Training in progress, step 45000, checkpoint

last-checkpoint/README.md

@@ -1187,236 +1187,13 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-<details><summary>Click to expand</summary>
-
 | Epoch  | Step  | Training Loss |
 |:------:|:-----:|:-------------:|
-| 0.5946 | 33650 | 0.2952        |
-| 0.5955 | 33700 | 0.2754        |
-| 0.5964 | 33750 | 0.3434        |
-| 0.5973 | 33800 | 0.2541        |
-| 0.5982 | 33850 | 0.2923        |
-| 0.5990 | 33900 | 0.2361        |
-| 0.5999 | 33950 | 0.4459        |
-| 0.6008 | 34000 | 0.3169        |
-| 0.6017 | 34050 | 0.3146        |
-| 0.6026 | 34100 | 0.3125        |
-| 0.6035 | 34150 | 0.2738        |
-| 0.6043 | 34200 | 0.3062        |
-| 0.6052 | 34250 | 0.3566        |
-| 0.6061 | 34300 | 0.3466        |
-| 0.6070 | 34350 | 0.2608        |
-| 0.6079 | 34400 | 0.3239        |
-| 0.6088 | 34450 | 0.3557        |
-| 0.6096 | 34500 | 0.4175        |
-| 0.6105 | 34550 | 0.3104        |
-| 0.6114 | 34600 | 0.3305        |
-| 0.6123 | 34650 | 0.2832        |
-| 0.6132 | 34700 | 0.3007        |
-| 0.6141 | 34750 | 0.3932        |
-| 0.6149 | 34800 | 0.3           |
-| 0.6158 | 34850 | 0.2785        |
-| 0.6167 | 34900 | 0.3015        |
-| 0.6176 | 34950 | 0.3291        |
-| 0.6185 | 35000 | 0.2634        |
-| 0.6194 | 35050 | 0.3212        |
-| 0.6202 | 35100 | 0.2965        |
-| 0.6211 | 35150 | 0.3557        |
-| 0.6220 | 35200 | 0.3535        |
-| 0.6229 | 35250 | 0.4183        |
-| 0.6238 | 35300 | 0.3355        |
-| 0.6247 | 35350 | 0.3626        |
-| 0.6255 | 35400 | 0.2542        |
-| 0.6264 | 35450 | 0.2555        |
-| 0.6273 | 35500 | 0.3418        |
-| 0.6282 | 35550 | 0.3118        |
-| 0.6291 | 35600 | 0.2889        |
-| 0.6300 | 35650 | 0.319         |
-| 0.6308 | 35700 | 0.312         |
-| 0.6317 | 35750 | 0.2776        |
-| 0.6326 | 35800 | 0.2574        |
-| 0.6335 | 35850 | 0.2816        |
-| 0.6344 | 35900 | 0.3392        |
-| 0.6353 | 35950 | 0.2856        |
-| 0.6361 | 36000 | 0.286         |
-| 0.6370 | 36050 | 0.3555        |
-| 0.6379 | 36100 | 0.3065        |
-| 0.6388 | 36150 | 0.3696        |
-| 0.6397 | 36200 | 0.2626        |
-| 0.6406 | 36250 | 0.2681        |
-| 0.6414 | 36300 | 0.3015        |
-| 0.6423 | 36350 | 0.3587        |
-| 0.6432 | 36400 | 0.4138        |
-| 0.6441 | 36450 | 0.3785        |
-| 0.6450 | 36500 | 0.3385        |
-| 0.6459 | 36550 | 0.3423        |
-| 0.6467 | 36600 | 0.3793        |
-| 0.6476 | 36650 | 0.3819        |
-| 0.6485 | 36700 | 0.3111        |
-| 0.6494 | 36750 | 0.3299        |
-| 0.6503 | 36800 | 0.3994        |
-| 0.6512 | 36850 | 0.3595        |
-| 0.6520 | 36900 | 0.3572        |
-| 0.6529 | 36950 | 0.3085        |
-| 0.6538 | 37000 | 0.2647        |
-| 0.6547 | 37050 | 0.2622        |
-| 0.6556 | 37100 | 0.3814        |
-| 0.6565 | 37150 | 0.4174        |
-| 0.6573 | 37200 | 0.3473        |
-| 0.6582 | 37250 | 0.3598        |
-| 0.6591 | 37300 | 0.2822        |
-| 0.6600 | 37350 | 0.2538        |
-| 0.6609 | 37400 | 0.2212        |
-| 0.6618 | 37450 | 0.2687        |
-| 0.6626 | 37500 | 0.3288        |
-| 0.6635 | 37550 | 0.4221        |
-| 0.6644 | 37600 | 0.3711        |
-| 0.6653 | 37650 | 0.2418        |
-| 0.6662 | 37700 | 0.3           |
-| 0.6671 | 37750 | 0.3147        |
-| 0.6680 | 37800 | 0.2895        |
-| 0.6688 | 37850 | 0.2649        |
-| 0.6697 | 37900 | 0.287         |
-| 0.6706 | 37950 | 0.267         |
-| 0.6715 | 38000 | 0.2862        |
-| 0.6724 | 38050 | 0.2931        |
-| 0.6733 | 38100 | 0.3039        |
-| 0.6741 | 38150 | 0.3067        |
-| 0.6750 | 38200 | 0.3072        |
-| 0.6759 | 38250 | 0.2744        |
-| 0.6768 | 38300 | 0.3098        |
-| 0.6777 | 38350 | 0.2837        |
-| 0.6786 | 38400 | 0.2998        |
-| 0.6794 | 38450 | 0.2477        |
-| 0.6803 | 38500 | 0.3343        |
-| 0.6812 | 38550 | 0.2411        |
-| 0.6821 | 38600 | 0.2641        |
-| 0.6830 | 38650 | 0.3673        |
-| 0.6839 | 38700 | 0.3456        |
-| 0.6847 | 38750 | 0.2554        |
-| 0.6856 | 38800 | 0.2289        |
-| 0.6865 | 38850 | 0.2409        |
-| 0.6874 | 38900 | 0.3395        |
-| 0.6883 | 38950 | 0.3296        |
-| 0.6892 | 39000 | 0.349         |
-| 0.6900 | 39050 | 0.2841        |
-| 0.6909 | 39100 | 0.3101        |
-| 0.6918 | 39150 | 0.3094        |
-| 0.6927 | 39200 | 0.2485        |
-| 0.6936 | 39250 | 0.2985        |
-| 0.6945 | 39300 | 0.3039        |
-| 0.6953 | 39350 | 0.2616        |
-| 0.6962 | 39400 | 0.2932        |
-| 0.6971 | 39450 | 0.3707        |
-| 0.6980 | 39500 | 0.2728        |
-| 0.6989 | 39550 | 0.2482        |
-| 0.6998 | 39600 | 0.3475        |
-| 0.7006 | 39650 | 0.3447        |
-| 0.7015 | 39700 | 0.2503        |
-| 0.7024 | 39750 | 0.3593        |
-| 0.7033 | 39800 | 0.2933        |
-| 0.7042 | 39850 | 0.3565        |
-| 0.7051 | 39900 | 0.2838        |
-| 0.7059 | 39950 | 0.2604        |
-| 0.7068 | 40000 | 0.2286        |
-| 0.7077 | 40050 | 0.2766        |
-| 0.7086 | 40100 | 0.2649        |
-| 0.7095 | 40150 | 0.3184        |
-| 0.7104 | 40200 | 0.334         |
-| 0.7112 | 40250 | 0.3609        |
-| 0.7121 | 40300 | 0.306         |
-| 0.7130 | 40350 | 0.2629        |
-| 0.7139 | 40400 | 0.2311        |
-| 0.7148 | 40450 | 0.2909        |
-| 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        |
-| 0.7218 | 40850 | 0.3355        |
-| 0.7227 | 40900 | 0.3322        |
-| 0.7236 | 40950 | 0.3424        |
-| 0.7245 | 41000 | 0.2834        |
-| 0.7254 | 41050 | 0.2776        |
-| 0.7263 | 41100 | 0.2924        |
-| 0.7271 | 41150 | 0.3982        |
-| 0.7280 | 41200 | 0.3379        |
-| 0.7289 | 41250 | 0.2876        |
-| 0.7298 | 41300 | 0.3289        |
-| 0.7307 | 41350 | 0.3119        |
-| 0.7316 | 41400 | 0.3007        |
-| 0.7324 | 41450 | 0.3499        |
-| 0.7333 | 41500 | 0.3016        |
-| 0.7342 | 41550 | 0.3232        |
-| 0.7351 | 41600 | 0.2577        |
-| 0.7360 | 41650 | 0.2928        |
-| 0.7369 | 41700 | 0.2814        |
-| 0.7377 | 41750 | 0.2962        |
-| 0.7386 | 41800 | 0.2756        |
-| 0.7395 | 41850 | 0.3287        |
-| 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        |
-| 0.7466 | 42250 | 0.3631        |
-| 0.7475 | 42300 | 0.2374        |
-| 0.7484 | 42350 | 0.3347        |
-| 0.7492 | 42400 | 0.3031        |
-| 0.7501 | 42450 | 0.2817        |
-| 0.7510 | 42500 | 0.3433        |
-| 0.7519 | 42550 | 0.3273        |
-| 0.7528 | 42600 | 0.3123        |
-| 0.7537 | 42650 | 0.29          |
-| 0.7545 | 42700 | 0.3352        |
-| 0.7554 | 42750 | 0.3143        |
-| 0.7563 | 42800 | 0.2833        |
-| 0.7572 | 42850 | 0.2851        |
-| 0.7581 | 42900 | 0.2956        |
-| 0.7590 | 42950 | 0.3038        |
-| 0.7598 | 43000 | 0.2195        |
-| 0.7607 | 43050 | 0.2588        |
-| 0.7616 | 43100 | 0.3065        |
-| 0.7625 | 43150 | 0.3252        |
-| 0.7634 | 43200 | 0.2418        |
-| 0.7643 | 43250 | 0.4002        |
-| 0.7651 | 43300 | 0.3379        |
-| 0.7660 | 43350 | 0.3574        |
-| 0.7669 | 43400 | 0.3664        |
-| 0.7678 | 43450 | 0.3274        |
-| 0.7687 | 43500 | 0.2443        |
-| 0.7696 | 43550 | 0.2998        |
-| 0.7704 | 43600 | 0.3619        |
-| 0.7713 | 43650 | 0.2586        |
-| 0.7722 | 43700 | 0.251         |
-| 0.7731 | 43750 | 0.3154        |
-| 0.7740 | 43800 | 0.3309        |
-| 0.7749 | 43850 | 0.2768        |
-| 0.7757 | 43900 | 0.3049        |
-| 0.7766 | 43950 | 0.2939        |
-| 0.7775 | 44000 | 0.2909        |
-| 0.7784 | 44050 | 0.2157        |
-| 0.7793 | 44100 | 0.2785        |
-| 0.7802 | 44150 | 0.2386        |
-| 0.7810 | 44200 | 0.3297        |
-| 0.7819 | 44250 | 0.2576        |
-| 0.7828 | 44300 | 0.2678        |
-| 0.7837 | 44350 | 0.3625        |
-| 0.7846 | 44400 | 0.311         |
-| 0.7855 | 44450 | 0.2924        |
-| 0.7863 | 44500 | 0.2602        |
-| 0.7872 | 44550 | 0.3936        |
-| 0.7881 | 44600 | 0.229         |
-| 0.7890 | 44650 | 0.3017        |
-| 0.7899 | 44700 | 0.2795        |
-| 0.7908 | 44750 | 0.279         |
-| 0.7916 | 44800 | 0.227         |
+| 0.7925 | 44850 | 0.25          |
+| 0.7934 | 44900 | 0.3381        |
+| 0.7943 | 44950 | 0.2914        |
+| 0.7952 | 45000 | 0.282         |
 
-</details>
 
 ### Framework Versions
 - Python: 3.11.13

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2970aabf3a655ac85113d5b6672798ff4b6430f64aad4045ed8ffd01109ee0a4
+oid sha256:0ef76b6fee8c0fd9556900a05eb0770041bcc5a9708508b78f491641cac655f8
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8b8c1496f83dcf4b7c667f04fccd67c7d43b788742223114f77d71b8b17910
+oid sha256:eb08a5d8f04e486ccde9a85e4e9299751359a9d9614ffc3531e3deafb4e0a876
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb56f2c027efc838c67094a45905db4a06a6d3525086412dec63fe94b6326cc5
+oid sha256:e6e372030ae72b97fbc6cc5e639f35bf2df20cbde1f7751bd5565217fb58eec7
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d02bc78b22ccfd2d2cb2a9e32bb7cd76760001fe2e9b8f3babc4091b78fde49
+oid sha256:9c78515125dc6571e473b9ee78fd09306ea3ef81a3f639c80068abccc6924eae
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d1b4b34303310b51ebb01ce33c3b39156dd3c7f40c71fbb94511f9c8503c5fa
+oid sha256:8371b7f9012f9b7db42f400823445baf760f1582673ba8da16f0fa77bea3fc99
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7916453146260006,
+  "epoch": 0.7951794454948666,
   "eval_steps": 500,
-  "global_step": 44800,
+  "global_step": 45000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6280,6 +6280,34 @@
       "learning_rate": 1.1592154090828769e-05,
       "loss": 0.227,
       "step": 44800
+    },
+    {
+      "epoch": 0.7925288473432172,
+      "grad_norm": 1.5428054332733154,
+      "learning_rate": 1.1543068072490232e-05,
+      "loss": 0.25,
+      "step": 44850
+    },
+    {
+      "epoch": 0.7934123800604337,
+      "grad_norm": 4.3441057205200195,
+      "learning_rate": 1.1494963774518466e-05,
+      "loss": 0.3381,
+      "step": 44900
+    },
+    {
+      "epoch": 0.7942959127776501,
+      "grad_norm": 1.589739203453064,
+      "learning_rate": 1.1445877756179931e-05,
+      "loss": 0.2914,
+      "step": 44950
+    },
+    {
+      "epoch": 0.7951794454948666,
+      "grad_norm": 1.8874093294143677,
+      "learning_rate": 1.1396791737841392e-05,
+      "loss": 0.282,
+      "step": 45000
     }
   ],
   "logging_steps": 50,

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a21a534e4993b863994e64d84a120efcce8aac5f212cbacbdb8f1e5edfbb2e
+oid sha256:b97480b9506272973ef63d3e54eedf906636737574e44c7ac22ad4421393b708
 size 5560