Training in progress, step 56000, checkpoint

last-checkpoint/README.md

@@ -1273,6 +1273,10 @@ You can finetune this model on your own dataset.
 | 0.9843 | 55700 | 0.2922        |
 | 0.9851 | 55750 | 0.2409        |
 | 0.9860 | 55800 | 0.2704        |
+| 0.9869 | 55850 | 0.2855        |
+| 0.9878 | 55900 | 0.241         |
+| 0.9887 | 55950 | 0.2616        |
+| 0.9896 | 56000 | 0.2572        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90fcb416e3f1fd9c1877f4daf0be2fc8df1e1250a64fe3f07aae6546f23d2ab0
+oid sha256:77ce30d7aacd666933a14d83cc737c586dcae579850f877da7309f9895799d43
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e61e9433fbd41b3556eca2c0125db34a8ece386095ac01a954bcccc5ae50de3
+oid sha256:8d280d8e79c740dc707e7398c5e14c4f2ad422cb187845da01e50e47c090ae44
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404572bee52c0f6fd3f51338bcd9d76b45287337ee0a6f0be420d6125dc37b05
+oid sha256:c072afea83c70b7165bf32b5c5585de459f967b6f4f050240893f3e9f57351d0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87465185b3464123ac777bc7dfe2dec56250d184ec4a7d3aafc9cf39b60be6dc
+oid sha256:4674ba66a393298737c507490cd48fcb412b9b21de3a1d3996a7109c47aaae95
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ccf2bc2593182b06063b40af4f602a3ba516c801f8e0f593c69740ab2da6ec
+oid sha256:9c1d493f6ec6785592b7a247d7ab39afb368b0e235cf1f0840677960dedafdad
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9860225124136347,
+  "epoch": 0.9895566432825007,
   "eval_steps": 500,
-  "global_step": 55800,
+  "global_step": 56000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7820,6 +7820,34 @@
       "learning_rate": 7.991203785513735e-07,
       "loss": 0.2704,
       "step": 55800
+    },
+    {
+      "epoch": 0.9869060451308512,
+      "grad_norm": 1.3643758296966553,
+      "learning_rate": 7.50034360212837e-07,
+      "loss": 0.2855,
+      "step": 55850
+    },
+    {
+      "epoch": 0.9877895778480678,
+      "grad_norm": 1.2211904525756836,
+      "learning_rate": 7.009483418743006e-07,
+      "loss": 0.241,
+      "step": 55900
+    },
+    {
+      "epoch": 0.9886731105652843,
+      "grad_norm": 3.049858570098877,
+      "learning_rate": 6.518623235357641e-07,
+      "loss": 0.2616,
+      "step": 55950
+    },
+    {
+      "epoch": 0.9895566432825007,
+      "grad_norm": 1.8196197748184204,
+      "learning_rate": 6.027763051972277e-07,
+      "loss": 0.2572,
+      "step": 56000
     }
   ],
   "logging_steps": 50,