Training in progress, step 19800, checkpoint

last-checkpoint/README.md

@@ -1419,6 +1419,10 @@ You can finetune this model on your own dataset.
 | 0.3446 | 19500 | 0.3162        |
 | 0.3455 | 19550 | 0.345         |
 | 0.3463 | 19600 | 0.3017        |
+| 0.3472 | 19650 | 0.4232        |
+| 0.3481 | 19700 | 0.3363        |
+| 0.3490 | 19750 | 0.3484        |
+| 0.3499 | 19800 | 0.3719        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5355e90f9d05aafbab0c12494b27835f95ccb60172ff8fbe78fd57d6b61d67
+oid sha256:cd5eef7a8ccb9cf3acddf38413c2a3c502b5ce2a1088eb18fb67381be28aa0b3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe72551b76baf33ba47fef562d43a709c57a754ed9cdde4263ce1cd0a109508
+oid sha256:ab4e5b5caf13d1eec3092fa3e49dd10854dc5a752cc2c7c411b466cb5228df24
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be3ce8b220887769ad7876242753f4d51d8fa743fffcf793c5f91b58a8f4c701
+oid sha256:a8fa7c73605caa44480fe5e545c18595e07811fe1f9941e301514020b5f116aa
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7402b49777be73c34eb03204101175d67711cc065bdfdb2c545471bf86e49076
+oid sha256:a05cf559cb926a0aaa258d4eb59fface2cba6fb224d9ac862f61329ba4c633ed
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ee56c6db80ef2379420c7b71a3a71ecc892a7c8e43c85a15d491461e416ad9
+oid sha256:5bd2f58f5426e635513a37b281d7dfa98342178368a3b72b502de96e85a2a152
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.34634482514887527,
+  "epoch": 0.3498789560177413,
   "eval_steps": 500,
-  "global_step": 19600,
+  "global_step": 19800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2752,6 +2752,34 @@
       "learning_rate": 3.632070840941666e-05,
       "loss": 0.3017,
       "step": 19600
+    },
+    {
+      "epoch": 0.3472283578660918,
+      "grad_norm": 3.46663498878479,
+      "learning_rate": 3.627162239107813e-05,
+      "loss": 0.4232,
+      "step": 19650
+    },
+    {
+      "epoch": 0.3481118905833083,
+      "grad_norm": 1.5614382028579712,
+      "learning_rate": 3.622253637273959e-05,
+      "loss": 0.3363,
+      "step": 19700
+    },
+    {
+      "epoch": 0.3489954233005248,
+      "grad_norm": 1.3841484785079956,
+      "learning_rate": 3.617345035440106e-05,
+      "loss": 0.3484,
+      "step": 19750
+    },
+    {
+      "epoch": 0.3498789560177413,
+      "grad_norm": 1.941517949104309,
+      "learning_rate": 3.6124364336062515e-05,
+      "loss": 0.3719,
+      "step": 19800
     }
   ],
   "logging_steps": 50,