Training in progress, step 19400, checkpoint

last-checkpoint/README.md

@@ -1411,6 +1411,10 @@ You can finetune this model on your own dataset.
 | 0.3375 | 19100 | 0.4034        |
 | 0.3384 | 19150 | 0.3476        |
 | 0.3393 | 19200 | 0.363         |
+| 0.3402 | 19250 | 0.3182        |
+| 0.3410 | 19300 | 0.3238        |
+| 0.3419 | 19350 | 0.3043        |
+| 0.3428 | 19400 | 0.3902        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df4767c3af86ada5d64ec1e82bd26678813b4adc76a3a64ed02773659cbd3a1c
+oid sha256:c809593a4e810558b7888d3e612f15efc51c5db37b7d0556584318528272574d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ccaf4e0b9685757c9b442e5d71f5cf29896d66f4cfd0e1ebce8fda1955c2b6
+oid sha256:415abbc1cb409cdbfc5f39cef8004307a437f7f9f53d32a212cdbb581c0e45e1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed10afe606c6f5f77149b4d46e00c2aeeaae1b1caab0bfc6ff1ecf5b3e7db240
+oid sha256:3d2ab8a0a44cb42f1e8599f3d83384df303f90a2cb7c743c1865d9517262e7ef
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313b190fc264431dd211e2e439d1b10b0d124518229dd39cd606069f801f643f
+oid sha256:1362f5572f2c24512c1a63574772877b23a9cc814bbc44fff72e3cde5341c40a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48deb26910c4a97c1b79325c939cfd44618a0d9f9449782152989a93c937ce2
+oid sha256:404504f0a70dc9bf558ab7039928bcb08279726175fd39a9b8bf44633e9ee073
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3392765634111431,
+  "epoch": 0.3428106942800092,
   "eval_steps": 500,
-  "global_step": 19200,
+  "global_step": 19400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2696,6 +2696,34 @@
       "learning_rate": 3.671339655612496e-05,
       "loss": 0.363,
       "step": 19200
+    },
+    {
+      "epoch": 0.3401600961283596,
+      "grad_norm": 1.965834379196167,
+      "learning_rate": 3.666431053778642e-05,
+      "loss": 0.3182,
+      "step": 19250
+    },
+    {
+      "epoch": 0.34104362884557615,
+      "grad_norm": 1.607900857925415,
+      "learning_rate": 3.661522451944788e-05,
+      "loss": 0.3238,
+      "step": 19300
+    },
+    {
+      "epoch": 0.3419271615627927,
+      "grad_norm": 1.4051165580749512,
+      "learning_rate": 3.6566138501109346e-05,
+      "loss": 0.3043,
+      "step": 19350
+    },
+    {
+      "epoch": 0.3428106942800092,
+      "grad_norm": 1.4679523706436157,
+      "learning_rate": 3.651705248277081e-05,
+      "loss": 0.3902,
+      "step": 19400
     }
   ],
   "logging_steps": 50,