Training in progress, step 49200, checkpoint

last-checkpoint/README.md

@@ -1273,6 +1273,10 @@ You can finetune this model on your own dataset.
 | 0.8641 | 48900 | 0.2224        |
 | 0.8650 | 48950 | 0.2701        |
 | 0.8659 | 49000 | 0.2506        |
+| 0.8667 | 49050 | 0.3032        |
+| 0.8676 | 49100 | 0.3881        |
+| 0.8685 | 49150 | 0.253         |
+| 0.8694 | 49200 | 0.2827        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84efeaad3a28b91cc498c5612f39d5a4c2c9f8daa7acd8511082cc68b8ddc2cb
+oid sha256:db270bdf7d87010d77739736698e8ae2458178b320b75a98ff547807297b32cf
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7a89c0e9e8e599e158b35c8a497af87a6ed6aa2e7dbb6685a96e88a89c0ee09
+oid sha256:7cdff63ae89dbc12a252704b70d4f4e647e5f14e3b07054703b4d441104730c5
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d739b2e6d744ac93c261a7254a1e982aa4ce3774f886b8c343e7cb40301307
+oid sha256:4b9fcb3d1d73275e0a2875dc17b667a53e5fe939e399224550e0ccf13df80b1e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:866c5a8b8535e30581fc80f2ad91749cdaeeee2ad90769cad0b001d56fb4e651
+oid sha256:3068685ac3b9a7af5938020cc76babca30a1c59648f52293d5fd49a933b85d96
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f974b2cab5a8a0bdcab6bbe8e6e05d55c8066b6602ba318fa916b4a6a3ca4678
+oid sha256:d9ba2b0f751d8d7f4bc3cb94f7968aeae57ec5b067c86272a37019de0cca79bf
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8658620628721881,
+  "epoch": 0.8693961937410543,
   "eval_steps": 500,
-  "global_step": 49000,
+  "global_step": 49200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6868,6 +6868,34 @@
       "learning_rate": 7.4708919911252476e-06,
       "loss": 0.2506,
       "step": 49000
+    },
+    {
+      "epoch": 0.8667455955894047,
+      "grad_norm": 1.3858048915863037,
+      "learning_rate": 7.421805972786712e-06,
+      "loss": 0.3032,
+      "step": 49050
+    },
+    {
+      "epoch": 0.8676291283066212,
+      "grad_norm": 1.2791121006011963,
+      "learning_rate": 7.373701674814947e-06,
+      "loss": 0.3881,
+      "step": 49100
+    },
+    {
+      "epoch": 0.8685126610238377,
+      "grad_norm": 1.6947706937789917,
+      "learning_rate": 7.32461565647641e-06,
+      "loss": 0.253,
+      "step": 49150
+    },
+    {
+      "epoch": 0.8693961937410543,
+      "grad_norm": 1.4587703943252563,
+      "learning_rate": 7.2755296381378734e-06,
+      "loss": 0.2827,
+      "step": 49200
     }
   ],
   "logging_steps": 50,