Training in progress, step 29000, checkpoint

last-checkpoint/README.md

@@ -1237,6 +1237,10 @@ You can finetune this model on your own dataset.
 | 0.5071 | 28700 | 0.2856        |
 | 0.5080 | 28750 | 0.3094        |
 | 0.5089 | 28800 | 0.3933        |
+| 0.5098 | 28850 | 0.3432        |
+| 0.5107 | 28900 | 0.3766        |
+| 0.5116 | 28950 | 0.3308        |
+| 0.5124 | 29000 | 0.3453        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526b3821cc22dabab82fd7d8615a24774c12cbfff6b5eac716e0f6982df2e75f
+oid sha256:451846c09636497fd112d06fea4af5c5807f5bba635b99c21653565147e61114
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2e0bba9075cf4efff85ef476d7466568456807cb8d8113da7d9be699bd6395
+oid sha256:23340dae6b29317ccbfc6381b15cd9845a0b70a4fe16736a45ec179849c8aec7
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9bd07dff5dde90cbe325d76b55b63b3e348e3827cc82b9387fe3b76aec8995f
+oid sha256:4c34c15295ec617b43466b44a678c1c552eeb9bc4954363b8b6c64f95ab20ef9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38258a3d5062f5c88ae31bcccabf324c777da3d611326c6312601c11bdc51857
+oid sha256:cf0c8dc0fee9ae5496d59e63cc2a462442628af8fbd2a0dba75a046615fd7a9e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2361ecc3f59af188c2bbc181225eb8037bc343b3fa1989c7fb6e76cff5a21110
+oid sha256:1df8a8c4e78370ac775514d3a5fa1a68e681a79225025bb6e6c736bca7dd3de6
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5089148451167147,
+  "epoch": 0.5124489759855807,
   "eval_steps": 500,
-  "global_step": 28800,
+  "global_step": 29000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4040,6 +4040,34 @@
       "learning_rate": 2.7292807916593038e-05,
       "loss": 0.3933,
       "step": 28800
+    },
+    {
+      "epoch": 0.5097983778339312,
+      "grad_norm": 3.18278431892395,
+      "learning_rate": 2.7243721898254506e-05,
+      "loss": 0.3432,
+      "step": 28850
+    },
+    {
+      "epoch": 0.5106819105511478,
+      "grad_norm": 1.7024506330490112,
+      "learning_rate": 2.7194635879915964e-05,
+      "loss": 0.3766,
+      "step": 28900
+    },
+    {
+      "epoch": 0.5115654432683642,
+      "grad_norm": 1.4224214553833008,
+      "learning_rate": 2.7145549861577428e-05,
+      "loss": 0.3308,
+      "step": 28950
+    },
+    {
+      "epoch": 0.5124489759855807,
+      "grad_norm": 1.5428136587142944,
+      "learning_rate": 2.7096463843238896e-05,
+      "loss": 0.3453,
+      "step": 29000
     }
   ],
   "logging_steps": 50,