Training in progress, step 40800, checkpoint

last-checkpoint/README.md

@@ -1331,6 +1331,10 @@ You can finetune this model on your own dataset.
 | 0.7157 | 40500 | 0.343         |
 | 0.7165 | 40550 | 0.3013        |
 | 0.7174 | 40600 | 0.3128        |
+| 0.7183 | 40650 | 0.2073        |
+| 0.7192 | 40700 | 0.2873        |
+| 0.7201 | 40750 | 0.3705        |
+| 0.7210 | 40800 | 0.2985        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ab7b3916da8a5dc2fefb182305b2800af148c80b90a0e5addb9b673bea08ca
+oid sha256:d78a54fb4d46ba6a28639611752cbd90c81e4f5c2899787ac51015d1444478c6
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3317b8c5d354e41a8855a79cd943bb15303f4b223b40b4b0117db599f16c0065
+oid sha256:18056243182ea1caa1b86090618604e7d1e429f23a12ff1faad08a57f30e9f02
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280a7f83a8ba48bb32d168a0a0cd5555d9e11709ce0ba3cfc77af9b48c2160fb
+oid sha256:d701f7ad37b76a01e770182d60edba5e764045eee0c4420747669dc57f30af68
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be209d4a461eee1fa1948cfcdede9079955638115f4647a4f1a424013de8c91
+oid sha256:9fc39115c671fd04a36f4927fc18f9015d2dce27d719fc74d0c9d59b53289a70
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206b866093eb1fb8cb9166f733d4bad077c57b2cd0d3adade63bbc86e09d7ad4
+oid sha256:cb354beb7a0d4ccd477dc950d57455f0fa927e9ecbdea63314e56687b97ea814
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.717428566379813,
+  "epoch": 0.7209626972486791,
   "eval_steps": 500,
-  "global_step": 40600,
+  "global_step": 40800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5692,6 +5692,34 @@
       "learning_rate": 1.571341619053229e-05,
       "loss": 0.3128,
       "step": 40600
+    },
+    {
+      "epoch": 0.7183120990970295,
+      "grad_norm": 1.5661957263946533,
+      "learning_rate": 1.5664330172193752e-05,
+      "loss": 0.2073,
+      "step": 40650
+    },
+    {
+      "epoch": 0.7191956318142461,
+      "grad_norm": 1.4217487573623657,
+      "learning_rate": 1.5615244153855217e-05,
+      "loss": 0.2873,
+      "step": 40700
+    },
+    {
+      "epoch": 0.7200791645314626,
+      "grad_norm": 1.6037381887435913,
+      "learning_rate": 1.556713985588345e-05,
+      "loss": 0.3705,
+      "step": 40750
+    },
+    {
+      "epoch": 0.7209626972486791,
+      "grad_norm": 1.7782158851623535,
+      "learning_rate": 1.5518053837544916e-05,
+      "loss": 0.2985,
+      "step": 40800
     }
   ],
   "logging_steps": 50,