Training in progress, step 33600, checkpoint

last-checkpoint/README.md

@@ -1331,6 +1331,10 @@ You can finetune this model on your own dataset.
 | 0.5884 | 33300 | 0.3448        |
 | 0.5893 | 33350 | 0.2409        |
 | 0.5902 | 33400 | 0.3313        |
+| 0.5911 | 33450 | 0.2981        |
+| 0.5920 | 33500 | 0.269         |
+| 0.5929 | 33550 | 0.4098        |
+| 0.5937 | 33600 | 0.2924        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b27e19aeb33a8e3d0002479a7c9b39941b110c3d8f2a434dd4c37398d7e3bf
+oid sha256:6f534df9eabe25064d029fb2d1fd136283ef967f7afc887a51be26077e972e34
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6630698de4c1d60df96c16179e2c8e1c72b61b401cb6fb1ef3f721fd3eab1635
+oid sha256:7b9243475a6ea2e44bb15f370f31b09dd572fa23757f65fe3e9261c3c93a8462
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b6af598f9b2ce21fbe71c40f1ad10247f9090027ef27f3c8a5469e0d37e9d2
+oid sha256:bd6945cb5a30962738a328e18b0f7ded3e18c1657315150f6cef20738ac2b26e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996a18422b4144a7e4ee40f3c4f84f0bb776c53f7d678050f150fa6a8f50971c
+oid sha256:ca24b530a082040eb648f26b5b54b5a0f292c3ed7dea28d1bd9dbe2dcf563558
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38bd9d190ea4ca40a5063536abac3be81a4c1f5db4e523367622b668bf53349c
+oid sha256:55b84df2ef27071e1bcf2b8efc3d6b7785ff7a24f59d685fade7a53af7a2593d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5901998551006343,
+  "epoch": 0.5937339859695004,
   "eval_steps": 500,
-  "global_step": 33400,
+  "global_step": 33600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4684,6 +4684,34 @@
       "learning_rate": 2.277885767018123e-05,
       "loss": 0.3313,
       "step": 33400
+    },
+    {
+      "epoch": 0.5910833878178509,
+      "grad_norm": 1.6026935577392578,
+      "learning_rate": 2.272977165184269e-05,
+      "loss": 0.2981,
+      "step": 33450
+    },
+    {
+      "epoch": 0.5919669205350674,
+      "grad_norm": 2.3030807971954346,
+      "learning_rate": 2.2680685633504154e-05,
+      "loss": 0.269,
+      "step": 33500
+    },
+    {
+      "epoch": 0.5928504532522839,
+      "grad_norm": 2.8911454677581787,
+      "learning_rate": 2.2631599615165616e-05,
+      "loss": 0.4098,
+      "step": 33550
+    },
+    {
+      "epoch": 0.5937339859695004,
+      "grad_norm": 1.4643045663833618,
+      "learning_rate": 2.258251359682708e-05,
+      "loss": 0.2924,
+      "step": 33600
     }
   ],
   "logging_steps": 50,