Training in progress, step 27800, checkpoint

last-checkpoint/README.md

@@ -1213,6 +1213,10 @@ You can finetune this model on your own dataset.
 | 0.4859 | 27500 | 0.3959        |
 | 0.4868 | 27550 | 0.3754        |
 | 0.4877 | 27600 | 0.3163        |
+| 0.4886 | 27650 | 0.35          |
+| 0.4895 | 27700 | 0.3397        |
+| 0.4904 | 27750 | 0.3853        |
+| 0.4912 | 27800 | 0.2568        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7664a0a0f5ecfa598f2701a1ff37b213f978409532fb7f103898692f18c2a725
+oid sha256:cdfacab69b0182b267f66ce210afc2a929861f8a381fcb609abe7250efbad353
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a099107f68059125238e954d06fc6e590362c99b51020b9fe7fdd85f6a409e
+oid sha256:d101e20d6391c1d00393694ed7c13a8ed5d54b7059e36795228521dd1687fa5d
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5363905a5180ae7b6dc66d9d24e9725568295ce2578c5fa9423e53d3f4ca3e
+oid sha256:e6ca64734da2f01bf95a86973d81c98cfbac0699ced506e6f5d14bfc6d5da161
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01018da1a415cc4a2591785629b35e825cfe5ca85d564c2b7250cf57ca5ee003
+oid sha256:e43246be50aae83c1910a5dc4ce6db1d2f843a5836c33c56704984643d301b0e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a4e22174e8f57aba7a9808391b59167576034c6b53740dc89da4532411a156
+oid sha256:e6ed64f7e529220ff21286b422216dac7ffe45f3b61319d3fedf56a8725ea92a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.48771005990351823,
+  "epoch": 0.4912441907723843,
   "eval_steps": 500,
-  "global_step": 27600,
+  "global_step": 27800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3872,6 +3872,34 @@
       "learning_rate": 2.8470872356717916e-05,
       "loss": 0.3163,
       "step": 27600
+    },
+    {
+      "epoch": 0.48859359262073476,
+      "grad_norm": 1.654520869255066,
+      "learning_rate": 2.8421786338379374e-05,
+      "loss": 0.35,
+      "step": 27650
+    },
+    {
+      "epoch": 0.4894771253379513,
+      "grad_norm": 1.5777958631515503,
+      "learning_rate": 2.8372700320040842e-05,
+      "loss": 0.3397,
+      "step": 27700
+    },
+    {
+      "epoch": 0.49036065805516776,
+      "grad_norm": 1.4474226236343384,
+      "learning_rate": 2.8323614301702307e-05,
+      "loss": 0.3853,
+      "step": 27750
+    },
+    {
+      "epoch": 0.4912441907723843,
+      "grad_norm": 1.603667140007019,
+      "learning_rate": 2.8274528283363765e-05,
+      "loss": 0.2568,
+      "step": 27800
     }
   ],
   "logging_steps": 50,