Training in progress, step 33400, checkpoint

last-checkpoint/README.md

@@ -1327,6 +1327,10 @@ You can finetune this model on your own dataset.
 | 0.5849 | 33100 | 0.2475        |
 | 0.5858 | 33150 | 0.348         |
 | 0.5867 | 33200 | 0.2779        |
+| 0.5875 | 33250 | 0.3166        |
+| 0.5884 | 33300 | 0.3448        |
+| 0.5893 | 33350 | 0.2409        |
+| 0.5902 | 33400 | 0.3313        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99a52192178bbce89ad50c778d4f9bf6832b1481f86c47e744cf7ba729322eed
+oid sha256:56b27e19aeb33a8e3d0002479a7c9b39941b110c3d8f2a434dd4c37398d7e3bf
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d206f55adca7413c00e9799da5a83e0d7eb862fb2cf37236c2e4b104f35bcc0
+oid sha256:6630698de4c1d60df96c16179e2c8e1c72b61b401cb6fb1ef3f721fd3eab1635
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e84175a067ef9ea1b90f9c520af471e35f0e36e402ca9c6d4d4252339d961a0e
+oid sha256:a0b6af598f9b2ce21fbe71c40f1ad10247f9090027ef27f3c8a5469e0d37e9d2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965065b740d957921866df8f0457265c0a3e6b7684746ca495482effad4548c9
+oid sha256:996a18422b4144a7e4ee40f3c4f84f0bb776c53f7d678050f150fa6a8f50971c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb425c5828f81b7dea1abb11cdabe1e52bb8172393d755ab6f7986190b2e5fb
+oid sha256:38bd9d190ea4ca40a5063536abac3be81a4c1f5db4e523367622b668bf53349c
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5866657242317683,
+  "epoch": 0.5901998551006343,
   "eval_steps": 500,
-  "global_step": 33200,
+  "global_step": 33400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4656,6 +4656,34 @@
       "learning_rate": 2.297520174353537e-05,
       "loss": 0.2779,
       "step": 33200
+    },
+    {
+      "epoch": 0.5875492569489849,
+      "grad_norm": 1.7234498262405396,
+      "learning_rate": 2.2926115725196838e-05,
+      "loss": 0.3166,
+      "step": 33250
+    },
+    {
+      "epoch": 0.5884327896662014,
+      "grad_norm": 1.4789388179779053,
+      "learning_rate": 2.28770297068583e-05,
+      "loss": 0.3448,
+      "step": 33300
+    },
+    {
+      "epoch": 0.5893163223834179,
+      "grad_norm": 0.8780321478843689,
+      "learning_rate": 2.2827943688519764e-05,
+      "loss": 0.2409,
+      "step": 33350
+    },
+    {
+      "epoch": 0.5901998551006343,
+      "grad_norm": 1.9462053775787354,
+      "learning_rate": 2.277885767018123e-05,
+      "loss": 0.3313,
+      "step": 33400
     }
   ],
   "logging_steps": 50,