Training in progress, step 39800, checkpoint

last-checkpoint/README.md

@@ -1311,6 +1311,10 @@ You can finetune this model on your own dataset.
 | 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        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642557ebf163ec87a2c4b2e6bcd49164daf736dd04b223bf43c296aa2ccd0691
+oid sha256:b7e3850ec81152c770c1287a58b16a081486e29359e4ddd6242aec24390a1095
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68fc796162e803cf8996cea52a774af09ba5e5580bd153dfb078c7440eb4c453
+oid sha256:fe6982d0068dc488d659ee3ea863838224b7f84d13622881dc74bd17ff8174f7
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e9f5adbd47cc46da9040df21f1d7ee84a7337e4df1a6edd24bdcba55b2b18f
+oid sha256:cf03aa505c305170adf85ee73ee56bc32702b85d7c76a3b04c609b9202b5754a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5969956edb13fe3030fe262e095ce3767ee21141a5bf0b22d9012217adf4404
+oid sha256:71d3db821ebc15469e7d3f1fde03936d361471a5f2cb1a21d3669fed48601709
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a02d77869643a47791f7c775e6b5711819ede3a850a6716616e73ea72431d66
+oid sha256:2795a9eb0d0e9717e4fddeb0ae82fb57c15cae7d137da34c1144f8d3ca3cd594
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6997579120354827,
+  "epoch": 0.7032920429043488,
   "eval_steps": 500,
-  "global_step": 39600,
+  "global_step": 39800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5552,6 +5552,34 @@
       "learning_rate": 1.6695136557303018e-05,
       "loss": 0.3475,
       "step": 39600
+    },
+    {
+      "epoch": 0.7006414447526992,
+      "grad_norm": 0.6908143758773804,
+      "learning_rate": 1.6646050538964482e-05,
+      "loss": 0.3447,
+      "step": 39650
+    },
+    {
+      "epoch": 0.7015249774699157,
+      "grad_norm": 1.5447782278060913,
+      "learning_rate": 1.6596964520625947e-05,
+      "loss": 0.2503,
+      "step": 39700
+    },
+    {
+      "epoch": 0.7024085101871322,
+      "grad_norm": 1.515202283859253,
+      "learning_rate": 1.6547878502287408e-05,
+      "loss": 0.3593,
+      "step": 39750
+    },
+    {
+      "epoch": 0.7032920429043488,
+      "grad_norm": 4.640558242797852,
+      "learning_rate": 1.6498792483948873e-05,
+      "loss": 0.2933,
+      "step": 39800
     }
   ],
   "logging_steps": 50,