Training in progress, step 31400, checkpoint

last-checkpoint/README.md

@@ -1285,6 +1285,10 @@ You can finetune this model on your own dataset.
 | 0.5496 | 31100 | 0.2833        |
 | 0.5504 | 31150 | 0.3           |
 | 0.5513 | 31200 | 0.3568        |
+| 0.5522 | 31250 | 0.3268        |
+| 0.5531 | 31300 | 0.4005        |
+| 0.5540 | 31350 | 0.2993        |
+| 0.5549 | 31400 | 0.3463        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ba70ef39f7de14bf486cd6a1d1eb679e64ef73a054af28b2b85197a684e102
+oid sha256:61791a9f27b2e84e2748c75d563b418265e6d5395cbf211b0cd0f03e7a800569
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff78a2cf01e3f4659cebb48c444154cc30791c7f270bbce76100fba6585b1f7
+oid sha256:18bdca8989ebbde834c52a39d768225227cd3368f6e914278dbdb9e94069701f
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:841783816c90320afe8451e0bfbb0199a5902c04c786b414a06919466808b3cc
+oid sha256:90c0f464ce2d63e5775d5f69a53393003698611f7c0fd1450ee54986328e19d1
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc906030957a3fd71ac5d5f065e62c1d0ee722af605316e3fb4aeb71bb2da6d9
+oid sha256:8d8621fe1648dc96d7d6a12a9e96d1ea20e9a16f5271880935750dfe7f0b53b1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e97975d3fced0482e8faf4c84b2ad2283b6983f383d82a9b91bf8d75fbaca1
+oid sha256:8192cf6ea07163c3522a31666ef2d6f88f70490e78651f44e286f3d02a1bce81
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5513244155431075,
+  "epoch": 0.5548585464119736,
   "eval_steps": 500,
-  "global_step": 31200,
+  "global_step": 31400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4376,6 +4376,34 @@
       "learning_rate": 2.493766075671006e-05,
       "loss": 0.3568,
       "step": 31200
+    },
+    {
+      "epoch": 0.552207948260324,
+      "grad_norm": 1.8015788793563843,
+      "learning_rate": 2.4888574738371522e-05,
+      "loss": 0.3268,
+      "step": 31250
+    },
+    {
+      "epoch": 0.5530914809775406,
+      "grad_norm": 2.7606303691864014,
+      "learning_rate": 2.4839488720032987e-05,
+      "loss": 0.4005,
+      "step": 31300
+    },
+    {
+      "epoch": 0.5539750136947571,
+      "grad_norm": 1.3418834209442139,
+      "learning_rate": 2.479040270169445e-05,
+      "loss": 0.2993,
+      "step": 31350
+    },
+    {
+      "epoch": 0.5548585464119736,
+      "grad_norm": 1.3790879249572754,
+      "learning_rate": 2.4741316683355912e-05,
+      "loss": 0.3463,
+      "step": 31400
     }
   ],
   "logging_steps": 50,