Training in progress, step 17600, checkpoint

last-checkpoint/README.md

@@ -1375,6 +1375,10 @@ You can finetune this model on your own dataset.
 | 0.3057 | 17300 | 0.2924        |
 | 0.3066 | 17350 | 0.4029        |
 | 0.3075 | 17400 | 0.5016        |
+| 0.3084 | 17450 | 0.3648        |
+| 0.3092 | 17500 | 0.3045        |
+| 0.3101 | 17550 | 0.3271        |
+| 0.3110 | 17600 | 0.519         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45090e53ca13162f5dfed87da6ebea51548a6f3908cbbefc66a73c68e67f368f
+oid sha256:b66468e216ee2c55c8722fcf5ffc4000ad473c11e2235fd48feb13c93ab9a883
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca6aad37af14fa05240de5a73f6854c9f991ab7d94bccdddb3bd4a0e3ff149d
+oid sha256:c80fc82acafe7b81de6e075cb1f70093e6580aa336f3c93bec03a9394db9ef8c
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23fe6d223e7616989ffc698a28faceb780fedfcab150f455b3003f3664a9d548
+oid sha256:7625a5ff890e229adfcb09536e86a3f211f3ec81111193662f8f33dc40007931
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2780f904a141afb4c77d183d8b90351cd99dc707535728f23c895b86a7cd2bb
+oid sha256:bfa613f344c94ccc67e76de2c8badaaabcf83b2833a1acdc3b0fc8f5681211e9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d388bf9897e62191d89d430ec5647330caf741ec214058515a40e21a614b139
+oid sha256:6c08c2ff99a1d61c2be28a306cae4d9334535d1863b102589cd2d55ee6bca1a6
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30746938559134845,
+  "epoch": 0.3110035164602145,
   "eval_steps": 500,
-  "global_step": 17400,
+  "global_step": 17600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2444,6 +2444,34 @@
       "learning_rate": 3.8479511495945495e-05,
       "loss": 0.5016,
       "step": 17400
+    },
+    {
+      "epoch": 0.308352918308565,
+      "grad_norm": 1.4788236618041992,
+      "learning_rate": 3.843042547760696e-05,
+      "loss": 0.3648,
+      "step": 17450
+    },
+    {
+      "epoch": 0.3092364510257815,
+      "grad_norm": 1.7631937265396118,
+      "learning_rate": 3.8381339459268424e-05,
+      "loss": 0.3045,
+      "step": 17500
+    },
+    {
+      "epoch": 0.310119983742998,
+      "grad_norm": 1.9122941493988037,
+      "learning_rate": 3.833225344092989e-05,
+      "loss": 0.3271,
+      "step": 17550
+    },
+    {
+      "epoch": 0.3110035164602145,
+      "grad_norm": 1.6838266849517822,
+      "learning_rate": 3.828316742259135e-05,
+      "loss": 0.519,
+      "step": 17600
     }
   ],
   "logging_steps": 50,