Training in progress, step 46600, checkpoint

last-checkpoint/README.md

@@ -1221,6 +1221,10 @@ You can finetune this model on your own dataset.
 | 0.8182 | 46300 | 0.2582        |
 | 0.8190 | 46350 | 0.285         |
 | 0.8199 | 46400 | 0.2989        |
+| 0.8208 | 46450 | 0.2761        |
+| 0.8217 | 46500 | 0.299         |
+| 0.8226 | 46550 | 0.2908        |
+| 0.8235 | 46600 | 0.3134        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:627d2b4f8ecea5cdfb170d123ae59ee0402c361c798b4d5c0a5332e334584559
+oid sha256:142d4c8ad016790fcbcb6bf5e68a5dcbdef2e9705f12fb07f181ef927a93333a
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef488a1aa99df1a7495ba789415dfd6ce209c02bba2a2c44e7bfe3c32f6adaaa
+oid sha256:9c9041e81c6e0019831198e6ff3f401abd14ed00e89f927bc706b188ab63b76d
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc1e5c929cb8f54d58e9ee1847d7a0b3eca4210598cf360f322a008e7b3cfc7
+oid sha256:80b3c6e69019b821213bf9d49d5b01da485427d6ae65f3fc1547d69ab36ff927
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4443157a5e465be0625068722ad0be9b943ae7cfc578916594c92f0db7089d29
+oid sha256:c76708a6769f6750a136317961002a8e94193f536a6dd070918f7e493fa54130
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c2f010939ae1c15c3c974f7d0a87bffdc388e9851106b282750c10255b68df
+oid sha256:e9203611a5650cd81962fd740668d81290ec5b3a4f3232d739000dc19f94e073
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8199183615769292,
+  "epoch": 0.8234524924457952,
   "eval_steps": 500,
-  "global_step": 46400,
+  "global_step": 46600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6504,6 +6504,34 @@
       "learning_rate": 1.0022383224362374e-05,
       "loss": 0.2989,
       "step": 46400
+    },
+    {
+      "epoch": 0.8208018942941457,
+      "grad_norm": 1.5713211297988892,
+      "learning_rate": 9.973297206023836e-06,
+      "loss": 0.2761,
+      "step": 46450
+    },
+    {
+      "epoch": 0.8216854270113623,
+      "grad_norm": 1.5968650579452515,
+      "learning_rate": 9.9242111876853e-06,
+      "loss": 0.299,
+      "step": 46500
+    },
+    {
+      "epoch": 0.8225689597285788,
+      "grad_norm": 1.5933504104614258,
+      "learning_rate": 9.875125169346763e-06,
+      "loss": 0.2908,
+      "step": 46550
+    },
+    {
+      "epoch": 0.8234524924457952,
+      "grad_norm": 0.9819146990776062,
+      "learning_rate": 9.826039151008228e-06,
+      "loss": 0.3134,
+      "step": 46600
     }
   ],
   "logging_steps": 50,