Training in progress, step 46200, checkpoint

last-checkpoint/README.md

@@ -1213,6 +1213,10 @@ You can finetune this model on your own dataset.
 | 0.8111 | 45900 | 0.285         |
 | 0.8120 | 45950 | 0.3952        |
 | 0.8129 | 46000 | 0.2802        |
+| 0.8137 | 46050 | 0.2687        |
+| 0.8146 | 46100 | 0.2787        |
+| 0.8155 | 46150 | 0.2943        |
+| 0.8164 | 46200 | 0.3386        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc453c795079d8ded19817daacd8fec5d095bba6393f23049cff77eeb1abaf9
+oid sha256:317dee7bdf4b84d46a50601403d19626cd472b80bda36741dc48bf64d5b51d05
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303c03bcbf6290c5fb7fcf2c4927d56af5a210c091c12a9beba5ee6c9213f174
+oid sha256:5717440dcd3e2f09e5f546818459b38ffae88bc9a9b8cb8d67aa113aebadabd8
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431f36421847b278b660e6526fb15af6b02fbddb625572cac02bb7ad994d2dda
+oid sha256:1bb8a12ff0a64fc5ed6adc7345aa4a83fd87d261a05c853430ab076afe05a154
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e42fd89832885ab30327a4c2371265408743318772a17d94083f8bfb054483
+oid sha256:346548a4c17d9cad2c82496da0276965825c893a3342335d781b694e90a062d5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4d32ff62b246761d94af48903691044aacc80825efb2f5658f28d83287222c
+oid sha256:32b13323b686f2ab7c5492467b0d1175f40fe477951600d7f6162cdddd7d92fb
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8128500998391971,
+  "epoch": 0.8163842307080631,
   "eval_steps": 500,
-  "global_step": 46000,
+  "global_step": 46200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6448,6 +6448,34 @@
       "learning_rate": 1.0415071371070664e-05,
       "loss": 0.2802,
       "step": 46000
+    },
+    {
+      "epoch": 0.8137336325564135,
+      "grad_norm": 0.8188498020172119,
+      "learning_rate": 1.0365985352732128e-05,
+      "loss": 0.2687,
+      "step": 46050
+    },
+    {
+      "epoch": 0.81461716527363,
+      "grad_norm": 1.3656600713729858,
+      "learning_rate": 1.0316899334393591e-05,
+      "loss": 0.2787,
+      "step": 46100
+    },
+    {
+      "epoch": 0.8155006979908466,
+      "grad_norm": 1.3830708265304565,
+      "learning_rate": 1.0267813316055056e-05,
+      "loss": 0.2943,
+      "step": 46150
+    },
+    {
+      "epoch": 0.8163842307080631,
+      "grad_norm": 1.866623878479004,
+      "learning_rate": 1.0218727297716519e-05,
+      "loss": 0.3386,
+      "step": 46200
     }
   ],
   "logging_steps": 50,