Training in progress, step 53400, checkpoint

last-checkpoint/README.md

@@ -1221,6 +1221,10 @@ You can finetune this model on your own dataset.
 | 0.9383 | 53100 | 0.2066        |
 | 0.9392 | 53150 | 0.2957        |
 | 0.9401 | 53200 | 0.3931        |
+| 0.9410 | 53250 | 0.3384        |
+| 0.9418 | 53300 | 0.234         |
+| 0.9427 | 53350 | 0.2244        |
+| 0.9436 | 53400 | 0.2736        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2487922e51e359a9f1ecb6a445d3e636440e65c32739f52f813e51dba1e67cff
+oid sha256:39c1a96a93254cf31ffb70f6814ad348fc844266fcb793b7212c9e8b11daf19d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6a3019423076f9d2bcde60bdb5789ba741f63b281497780b4c7a5a01452766
+oid sha256:b1b5b98b6da8546e8a7a2cc62e31dd4b93cce07de3e6e6f9ce4ce52ad9cdab9b
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:703c575158d027ee9439c8f4b7cba9394179cb8e338f46e41a82b465fd641366
+oid sha256:ca41761b8d788c104936e19f7e170bfd0a6d6a882f10f2b6319094786889629a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d78afd0a4dfa1ad614feedb884bc52a6d0ef53d711277b9eb7759daf275b74c
+oid sha256:afe990ada4836e3b8da06b332bb1effcb8ba00456aa80c3ca264f6cde84a1b18
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6628a730df5612a115afdb07517d1848beb0c28c4d9cd90e5531c3a4536e32
+oid sha256:6b096fb0b9d4b123e0ea98d85fa01bcdb3622620e30def8e03e9a27f4fc9f25b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9400788111183758,
+  "epoch": 0.9436129419872418,
   "eval_steps": 500,
-  "global_step": 53200,
+  "global_step": 53400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7456,6 +7456,34 @@
       "learning_rate": 3.3506116117884983e-06,
       "loss": 0.3931,
       "step": 53200
+    },
+    {
+      "epoch": 0.9409623438355922,
+      "grad_norm": 1.065996766090393,
+      "learning_rate": 3.3015255934499617e-06,
+      "loss": 0.3384,
+      "step": 53250
+    },
+    {
+      "epoch": 0.9418458765528087,
+      "grad_norm": 1.57516610622406,
+      "learning_rate": 3.252439575111425e-06,
+      "loss": 0.234,
+      "step": 53300
+    },
+    {
+      "epoch": 0.9427294092700252,
+      "grad_norm": 1.2013062238693237,
+      "learning_rate": 3.203353556772889e-06,
+      "loss": 0.2244,
+      "step": 53350
+    },
+    {
+      "epoch": 0.9436129419872418,
+      "grad_norm": 1.448370099067688,
+      "learning_rate": 3.1542675384343524e-06,
+      "loss": 0.2736,
+      "step": 53400
     }
   ],
   "logging_steps": 50,