Training in progress, step 20000, checkpoint

last-checkpoint/README.md

@@ -1423,6 +1423,10 @@ You can finetune this model on your own dataset.
 | 0.3481 | 19700 | 0.3363        |
 | 0.3490 | 19750 | 0.3484        |
 | 0.3499 | 19800 | 0.3719        |
+| 0.3508 | 19850 | 0.3226        |
+| 0.3516 | 19900 | 0.3636        |
+| 0.3525 | 19950 | 0.3704        |
+| 0.3534 | 20000 | 0.3459        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd5eef7a8ccb9cf3acddf38413c2a3c502b5ce2a1088eb18fb67381be28aa0b3
+oid sha256:e7072d59f5aacf209413bfe1b68393d31e61f586cffca0291db2c96c4018ed70
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4e5b5caf13d1eec3092fa3e49dd10854dc5a752cc2c7c411b466cb5228df24
+oid sha256:7ace23ee1b367e732fb2aa3f1a05392e0e438a9535dad79c057fb1b8e02b9d68
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8fa7c73605caa44480fe5e545c18595e07811fe1f9941e301514020b5f116aa
+oid sha256:14dd25fc849fe74831fabbde14139b26a0f4aad6b8e087440c778d9e11ab8d7e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05cf559cb926a0aaa258d4eb59fface2cba6fb224d9ac862f61329ba4c633ed
+oid sha256:313073d5ed3020eae2b8815f959d08ffdd33605f3a4a238421bfb13a6954c251
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd2f58f5426e635513a37b281d7dfa98342178368a3b72b502de96e85a2a152
+oid sha256:cde16ded14375bc47c997c2d556dc8340b61e53a3892d07fbf99a72d763ffa8d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3498789560177413,
+  "epoch": 0.3534130868866074,
   "eval_steps": 500,
-  "global_step": 19800,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2780,6 +2780,34 @@
       "learning_rate": 3.6124364336062515e-05,
       "loss": 0.3719,
       "step": 19800
+    },
+    {
+      "epoch": 0.35076248873495786,
+      "grad_norm": 4.908963680267334,
+      "learning_rate": 3.607527831772398e-05,
+      "loss": 0.3226,
+      "step": 19850
+    },
+    {
+      "epoch": 0.3516460214521744,
+      "grad_norm": 1.5221627950668335,
+      "learning_rate": 3.6026192299385444e-05,
+      "loss": 0.3636,
+      "step": 19900
+    },
+    {
+      "epoch": 0.3525295541693909,
+      "grad_norm": 1.8089814186096191,
+      "learning_rate": 3.597710628104691e-05,
+      "loss": 0.3704,
+      "step": 19950
+    },
+    {
+      "epoch": 0.3534130868866074,
+      "grad_norm": 2.786560535430908,
+      "learning_rate": 3.5928020262708373e-05,
+      "loss": 0.3459,
+      "step": 20000
     }
   ],
   "logging_steps": 50,