Training in progress, step 43800, checkpoint

last-checkpoint/README.md

@@ -1391,6 +1391,10 @@ You can finetune this model on your own dataset.
 | 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        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582d7207fbae78615ca0e36023c8110cb512dfcbe185f219cdbef0f8c88f6707
+oid sha256:87245a00c511204e0c66583191ab9429ad97c78538541227c616f90b8381119e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38bd1bddb06afe7bdefce01320f5544bdf1fc670f6d4527df71f8729233aad04
+oid sha256:8b6c1541af87dcd1797f9d736a3cac898e50e3ecafd501e98798ccab543ede07
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec0767005b2ab07f761617d9b9ec8dd40511cb9cacfed18b38312ca707add4f
+oid sha256:69c36e80b730b2d3f19367fe96dc275025a093a975c30683cdcf06771c2e520f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a993fdfb900c15fe63d9947d4534a020649b78ba75ceb8b6036bf3ab2fc94f
+oid sha256:0c2a170b686e6b3841063ec2a8f0cf18b4985f4986723acd35709abf15d5c19e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d4bed09415fa87d626fafe2a8875f4460b02e4d1ca2a4d5c36913f61694143
+oid sha256:a1960f4f5d6f42011bfc954842f6c57ccfbbc8ac7380b9fbe5cdcbb8bd1b0029
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7704405294128042,
+  "epoch": 0.7739746602816703,
   "eval_steps": 500,
-  "global_step": 43600,
+  "global_step": 43800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6112,6 +6112,34 @@
       "learning_rate": 1.2770218530953642e-05,
       "loss": 0.3619,
       "step": 43600
+    },
+    {
+      "epoch": 0.7713240621300207,
+      "grad_norm": 2.726393461227417,
+      "learning_rate": 1.2721132512615109e-05,
+      "loss": 0.2586,
+      "step": 43650
+    },
+    {
+      "epoch": 0.7722075948472372,
+      "grad_norm": 1.146583080291748,
+      "learning_rate": 1.2672046494276572e-05,
+      "loss": 0.251,
+      "step": 43700
+    },
+    {
+      "epoch": 0.7730911275644538,
+      "grad_norm": 1.2839117050170898,
+      "learning_rate": 1.2622960475938033e-05,
+      "loss": 0.3154,
+      "step": 43750
+    },
+    {
+      "epoch": 0.7739746602816703,
+      "grad_norm": 1.3681036233901978,
+      "learning_rate": 1.25738744575995e-05,
+      "loss": 0.3309,
+      "step": 43800
     }
   ],
   "logging_steps": 50,