Training in progress, step 42200, checkpoint

last-checkpoint/README.md

@@ -1359,6 +1359,10 @@ You can finetune this model on your own dataset.
 | 0.7404 | 41900 | 0.34          |
 | 0.7413 | 41950 | 0.3402        |
 | 0.7422 | 42000 | 0.2404        |
+| 0.7431 | 42050 | 0.2655        |
+| 0.7439 | 42100 | 0.3288        |
+| 0.7448 | 42150 | 0.3333        |
+| 0.7457 | 42200 | 0.3602        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e57b3e2b58d734f4c35cbc52b8711045e136c227d6cc5e1dcddb6a3c1910ff6e
+oid sha256:83afd304da9ec0fb20d98a2d12c9411b67ec3d42591e5ff6ab887eab75060bc9
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81694f45179e6fe9a2996d2cdf88f73c60893feef53e707cd5693d75ccfd65f7
+oid sha256:a3baaf946db368404b08114c9679bf96f88de1ac7c8c80c8a46d8a2e2273b4cf
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189c7583745a64b89aee209b7060333b361b8f00c73935be83712585003d2b83
+oid sha256:d763d9ca70425fdf40bf2c310ee3aa99e16879e3dcca91b65438c05121dc800c
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f620c9a2a7cac59f29c3864d51fa02083d5c4a45835ed46377aa71b80487d3
+oid sha256:cdc5774e283703e787806fc20a7b89a411d313a132b63638672a2da2a5ead08e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:191a5ae829d69c8ce786757578a128230a22a499f634555db1cb0373af1f974a
+oid sha256:c96b3ee97617878f5775584f3569298deaaee2c710b13a42dfd4b9c9b2808a60
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7421674824618756,
+  "epoch": 0.7457016133307416,
   "eval_steps": 500,
-  "global_step": 42000,
+  "global_step": 42200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5888,6 +5888,34 @@
       "learning_rate": 1.4339989397420039e-05,
       "loss": 0.2404,
       "step": 42000
+    },
+    {
+      "epoch": 0.7430510151790921,
+      "grad_norm": 1.4757792949676514,
+      "learning_rate": 1.4290903379081502e-05,
+      "loss": 0.2655,
+      "step": 42050
+    },
+    {
+      "epoch": 0.7439345478963086,
+      "grad_norm": 1.6618765592575073,
+      "learning_rate": 1.4241817360742968e-05,
+      "loss": 0.3288,
+      "step": 42100
+    },
+    {
+      "epoch": 0.7448180806135252,
+      "grad_norm": 1.3700001239776611,
+      "learning_rate": 1.4192731342404431e-05,
+      "loss": 0.3333,
+      "step": 42150
+    },
+    {
+      "epoch": 0.7457016133307416,
+      "grad_norm": 1.4557344913482666,
+      "learning_rate": 1.4143645324065894e-05,
+      "loss": 0.3602,
+      "step": 42200
     }
   ],
   "logging_steps": 50,