Training in progress, step 48000, checkpoint

last-checkpoint/README.md

@@ -1249,6 +1249,10 @@ You can finetune this model on your own dataset.
 | 0.8429 | 47700 | 0.2929        |
 | 0.8438 | 47750 | 0.3466        |
 | 0.8447 | 47800 | 0.3012        |
+| 0.8455 | 47850 | 0.2953        |
+| 0.8464 | 47900 | 0.2914        |
+| 0.8473 | 47950 | 0.3219        |
+| 0.8482 | 48000 | 0.3104        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce1f6af6d2a72f031e3c0de240f823edc94a245e95fb7a33a39dc0ad38f9ec0
+oid sha256:4d06b1080b11ff71d438c79d42b856600d8a1837767cc93a0f4b910c0a5b3bbe
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:310b5e6c85d4fa71697a913a5e8eb1baf2af955a83f82ffe53be481221938fc4
+oid sha256:67ed6a39e52c37128938194bb73101a8a9722b0f52ba4f5496c71d280b71e9fc
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6664f2f42fe11eba3d15efd3cef84351c1ed700ca012feeaaba10e813a674fd6
+oid sha256:ddda33f244c8e8c75c77f432ddeb1ecd4a5542f0afaeca6c9a4938180a8390c2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8621fe1648dc96d7d6a12a9e96d1ea20e9a16f5271880935750dfe7f0b53b1
+oid sha256:c19235faf86fc7b488d049c5de2dd9270a2ad7d80400a9f4692705e68f0f698f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:785cadb5b905b280e8fff12125b530dd86b352b15f0eb2d7c104357be9261774
+oid sha256:8ac25fdb927a745ab43f8015082d3fd4a83655134c52103466f1ab5cd6a68cc3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8446572776589917,
+  "epoch": 0.8481914085278578,
   "eval_steps": 500,
-  "global_step": 47800,
+  "global_step": 48000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6700,6 +6700,34 @@
       "learning_rate": 8.648956431250123e-06,
       "loss": 0.3012,
       "step": 47800
+    },
+    {
+      "epoch": 0.8455408103762082,
+      "grad_norm": 1.188514232635498,
+      "learning_rate": 8.599870412911587e-06,
+      "loss": 0.2953,
+      "step": 47850
+    },
+    {
+      "epoch": 0.8464243430934247,
+      "grad_norm": 1.5537595748901367,
+      "learning_rate": 8.55078439457305e-06,
+      "loss": 0.2914,
+      "step": 47900
+    },
+    {
+      "epoch": 0.8473078758106413,
+      "grad_norm": 1.640060544013977,
+      "learning_rate": 8.501698376234513e-06,
+      "loss": 0.3219,
+      "step": 47950
+    },
+    {
+      "epoch": 0.8481914085278578,
+      "grad_norm": 1.896763801574707,
+      "learning_rate": 8.452612357895976e-06,
+      "loss": 0.3104,
+      "step": 48000
     }
   ],
   "logging_steps": 50,