Training in progress, step 29200, checkpoint

last-checkpoint/README.md

@@ -1241,6 +1241,10 @@ You can finetune this model on your own dataset.
 | 0.5107 | 28900 | 0.3766        |
 | 0.5116 | 28950 | 0.3308        |
 | 0.5124 | 29000 | 0.3453        |
+| 0.5133 | 29050 | 0.2904        |
+| 0.5142 | 29100 | 0.2647        |
+| 0.5151 | 29150 | 0.4395        |
+| 0.5160 | 29200 | 0.295         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451846c09636497fd112d06fea4af5c5807f5bba635b99c21653565147e61114
+oid sha256:6302ef96cfec2421b0ca1ae5faa95bc5dd4d222138074480f8f7e034e0f55fc2
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23340dae6b29317ccbfc6381b15cd9845a0b70a4fe16736a45ec179849c8aec7
+oid sha256:6dd6b7448710e566b9e15662a68fba694d10e1ca083c5858cb67b26f8f1705c9
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c34c15295ec617b43466b44a678c1c552eeb9bc4954363b8b6c64f95ab20ef9
+oid sha256:1049af8581efffa2917702c9f959fe2570b21616b1ec430cb670ed82abab5b37
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0c8dc0fee9ae5496d59e63cc2a462442628af8fbd2a0dba75a046615fd7a9e
+oid sha256:019221f3192f4927c921b123577a1666f9b9f4c37e86b8641ed6cf124537ad31
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df8a8c4e78370ac775514d3a5fa1a68e681a79225025bb6e6c736bca7dd3de6
+oid sha256:f8bdd077ed24c7c735344da9353b0b35d61ed70a50b66211d3c4d79475e4b984
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5124489759855807,
+  "epoch": 0.5159831068544468,
   "eval_steps": 500,
-  "global_step": 29000,
+  "global_step": 29200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4068,6 +4068,34 @@
       "learning_rate": 2.7096463843238896e-05,
       "loss": 0.3453,
       "step": 29000
+    },
+    {
+      "epoch": 0.5133325087027972,
+      "grad_norm": 1.4710556268692017,
+      "learning_rate": 2.7047377824900354e-05,
+      "loss": 0.2904,
+      "step": 29050
+    },
+    {
+      "epoch": 0.5142160414200138,
+      "grad_norm": 1.5080032348632812,
+      "learning_rate": 2.6998291806561822e-05,
+      "loss": 0.2647,
+      "step": 29100
+    },
+    {
+      "epoch": 0.5150995741372303,
+      "grad_norm": 1.7176605463027954,
+      "learning_rate": 2.6949205788223287e-05,
+      "loss": 0.4395,
+      "step": 29150
+    },
+    {
+      "epoch": 0.5159831068544468,
+      "grad_norm": 1.4339267015457153,
+      "learning_rate": 2.6900119769884745e-05,
+      "loss": 0.295,
+      "step": 29200
     }
   ],
   "logging_steps": 50,