Training in progress, step 54000, checkpoint

last-checkpoint/README.md

@@ -1233,6 +1233,10 @@ You can finetune this model on your own dataset.
 | 0.9489 | 53700 | 0.303         |
 | 0.9498 | 53750 | 0.2651        |
 | 0.9507 | 53800 | 0.3384        |
+| 0.9516 | 53850 | 0.3324        |
+| 0.9524 | 53900 | 0.2253        |
+| 0.9533 | 53950 | 0.2942        |
+| 0.9542 | 54000 | 0.2997        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32883cc8380b5551ef8b0cc0e17f87142260e9e4e1f436103ef31fd1a32a59e7
+oid sha256:d367b7e3094b9509638dc3aab8cd20aa7d72d8a2079791ccc62c560157ab98a0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb8e455fcefebf6e65cc70da46171fa65d7d3724795dbd5ebe39eb526ed73b1
+oid sha256:ebfbc0071777229c33761182ed33d399969ad60e886668928a56deda972d74c1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1d10cc07f26722031d44ae9ed204b0fd93f2944405a821aaf7d32c94a690ee
+oid sha256:4b32f599e36a2e355058567f81a1cf5fcee6ab44b38d16fa4944caffd04dfbb3
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb8b2220528541cf3e98738aad3670d259e0a7ccf7ba003e8c4a04ead86cd5e
+oid sha256:8db4dd2df84f2b4b00fc6674bde1c97fccefdb7d0ae1f644ab8647d522122a7c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e02c7889d99a6f23f73ba0719fb9e5f5f23bfc59153bd58184aaf763c67dfbef
+oid sha256:f315466204b131c92fd6cdb19db01462071017aa8244ad37245b5ffab5418efa
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9506812037249739,
+  "epoch": 0.95421533459384,
   "eval_steps": 500,
-  "global_step": 53800,
+  "global_step": 54000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7540,6 +7540,34 @@
       "learning_rate": 2.761579391726061e-06,
       "loss": 0.3384,
       "step": 53800
+    },
+    {
+      "epoch": 0.9515647364421904,
+      "grad_norm": 3.1194252967834473,
+      "learning_rate": 2.712493373387524e-06,
+      "loss": 0.3324,
+      "step": 53850
+    },
+    {
+      "epoch": 0.952448269159407,
+      "grad_norm": 1.082737684249878,
+      "learning_rate": 2.663407355048988e-06,
+      "loss": 0.2253,
+      "step": 53900
+    },
+    {
+      "epoch": 0.9533318018766235,
+      "grad_norm": 1.0127415657043457,
+      "learning_rate": 2.614321336710452e-06,
+      "loss": 0.2942,
+      "step": 53950
+    },
+    {
+      "epoch": 0.95421533459384,
+      "grad_norm": 4.512701988220215,
+      "learning_rate": 2.5652353183719152e-06,
+      "loss": 0.2997,
+      "step": 54000
     }
   ],
   "logging_steps": 50,