.44176635860825925,
+  "epoch": 0.44530048947712536,
   "eval_steps": 500,
-  "global_step": 25000,
+  "global_step": 25200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3508,6 +3508,34 @@
       "learning_rate": 3.1021381869588265e-05,
       "loss": 0.349,
       "step": 25000
+    },
+    {
+      "epoch": 0.4426498913254758,
+      "grad_norm": 1.4080630540847778,
+      "learning_rate": 3.0972295851249736e-05,
+      "loss": 0.3527,
+      "step": 25050
+    },
+    {
+      "epoch": 0.4435334240426923,
+      "grad_norm": 1.7197438478469849,
+      "learning_rate": 3.0923209832911194e-05,
+      "loss": 0.3773,
+      "step": 25100
+    },
+    {
+      "epoch": 0.44441695675990883,
+      "grad_norm": 1.5831055641174316,
+      "learning_rate": 3.087510553493943e-05,
+      "loss": 0.3372,
+      "step": 25150
+    },
+    {
+      "epoch": 0.44530048947712536,
+      "grad_norm": 1.7535090446472168,
+      "learning_rate": 3.082601951660089e-05,
+      "loss": 0.3178,
+      "step": 25200
     }
   ],
   "logging_steps": 50,