Training in progress, step 54800, checkpoint

last-checkpoint/README.md

@@ -1249,6 +1249,10 @@ You can finetune this model on your own dataset.
 | 0.9631 | 54500 | 0.3229        |
 | 0.9639 | 54550 | 0.3064        |
 | 0.9648 | 54600 | 0.2925        |
+| 0.9657 | 54650 | 0.301         |
+| 0.9666 | 54700 | 0.2484        |
+| 0.9675 | 54750 | 0.3228        |
+| 0.9684 | 54800 | 0.2935        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6908b7749db5d0a826221cc7ecf07127dce59b7cc3e1282b238fab4edc8c06dc
+oid sha256:4660d5cc04b8230e366c2507b6edc6eb9740e5655f078f06d7fa8b708868348d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f62d74de1aa89c4bdb621c1ad70670a4bf5390f8a562eceb290549e4b451ee2
+oid sha256:b7ddc79258480305b86c7de987bf66efad05525fb132f3c4537096562844858a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c5edde7f9f695c0f4e2228698ef25b87e27f53ab10a510ae3e7d0707680eae
+oid sha256:fe80331ddc64a10f3922d2d2aa6e1345a324e582ebfcde4acd33dd3c01a97f23
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722f444d07f10344822682b1f6fd20e81bcbd5d550a56fbe82dc92a7f96b7a4c
+oid sha256:3a394d9ef4969559c2e748a44250c8baede91e41491cb79bd3a87fcd799d229f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2266beea22f5d851f4cb4c5de2987869a11c52788a165a553f5636a0c72bb073
+oid sha256:175e278f8a42116e02058ec0c5ec6fdf92f24c652abe7967b071b8b6350190f1
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9648177272004382,
+  "epoch": 0.9683518580693043,
   "eval_steps": 500,
-  "global_step": 54600,
+  "global_step": 54800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7652,6 +7652,34 @@
       "learning_rate": 1.9762030983094777e-06,
       "loss": 0.2925,
       "step": 54600
+    },
+    {
+      "epoch": 0.9657012599176548,
+      "grad_norm": 3.4723856449127197,
+      "learning_rate": 1.927117079970941e-06,
+      "loss": 0.301,
+      "step": 54650
+    },
+    {
+      "epoch": 0.9665847926348713,
+      "grad_norm": 3.3657915592193604,
+      "learning_rate": 1.8780310616324047e-06,
+      "loss": 0.2484,
+      "step": 54700
+    },
+    {
+      "epoch": 0.9674683253520878,
+      "grad_norm": 3.2125537395477295,
+      "learning_rate": 1.8289450432938681e-06,
+      "loss": 0.3228,
+      "step": 54750
+    },
+    {
+      "epoch": 0.9683518580693043,
+      "grad_norm": 3.5145859718322754,
+      "learning_rate": 1.779859024955332e-06,
+      "loss": 0.2935,
+      "step": 54800
     }
   ],
   "logging_steps": 50,