Training in progress, step 53000, checkpoint

last-checkpoint/README.md

@@ -1213,6 +1213,10 @@ You can finetune this model on your own dataset.
 | 0.9312 | 52700 | 0.2958        |
 | 0.9321 | 52750 | 0.2647        |
 | 0.9330 | 52800 | 0.2329        |
+| 0.9339 | 52850 | 0.2984        |
+| 0.9348 | 52900 | 0.2546        |
+| 0.9357 | 52950 | 0.2433        |
+| 0.9365 | 53000 | 0.3632        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a329281b62dee04f25df2a1445a6d06e38a118403d00dfd2047a9f0451d6a236
+oid sha256:a93506b17e187ec485e647736909a6e30a6b5a4afd58e635d7efbd2f47c5a3a2
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a7c65d7edd786206cd29e1711b41b5ec57296920cd7f0363e9e1febcd4786d
+oid sha256:c894f0484203c4d57b3d262318d41e2221d22d49b423c905fe11e9a50485d53b
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39806bf7f5ccc564dfbcbf96185e5776a4d453cf6ceeebfa61e6b15fd77f05f
+oid sha256:947b856c80c583e9eb627e7ad23316a7e3f099aa83e875d4ef3873a67bb2cfa9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f8eff2e31e5d461c8d76e9f3c73436b8f99cd51de4fc3b3a328f9ccbf1dbdd
+oid sha256:7b498b4acb31c2654058989155a84103c3b9f463016fc112303436f1bdf72023
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d76c0e19f4170b3811b1d648f816f3a3f40e357234c62ca57c1c93ddc1c338c
+oid sha256:3040b4b8d6d12ba279c6c44ff4763f072518857ded0ffa2a6cc4542788b7857b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9330105493806435,
+  "epoch": 0.9365446802495097,
   "eval_steps": 500,
-  "global_step": 52800,
+  "global_step": 53000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7400,6 +7400,34 @@
       "learning_rate": 3.7423180381300193e-06,
       "loss": 0.2329,
       "step": 52800
+    },
+    {
+      "epoch": 0.9338940820978601,
+      "grad_norm": 2.5619053840637207,
+      "learning_rate": 3.693232019791483e-06,
+      "loss": 0.2984,
+      "step": 52850
+    },
+    {
+      "epoch": 0.9347776148150766,
+      "grad_norm": 1.545856237411499,
+      "learning_rate": 3.6441460014529465e-06,
+      "loss": 0.2546,
+      "step": 52900
+    },
+    {
+      "epoch": 0.9356611475322931,
+      "grad_norm": 2.4920833110809326,
+      "learning_rate": 3.59505998311441e-06,
+      "loss": 0.2433,
+      "step": 52950
+    },
+    {
+      "epoch": 0.9365446802495097,
+      "grad_norm": 1.65108323097229,
+      "learning_rate": 3.5459739647758733e-06,
+      "loss": 0.3632,
+      "step": 53000
     }
   ],
   "logging_steps": 50,