Training in progress, step 51600, checkpoint

last-checkpoint/README.md

@@ -1187,144 +1187,13 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-<details><summary>Click to expand</summary>
-
 | Epoch  | Step  | Training Loss |
 |:------:|:-----:|:-------------:|
-| 0.7925 | 44850 | 0.25          |
-| 0.7934 | 44900 | 0.3381        |
-| 0.7943 | 44950 | 0.2914        |
-| 0.7952 | 45000 | 0.282         |
-| 0.7961 | 45050 | 0.2596        |
-| 0.7969 | 45100 | 0.311         |
-| 0.7978 | 45150 | 0.2368        |
-| 0.7987 | 45200 | 0.3147        |
-| 0.7996 | 45250 | 0.2964        |
-| 0.8005 | 45300 | 0.34          |
-| 0.8014 | 45350 | 0.3249        |
-| 0.8022 | 45400 | 0.4092        |
-| 0.8031 | 45450 | 0.2601        |
-| 0.8040 | 45500 | 0.306         |
-| 0.8049 | 45550 | 0.2888        |
-| 0.8058 | 45600 | 0.3101        |
-| 0.8067 | 45650 | 0.3148        |
-| 0.8075 | 45700 | 0.3975        |
-| 0.8084 | 45750 | 0.391         |
-| 0.8093 | 45800 | 0.3055        |
-| 0.8102 | 45850 | 0.2434        |
-| 0.8111 | 45900 | 0.285         |
-| 0.8120 | 45950 | 0.3952        |
-| 0.8129 | 46000 | 0.2802        |
-| 0.8137 | 46050 | 0.2687        |
-| 0.8146 | 46100 | 0.2787        |
-| 0.8155 | 46150 | 0.2943        |
-| 0.8164 | 46200 | 0.3386        |
-| 0.8173 | 46250 | 0.3227        |
-| 0.8182 | 46300 | 0.2582        |
-| 0.8190 | 46350 | 0.285         |
-| 0.8199 | 46400 | 0.2989        |
-| 0.8208 | 46450 | 0.2761        |
-| 0.8217 | 46500 | 0.299         |
-| 0.8226 | 46550 | 0.2908        |
-| 0.8235 | 46600 | 0.3134        |
-| 0.8243 | 46650 | 0.2603        |
-| 0.8252 | 46700 | 0.2965        |
-| 0.8261 | 46750 | 0.2506        |
-| 0.8270 | 46800 | 0.2258        |
-| 0.8279 | 46850 | 0.2209        |
-| 0.8288 | 46900 | 0.2756        |
-| 0.8296 | 46950 | 0.3345        |
-| 0.8305 | 47000 | 0.3016        |
-| 0.8314 | 47050 | 0.2712        |
-| 0.8323 | 47100 | 0.3721        |
-| 0.8332 | 47150 | 0.3483        |
-| 0.8341 | 47200 | 0.3002        |
-| 0.8349 | 47250 | 0.2333        |
-| 0.8358 | 47300 | 0.3043        |
-| 0.8367 | 47350 | 0.2992        |
-| 0.8376 | 47400 | 0.3367        |
-| 0.8385 | 47450 | 0.3135        |
-| 0.8394 | 47500 | 0.2681        |
-| 0.8402 | 47550 | 0.2764        |
-| 0.8411 | 47600 | 0.3211        |
-| 0.8420 | 47650 | 0.3081        |
-| 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        |
-| 0.8491 | 48050 | 0.3676        |
-| 0.8500 | 48100 | 0.2989        |
-| 0.8508 | 48150 | 0.3259        |
-| 0.8517 | 48200 | 0.2949        |
-| 0.8526 | 48250 | 0.3914        |
-| 0.8535 | 48300 | 0.2645        |
-| 0.8544 | 48350 | 0.3358        |
-| 0.8553 | 48400 | 0.2939        |
-| 0.8561 | 48450 | 0.4063        |
-| 0.8570 | 48500 | 0.3492        |
-| 0.8579 | 48550 | 0.2794        |
-| 0.8588 | 48600 | 0.2854        |
-| 0.8597 | 48650 | 0.2664        |
-| 0.8606 | 48700 | 0.3028        |
-| 0.8614 | 48750 | 0.2579        |
-| 0.8623 | 48800 | 0.3404        |
-| 0.8632 | 48850 | 0.3535        |
-| 0.8641 | 48900 | 0.2224        |
-| 0.8650 | 48950 | 0.2701        |
-| 0.8659 | 49000 | 0.2506        |
-| 0.8667 | 49050 | 0.3032        |
-| 0.8676 | 49100 | 0.3881        |
-| 0.8685 | 49150 | 0.253         |
-| 0.8694 | 49200 | 0.2827        |
-| 0.8703 | 49250 | 0.266         |
-| 0.8712 | 49300 | 0.3008        |
-| 0.8720 | 49350 | 0.3406        |
-| 0.8729 | 49400 | 0.3348        |
-| 0.8738 | 49450 | 0.3021        |
-| 0.8747 | 49500 | 0.3182        |
-| 0.8756 | 49550 | 0.3063        |
-| 0.8765 | 49600 | 0.2385        |
-| 0.8773 | 49650 | 0.3152        |
-| 0.8782 | 49700 | 0.267         |
-| 0.8791 | 49750 | 0.2599        |
-| 0.8800 | 49800 | 0.3226        |
-| 0.8809 | 49850 | 0.3516        |
-| 0.8818 | 49900 | 0.2912        |
-| 0.8826 | 49950 | 0.2853        |
-| 0.8835 | 50000 | 0.3212        |
-| 0.8844 | 50050 | 0.3399        |
-| 0.8853 | 50100 | 0.3104        |
-| 0.8862 | 50150 | 0.368         |
-| 0.8871 | 50200 | 0.2848        |
-| 0.8880 | 50250 | 0.4137        |
-| 0.8888 | 50300 | 0.3597        |
-| 0.8897 | 50350 | 0.3246        |
-| 0.8906 | 50400 | 0.2658        |
-| 0.8915 | 50450 | 0.2954        |
-| 0.8924 | 50500 | 0.3035        |
-| 0.8933 | 50550 | 0.2654        |
-| 0.8941 | 50600 | 0.2742        |
-| 0.8950 | 50650 | 0.3435        |
-| 0.8959 | 50700 | 0.2947        |
-| 0.8968 | 50750 | 0.3013        |
-| 0.8977 | 50800 | 0.3845        |
-| 0.8986 | 50850 | 0.2882        |
-| 0.8994 | 50900 | 0.3639        |
-| 0.9003 | 50950 | 0.2332        |
-| 0.9012 | 51000 | 0.3363        |
-| 0.9021 | 51050 | 0.2674        |
-| 0.9030 | 51100 | 0.331         |
-| 0.9039 | 51150 | 0.2881        |
-| 0.9047 | 51200 | 0.3553        |
-| 0.9056 | 51250 | 0.2936        |
-| 0.9065 | 51300 | 0.2987        |
-| 0.9074 | 51350 | 0.3343        |
-| 0.9083 | 51400 | 0.2919        |
+| 0.9092 | 51450 | 0.2997        |
+| 0.9100 | 51500 | 0.2247        |
+| 0.9109 | 51550 | 0.2918        |
+| 0.9118 | 51600 | 0.3295        |
 
-</details>
 
 ### Framework Versions
 - Python: 3.11.13

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6095595fb3007928d93e8e219ea90fc483d7933ff71480f93acc7032b0be18
+oid sha256:aeecd8d9471d7a0b6627d01abbb6ab9354f23702be741b49535069a09a804f63
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5528739540379e7472ab0ae207cba54ed4fa2009128623e5cc01b704f91e4334
+oid sha256:33a86535350dee0d838aabde4505a86ae7f966c06b02b476617bf119348d925b
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b1d2649da1c33c4c6171910ab9897e0cf291c76124110f095256b857bf610a
+oid sha256:a589e7cc1c3f0f337824a3d6a8bc421970447f40e56c215be58c6b1d6c52a5a0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ed7436953ae4e16b051c219b7cb3a2e2190d41cf4e564a35d17483bdb596e66
+oid sha256:39475f4e00274ea95478c0aa6d264be5db3bd87ad877f934d4b5cd1f7f759e82
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac1d7bd261ca287c71b297338a8785cacbd5d9b3b50d5e9d2567d8805ed369c
+oid sha256:b0adae6525b0259ff389512f804b95631a5bbbd0e13a53824c06deb281fe18e7
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9082716332985811,
+  "epoch": 0.9118057641674471,
   "eval_steps": 500,
-  "global_step": 51400,
+  "global_step": 51600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7204,6 +7204,34 @@
       "learning_rate": 5.1167265516090395e-06,
       "loss": 0.2919,
       "step": 51400
+    },
+    {
+      "epoch": 0.9091551660157976,
+      "grad_norm": 1.3142715692520142,
+      "learning_rate": 5.067640533270503e-06,
+      "loss": 0.2997,
+      "step": 51450
+    },
+    {
+      "epoch": 0.9100386987330141,
+      "grad_norm": 1.3387079238891602,
+      "learning_rate": 5.018554514931967e-06,
+      "loss": 0.2247,
+      "step": 51500
+    },
+    {
+      "epoch": 0.9109222314502307,
+      "grad_norm": 1.9581636190414429,
+      "learning_rate": 4.96946849659343e-06,
+      "loss": 0.2918,
+      "step": 51550
+    },
+    {
+      "epoch": 0.9118057641674471,
+      "grad_norm": 1.3822007179260254,
+      "learning_rate": 4.920382478254894e-06,
+      "loss": 0.3295,
+      "step": 51600
     }
   ],
   "logging_steps": 50,

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97480b9506272973ef63d3e54eedf906636737574e44c7ac22ad4421393b708
+oid sha256:0b1eb037399f5df91069f9b474c7a40c3e0d7a309caabb274d665499c0377b52
 size 5560