Training in progress, step 52000, checkpoint

last-checkpoint/README.md

@@ -1193,6 +1193,10 @@ You can finetune this model on your own dataset.
 | 0.9136 | 51700 | 0.3088        |
 | 0.9145 | 51750 | 0.2287        |
 | 0.9153 | 51800 | 0.2067        |
+| 0.9162 | 51850 | 0.2735        |
+| 0.9171 | 51900 | 0.3976        |
+| 0.9180 | 51950 | 0.2939        |
+| 0.9189 | 52000 | 0.3193        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8adbf03525b39d3cbba1bbdde2da90cb7be2d698601f862e040d6383edf785e8
+oid sha256:64df739ab78548e5d75f993ab6041c207785adcb30fa9a57cf9234173976387d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddba7d83c634a4905db07a12f6761ec90e0847d3c3a75cb805e5a2c45f6f055e
+oid sha256:ab3798d7d967dd27d94d9da8c3b443a2ae8d98157d0a447c72ba241256385ef3
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3acf2d762800b6693f2eadfe02d38f79ee54f3a4fcf7d7f00a5e20954d4a73
+oid sha256:1bf77e2ef33f60ef48f8a5fc09cb1943760ae6ba4d88634c23d14cfcf6cad117
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37c94dad9c27aa070c66f020f85050e7628adbe8df381c470c2f01ed333d243
+oid sha256:12597bbc3e3311f727af17ce6725c67e2c62ce8d20a5da4fcf3ead6fc2b4cd3a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4fc38cbd3a40df512cafd836390b147d408874f4ecc602c76931ee4bd316f8
+oid sha256:69967b924386ed794e36fcb2fe2f94715b55410c1d3076df0af1214b0c14df7b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9153398950363132,
+  "epoch": 0.9188740259051793,
   "eval_steps": 500,
-  "global_step": 51800,
+  "global_step": 52000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7260,6 +7260,34 @@
       "learning_rate": 4.724038404900748e-06,
       "loss": 0.2067,
       "step": 51800
+    },
+    {
+      "epoch": 0.9162234277535297,
+      "grad_norm": 1.1146478652954102,
+      "learning_rate": 4.674952386562212e-06,
+      "loss": 0.2735,
+      "step": 51850
+    },
+    {
+      "epoch": 0.9171069604707462,
+      "grad_norm": 2.2454397678375244,
+      "learning_rate": 4.625866368223675e-06,
+      "loss": 0.3976,
+      "step": 51900
+    },
+    {
+      "epoch": 0.9179904931879628,
+      "grad_norm": 1.902377724647522,
+      "learning_rate": 4.576780349885139e-06,
+      "loss": 0.2939,
+      "step": 51950
+    },
+    {
+      "epoch": 0.9188740259051793,
+      "grad_norm": 4.320808410644531,
+      "learning_rate": 4.527694331546602e-06,
+      "loss": 0.3193,
+      "step": 52000
     }
   ],
   "logging_steps": 50,