Training in progress, step 37600, checkpoint

last-checkpoint/README.md

@@ -1265,6 +1265,10 @@ You can finetune this model on your own dataset.
 | 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        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:682fa9590e06a4b4fccae7f5f773e5cc53952c5e99d2335a76b83158b65098ed
+oid sha256:49cc2b93728e49de217dc60cd367d1893bf2f9bed3ceb4afe515eabf48f6ed08
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9245c8c24824eb122166f727d92f67c72576954b6b177342efb7c87cca99916e
+oid sha256:336c01379450b237f69846bbca72ce99e84b15f94ed370646502b855f060fb86
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4055cc979b2b5391466d56f1b911260413ca5d1e7980d72b0ab4b419cbf9b1f2
+oid sha256:4d1e5086acf3138ad2715b1b0217454786680720f4c61739eebdb529556b78ae
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88bd0768fb513693c45a5dd657bdd8c5632ab92debcf304b18dc0e31cdbf92a9
+oid sha256:fa03be736ad2e04b4837e2c32a43b6b3386812b76663243651e6e6a4bb8fb202
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f778ab4b27197de7dc711e3e33f3210ad38a94a9b2fa894dde1075de7a2d68
+oid sha256:188c2cbd8075ea7a1b7865239bd6d95b63ebe7d536a5366864b0e98bf73e24a0
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6608824724779558,
+  "epoch": 0.664416603346822,
   "eval_steps": 500,
-  "global_step": 37400,
+  "global_step": 37600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5244,6 +5244,34 @@
       "learning_rate": 1.8853939643831853e-05,
       "loss": 0.2212,
       "step": 37400
+    },
+    {
+      "epoch": 0.6617660051951724,
+      "grad_norm": 1.2916769981384277,
+      "learning_rate": 1.8804853625493314e-05,
+      "loss": 0.2687,
+      "step": 37450
+    },
+    {
+      "epoch": 0.6626495379123889,
+      "grad_norm": 1.5212571620941162,
+      "learning_rate": 1.875576760715478e-05,
+      "loss": 0.3288,
+      "step": 37500
+    },
+    {
+      "epoch": 0.6635330706296054,
+      "grad_norm": 1.5829190015792847,
+      "learning_rate": 1.870668158881624e-05,
+      "loss": 0.4221,
+      "step": 37550
+    },
+    {
+      "epoch": 0.664416603346822,
+      "grad_norm": 1.4784077405929565,
+      "learning_rate": 1.8657595570477705e-05,
+      "loss": 0.3711,
+      "step": 37600
     }
   ],
   "logging_steps": 50,