Training in progress, step 17800, checkpoint

last-checkpoint/README.md

@@ -1379,6 +1379,10 @@ You can finetune this model on your own dataset.
 | 0.3092 | 17500 | 0.3045        |
 | 0.3101 | 17550 | 0.3271        |
 | 0.3110 | 17600 | 0.519         |
+| 0.3119 | 17650 | 0.341         |
+| 0.3128 | 17700 | 0.3352        |
+| 0.3137 | 17750 | 0.4406        |
+| 0.3145 | 17800 | 0.3822        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b66468e216ee2c55c8722fcf5ffc4000ad473c11e2235fd48feb13c93ab9a883
+oid sha256:d23dcacb737e2af42314c6ab6136446e4982fee8745c6c03e350fd15717250aa
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80fc82acafe7b81de6e075cb1f70093e6580aa336f3c93bec03a9394db9ef8c
+oid sha256:4eb8f9bc1642eae53fb943b388f6c8e06377f86d8a4ed25c9948af7605742194
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7625a5ff890e229adfcb09536e86a3f211f3ec81111193662f8f33dc40007931
+oid sha256:116d3f323503837c4f5074c61dce27aa590a7a4580eb34472179dff367b43737
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa613f344c94ccc67e76de2c8badaaabcf83b2833a1acdc3b0fc8f5681211e9
+oid sha256:54d3b315ce89145171b35cb9993d6540d84cc0fc327f65af910fcf8f238d2633
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c08c2ff99a1d61c2be28a306cae4d9334535d1863b102589cd2d55ee6bca1a6
+oid sha256:3bb6755a2a28890a2c297eec26254b464de2f60f49387af25b290236695ca25d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3110035164602145,
+  "epoch": 0.31453764732908057,
   "eval_steps": 500,
-  "global_step": 17600,
+  "global_step": 17800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2472,6 +2472,34 @@
       "learning_rate": 3.828316742259135e-05,
       "loss": 0.519,
       "step": 17600
+    },
+    {
+      "epoch": 0.31188704917743104,
+      "grad_norm": 4.507582187652588,
+      "learning_rate": 3.823408140425281e-05,
+      "loss": 0.341,
+      "step": 17650
+    },
+    {
+      "epoch": 0.31277058189464757,
+      "grad_norm": 1.3272327184677124,
+      "learning_rate": 3.8184995385914276e-05,
+      "loss": 0.3352,
+      "step": 17700
+    },
+    {
+      "epoch": 0.3136541146118641,
+      "grad_norm": 2.516676664352417,
+      "learning_rate": 3.813590936757574e-05,
+      "loss": 0.4406,
+      "step": 17750
+    },
+    {
+      "epoch": 0.31453764732908057,
+      "grad_norm": 1.8230887651443481,
+      "learning_rate": 3.8086823349237206e-05,
+      "loss": 0.3822,
+      "step": 17800
     }
   ],
   "logging_steps": 50,