Training in progress, step 40200, checkpoint

last-checkpoint/README.md

@@ -1319,6 +1319,10 @@ You can finetune this model on your own dataset.
 | 0.7051 | 39900 | 0.2838        |
 | 0.7059 | 39950 | 0.2604        |
 | 0.7068 | 40000 | 0.2286        |
+| 0.7077 | 40050 | 0.2766        |
+| 0.7086 | 40100 | 0.2649        |
+| 0.7095 | 40150 | 0.3184        |
+| 0.7104 | 40200 | 0.334         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7b416494c6b7505e7fa6eedc83168208b62d0c9428d6cb56bafda1f34f24d9
+oid sha256:2c11448eab5085dafbe70840b347e552395741208f4c056feba7bdf25c3684b4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be35770dca7605f30d91ba6120504ca43247cfeb02e3d77916fdb2cc3dbfaba0
+oid sha256:176196a55e3283e4494c033b91ec493e6e73b898ba15899622781e50e5276a9c
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf81c04ea51b7be585fb96d50f50e5dc3906dc50f1775c970264b1a4d1eefeb
+oid sha256:45c20f027761b73065674875134aab16adfe944ddeaaac5054a42d467120ac3f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c793708154234024ec2f24e89dee0955c43c3c92b7c5bd216b3138f06c4acd
+oid sha256:024951ca35599ed7cd93018ece748744d262ffe3e8da72f14612df6525b8ad2b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec77879460249ba1a47baa584385b3461e6077b0f1f35d15287420496875963
+oid sha256:91554dd52659f1199ca0e07de2f95f60454723c4c5c500a75b5d255aeb95a210
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7068261737732148,
+  "epoch": 0.7103603046420809,
   "eval_steps": 500,
-  "global_step": 40000,
+  "global_step": 40200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5608,6 +5608,34 @@
       "learning_rate": 1.6302448410594725e-05,
       "loss": 0.2286,
       "step": 40000
+    },
+    {
+      "epoch": 0.7077097064904313,
+      "grad_norm": 1.541528344154358,
+      "learning_rate": 1.6253362392256193e-05,
+      "loss": 0.2766,
+      "step": 40050
+    },
+    {
+      "epoch": 0.7085932392076478,
+      "grad_norm": 1.4408469200134277,
+      "learning_rate": 1.6204276373917654e-05,
+      "loss": 0.2649,
+      "step": 40100
+    },
+    {
+      "epoch": 0.7094767719248644,
+      "grad_norm": 1.57314932346344,
+      "learning_rate": 1.6155190355579115e-05,
+      "loss": 0.3184,
+      "step": 40150
+    },
+    {
+      "epoch": 0.7103603046420809,
+      "grad_norm": 2.2145802974700928,
+      "learning_rate": 1.6106104337240583e-05,
+      "loss": 0.334,
+      "step": 40200
     }
   ],
   "logging_steps": 50,