Training in progress, step 54200, checkpoint

last-checkpoint/README.md

@@ -1237,6 +1237,10 @@ You can finetune this model on your own dataset.
 | 0.9524 | 53900 | 0.2253        |
 | 0.9533 | 53950 | 0.2942        |
 | 0.9542 | 54000 | 0.2997        |
+| 0.9551 | 54050 | 0.3954        |
+| 0.9560 | 54100 | 0.3496        |
+| 0.9569 | 54150 | 0.2609        |
+| 0.9577 | 54200 | 0.3942        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d367b7e3094b9509638dc3aab8cd20aa7d72d8a2079791ccc62c560157ab98a0
+oid sha256:23c626c07a484cf440299aeab5250215215dc9a9504ba76a2c4d8cbb2ee9f703
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebfbc0071777229c33761182ed33d399969ad60e886668928a56deda972d74c1
+oid sha256:31a1ca22d51c4852d7b597cdc6df536f10b0a83016c09217dd4a746f81603dfe
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b32f599e36a2e355058567f81a1cf5fcee6ab44b38d16fa4944caffd04dfbb3
+oid sha256:f12eb5ebd31ffd5667160725a966706229b611b4915c7e9e0942936f7af1fe3f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db4dd2df84f2b4b00fc6674bde1c97fccefdb7d0ae1f644ab8647d522122a7c
+oid sha256:ecc3972897ec297e0f8185ac88e544940af5d6dbb43a2cbce3b08ddf982f52c7
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f315466204b131c92fd6cdb19db01462071017aa8244ad37245b5ffab5418efa
+oid sha256:c74d3b4e96c259643bb77262d75e1f23a0f31a3e975d23f8db0d5e5def888ead
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.95421533459384,
+  "epoch": 0.9577494654627061,
   "eval_steps": 500,
-  "global_step": 54000,
+  "global_step": 54200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7568,6 +7568,34 @@
       "learning_rate": 2.5652353183719152e-06,
       "loss": 0.2997,
       "step": 54000
+    },
+    {
+      "epoch": 0.9550988673110565,
+      "grad_norm": 1.0720359086990356,
+      "learning_rate": 2.5161493000333786e-06,
+      "loss": 0.3954,
+      "step": 54050
+    },
+    {
+      "epoch": 0.9559824000282731,
+      "grad_norm": 1.608279824256897,
+      "learning_rate": 2.467063281694842e-06,
+      "loss": 0.3496,
+      "step": 54100
+    },
+    {
+      "epoch": 0.9568659327454896,
+      "grad_norm": 1.2330106496810913,
+      "learning_rate": 2.4179772633563054e-06,
+      "loss": 0.2609,
+      "step": 54150
+    },
+    {
+      "epoch": 0.9577494654627061,
+      "grad_norm": 1.4279929399490356,
+      "learning_rate": 2.3688912450177693e-06,
+      "loss": 0.3942,
+      "step": 54200
     }
   ],
   "logging_steps": 50,