Training in progress, step 46400, checkpoint

last-checkpoint/README.md

@@ -1217,6 +1217,10 @@ You can finetune this model on your own dataset.
 | 0.8146 | 46100 | 0.2787        |
 | 0.8155 | 46150 | 0.2943        |
 | 0.8164 | 46200 | 0.3386        |
+| 0.8173 | 46250 | 0.3227        |
+| 0.8182 | 46300 | 0.2582        |
+| 0.8190 | 46350 | 0.285         |
+| 0.8199 | 46400 | 0.2989        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317dee7bdf4b84d46a50601403d19626cd472b80bda36741dc48bf64d5b51d05
+oid sha256:627d2b4f8ecea5cdfb170d123ae59ee0402c361c798b4d5c0a5332e334584559
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5717440dcd3e2f09e5f546818459b38ffae88bc9a9b8cb8d67aa113aebadabd8
+oid sha256:ef488a1aa99df1a7495ba789415dfd6ce209c02bba2a2c44e7bfe3c32f6adaaa
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb8a12ff0a64fc5ed6adc7345aa4a83fd87d261a05c853430ab076afe05a154
+oid sha256:6bc1e5c929cb8f54d58e9ee1847d7a0b3eca4210598cf360f322a008e7b3cfc7
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346548a4c17d9cad2c82496da0276965825c893a3342335d781b694e90a062d5
+oid sha256:4443157a5e465be0625068722ad0be9b943ae7cfc578916594c92f0db7089d29
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b13323b686f2ab7c5492467b0d1175f40fe477951600d7f6162cdddd7d92fb
+oid sha256:77c2f010939ae1c15c3c974f7d0a87bffdc388e9851106b282750c10255b68df
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8163842307080631,
+  "epoch": 0.8199183615769292,
   "eval_steps": 500,
-  "global_step": 46200,
+  "global_step": 46400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6476,6 +6476,34 @@
       "learning_rate": 1.0218727297716519e-05,
       "loss": 0.3386,
       "step": 46200
+    },
+    {
+      "epoch": 0.8172677634252796,
+      "grad_norm": 1.5368878841400146,
+      "learning_rate": 1.0169641279377982e-05,
+      "loss": 0.3227,
+      "step": 46250
+    },
+    {
+      "epoch": 0.8181512961424962,
+      "grad_norm": 3.281324625015259,
+      "learning_rate": 1.0120555261039447e-05,
+      "loss": 0.2582,
+      "step": 46300
+    },
+    {
+      "epoch": 0.8190348288597127,
+      "grad_norm": 1.4477012157440186,
+      "learning_rate": 1.007146924270091e-05,
+      "loss": 0.285,
+      "step": 46350
+    },
+    {
+      "epoch": 0.8199183615769292,
+      "grad_norm": 2.9229135513305664,
+      "learning_rate": 1.0022383224362374e-05,
+      "loss": 0.2989,
+      "step": 46400
     }
   ],
   "logging_steps": 50,