Training in progress, step 49000, checkpoint

last-checkpoint/README.md

@@ -1269,6 +1269,10 @@ You can finetune this model on your own dataset.
 | 0.8606 | 48700 | 0.3028        |
 | 0.8614 | 48750 | 0.2579        |
 | 0.8623 | 48800 | 0.3404        |
+| 0.8632 | 48850 | 0.3535        |
+| 0.8641 | 48900 | 0.2224        |
+| 0.8650 | 48950 | 0.2701        |
+| 0.8659 | 49000 | 0.2506        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36dc7c9e83fd465b92a2847be177b9eb428689ac2977e5e232b38d92574447f6
+oid sha256:84efeaad3a28b91cc498c5612f39d5a4c2c9f8daa7acd8511082cc68b8ddc2cb
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476cfc5664418f0c7219fe39c91775cf7ee5aec7d0f1d77a8008aa21455285b8
+oid sha256:c7a89c0e9e8e599e158b35c8a497af87a6ed6aa2e7dbb6685a96e88a89c0ee09
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c91689e6fe6ea5ac1e3ed99062e8d26595b040c06b11772caa18d4fe3ffb3e8
+oid sha256:c3d739b2e6d744ac93c261a7254a1e982aa4ce3774f886b8c343e7cb40301307
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d183fbaa9612fc768da7cf7cefd13466b61ea27398ff0fc8e2f5977752f4ef
+oid sha256:866c5a8b8535e30581fc80f2ad91749cdaeeee2ad90769cad0b001d56fb4e651
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86d99e394985101a11e9cbc029a6edaca303ea24f38f1f70ed88d32b2ae0eb0
+oid sha256:f974b2cab5a8a0bdcab6bbe8e6e05d55c8066b6602ba318fa916b4a6a3ca4678
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.862327932003322,
+  "epoch": 0.8658620628721881,
   "eval_steps": 500,
-  "global_step": 48800,
+  "global_step": 49000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6840,6 +6840,34 @@
       "learning_rate": 7.667236064479394e-06,
       "loss": 0.3404,
       "step": 48800
+    },
+    {
+      "epoch": 0.8632114647205386,
+      "grad_norm": 1.3516128063201904,
+      "learning_rate": 7.618150046140858e-06,
+      "loss": 0.3535,
+      "step": 48850
+    },
+    {
+      "epoch": 0.8640949974377551,
+      "grad_norm": 1.4083527326583862,
+      "learning_rate": 7.569064027802321e-06,
+      "loss": 0.2224,
+      "step": 48900
+    },
+    {
+      "epoch": 0.8649785301549716,
+      "grad_norm": 1.421423077583313,
+      "learning_rate": 7.5199780094637854e-06,
+      "loss": 0.2701,
+      "step": 48950
+    },
+    {
+      "epoch": 0.8658620628721881,
+      "grad_norm": 2.421118974685669,
+      "learning_rate": 7.4708919911252476e-06,
+      "loss": 0.2506,
+      "step": 49000
     }
   ],
   "logging_steps": 50,