Training in progress, step 36000, checkpoint

last-checkpoint/README.md

@@ -1233,6 +1233,10 @@ You can finetune this model on your own dataset.
 | 0.6308 | 35700 | 0.312         |
 | 0.6317 | 35750 | 0.2776        |
 | 0.6326 | 35800 | 0.2574        |
+| 0.6335 | 35850 | 0.2816        |
+| 0.6344 | 35900 | 0.3392        |
+| 0.6353 | 35950 | 0.2856        |
+| 0.6361 | 36000 | 0.286         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bae377c97d95c091e602ea66921e5e1054c92655fcc87b72a9e144d35f4777b9
+oid sha256:14b384b5f887acee5a6096737f368c3613e7537b072283344d0460f9ee33683f
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53dd7b57f3f8c10ab9b2a35f0933e4ed0758fa2fa30468c3dcc9a374cbfea064
+oid sha256:94f7c656111e857b9a5964461ddb67ba8434de7b657a0de6cf811249e9f135c7
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21564110007d55db6f6a52d1c9590217ce427ced36eba0a8dc124d9288a67d6c
+oid sha256:83863be742a336d65a58bf9026fc223fa44e5cc37215b2331b9a723f209bc947
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ecaf6e4f08856d634b99dd1969eedbd96a7e22708903309e7e68fda2bacc394
+oid sha256:a1b02513987752f55c2a09cb46fb561fd6490aaf9c1a9fb121a08671c8653dcd
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7083008eae1faaed45dcde0eba354b7d59a06375dff301d884f49f745cc4e30
+oid sha256:e587de7316b1032258fa34321e4e4cbe60d0a5d83b11f22c68cdcdf7469e3a42
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6326094255270273,
+  "epoch": 0.6361435563958934,
   "eval_steps": 500,
-  "global_step": 35800,
+  "global_step": 36000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5020,6 +5020,34 @@
       "learning_rate": 2.0423710510298248e-05,
       "loss": 0.2574,
       "step": 35800
+    },
+    {
+      "epoch": 0.6334929582442438,
+      "grad_norm": 1.6969387531280518,
+      "learning_rate": 2.0374624491959713e-05,
+      "loss": 0.2816,
+      "step": 35850
+    },
+    {
+      "epoch": 0.6343764909614603,
+      "grad_norm": 2.4319510459899902,
+      "learning_rate": 2.0325538473621174e-05,
+      "loss": 0.3392,
+      "step": 35900
+    },
+    {
+      "epoch": 0.6352600236786768,
+      "grad_norm": 1.4081567525863647,
+      "learning_rate": 2.027645245528264e-05,
+      "loss": 0.2856,
+      "step": 35950
+    },
+    {
+      "epoch": 0.6361435563958934,
+      "grad_norm": 1.2967078685760498,
+      "learning_rate": 2.02273664369441e-05,
+      "loss": 0.286,
+      "step": 36000
     }
   ],
   "logging_steps": 50,