Training in progress, step 40000, checkpoint

last-checkpoint/README.md

@@ -1315,6 +1315,10 @@ You can finetune this model on your own dataset.
 | 0.7015 | 39700 | 0.2503        |
 | 0.7024 | 39750 | 0.3593        |
 | 0.7033 | 39800 | 0.2933        |
+| 0.7042 | 39850 | 0.3565        |
+| 0.7051 | 39900 | 0.2838        |
+| 0.7059 | 39950 | 0.2604        |
+| 0.7068 | 40000 | 0.2286        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e3850ec81152c770c1287a58b16a081486e29359e4ddd6242aec24390a1095
+oid sha256:4c7b416494c6b7505e7fa6eedc83168208b62d0c9428d6cb56bafda1f34f24d9
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6982d0068dc488d659ee3ea863838224b7f84d13622881dc74bd17ff8174f7
+oid sha256:be35770dca7605f30d91ba6120504ca43247cfeb02e3d77916fdb2cc3dbfaba0
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf03aa505c305170adf85ee73ee56bc32702b85d7c76a3b04c609b9202b5754a
+oid sha256:cbf81c04ea51b7be585fb96d50f50e5dc3906dc50f1775c970264b1a4d1eefeb
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71d3db821ebc15469e7d3f1fde03936d361471a5f2cb1a21d3669fed48601709
+oid sha256:48c793708154234024ec2f24e89dee0955c43c3c92b7c5bd216b3138f06c4acd
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2795a9eb0d0e9717e4fddeb0ae82fb57c15cae7d137da34c1144f8d3ca3cd594
+oid sha256:eec77879460249ba1a47baa584385b3461e6077b0f1f35d15287420496875963
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7032920429043488,
+  "epoch": 0.7068261737732148,
   "eval_steps": 500,
-  "global_step": 39800,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5580,6 +5580,34 @@
       "learning_rate": 1.6498792483948873e-05,
       "loss": 0.2933,
       "step": 39800
+    },
+    {
+      "epoch": 0.7041755756215653,
+      "grad_norm": 1.1238136291503906,
+      "learning_rate": 1.6449706465610338e-05,
+      "loss": 0.3565,
+      "step": 39850
+    },
+    {
+      "epoch": 0.7050591083387818,
+      "grad_norm": 1.5694066286087036,
+      "learning_rate": 1.64006204472718e-05,
+      "loss": 0.2838,
+      "step": 39900
+    },
+    {
+      "epoch": 0.7059426410559984,
+      "grad_norm": 1.808310866355896,
+      "learning_rate": 1.6351534428933263e-05,
+      "loss": 0.2604,
+      "step": 39950
+    },
+    {
+      "epoch": 0.7068261737732148,
+      "grad_norm": 1.6668068170547485,
+      "learning_rate": 1.6302448410594725e-05,
+      "loss": 0.2286,
+      "step": 40000
     }
   ],
   "logging_steps": 50,