Training in progress, step 53200, checkpoint

last-checkpoint/README.md

@@ -1217,6 +1217,10 @@ You can finetune this model on your own dataset.
 | 0.9348 | 52900 | 0.2546        |
 | 0.9357 | 52950 | 0.2433        |
 | 0.9365 | 53000 | 0.3632        |
+| 0.9374 | 53050 | 0.2602        |
+| 0.9383 | 53100 | 0.2066        |
+| 0.9392 | 53150 | 0.2957        |
+| 0.9401 | 53200 | 0.3931        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a93506b17e187ec485e647736909a6e30a6b5a4afd58e635d7efbd2f47c5a3a2
+oid sha256:2487922e51e359a9f1ecb6a445d3e636440e65c32739f52f813e51dba1e67cff
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c894f0484203c4d57b3d262318d41e2221d22d49b423c905fe11e9a50485d53b
+oid sha256:cb6a3019423076f9d2bcde60bdb5789ba741f63b281497780b4c7a5a01452766
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947b856c80c583e9eb627e7ad23316a7e3f099aa83e875d4ef3873a67bb2cfa9
+oid sha256:703c575158d027ee9439c8f4b7cba9394179cb8e338f46e41a82b465fd641366
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b498b4acb31c2654058989155a84103c3b9f463016fc112303436f1bdf72023
+oid sha256:0d78afd0a4dfa1ad614feedb884bc52a6d0ef53d711277b9eb7759daf275b74c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3040b4b8d6d12ba279c6c44ff4763f072518857ded0ffa2a6cc4542788b7857b
+oid sha256:5c6628a730df5612a115afdb07517d1848beb0c28c4d9cd90e5531c3a4536e32
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9365446802495097,
+  "epoch": 0.9400788111183758,
   "eval_steps": 500,
-  "global_step": 53000,
+  "global_step": 53200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7428,6 +7428,34 @@
       "learning_rate": 3.5459739647758733e-06,
       "loss": 0.3632,
       "step": 53000
+    },
+    {
+      "epoch": 0.9374282129667262,
+      "grad_norm": 2.5942931175231934,
+      "learning_rate": 3.496887946437337e-06,
+      "loss": 0.2602,
+      "step": 53050
+    },
+    {
+      "epoch": 0.9383117456839427,
+      "grad_norm": 1.256638526916504,
+      "learning_rate": 3.4478019280988005e-06,
+      "loss": 0.2066,
+      "step": 53100
+    },
+    {
+      "epoch": 0.9391952784011592,
+      "grad_norm": 3.677544593811035,
+      "learning_rate": 3.399697630127035e-06,
+      "loss": 0.2957,
+      "step": 53150
+    },
+    {
+      "epoch": 0.9400788111183758,
+      "grad_norm": 1.3518919944763184,
+      "learning_rate": 3.3506116117884983e-06,
+      "loss": 0.3931,
+      "step": 53200
     }
   ],
   "logging_steps": 50,