Training in progress, step 10200, checkpoint

last-checkpoint/README.md

@@ -1225,6 +1225,10 @@ You can finetune this model on your own dataset.
 | 0.1749 | 9900  | 0.4193        |
 | 0.1758 | 9950  | 0.3173        |
 | 0.1767 | 10000 | 0.4569        |
+| 0.1776 | 10050 | 0.4538        |
+| 0.1785 | 10100 | 0.4422        |
+| 0.1794 | 10150 | 0.3747        |
+| 0.1802 | 10200 | 0.3989        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59544be7f17f690843a7b80096f64b1e3d29b5b39717cdc35f18b358c6aa330b
+oid sha256:8b1113f1dc63b4ef74f5c024aa4257a74f5c601162a5392123b472bd440c772d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7786e202caa6e3b4a367e42ca66bc274cb81d33f0bd440e8ec441d4bc4a6bbfb
+oid sha256:372cd21ba6640c7fb2d1ef5b71e6d5270fa8bff460e3c646226db5c68492b951
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6395e61165750a60c8ef153cec1804a8ff2db337ecba35b230075ccb363443da
+oid sha256:11b6cb074bbe2129c4a92512f6b7604d9e93435cd6ffac4a406363aba2e66f67
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f63680070bf507d18d4c264f788fe918fbe3f7f9774c4e8c816737dc3b4be4
+oid sha256:8373615cf09b792af1b9fd441a341b87607a411c0918e8ae083ffab9de6dcc10
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84fcbd3212b661f15243c53e45a5f75752a67ffa024a0416b41d6014d2a1bc3d
+oid sha256:58c8231fde4f806f412947f64ac786f123198ace358add629069cb5de99c1e42
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1767065434433037,
+  "epoch": 0.18024067431216978,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1408,6 +1408,34 @@
       "learning_rate": 4.574031532858181e-05,
       "loss": 0.4569,
       "step": 10000
+    },
+    {
+      "epoch": 0.17759007616052022,
+      "grad_norm": 1.6226812601089478,
+      "learning_rate": 4.569122931024327e-05,
+      "loss": 0.4538,
+      "step": 10050
+    },
+    {
+      "epoch": 0.17847360887773675,
+      "grad_norm": 1.9845385551452637,
+      "learning_rate": 4.564214329190474e-05,
+      "loss": 0.4422,
+      "step": 10100
+    },
+    {
+      "epoch": 0.17935714159495325,
+      "grad_norm": 1.7016047239303589,
+      "learning_rate": 4.5593057273566195e-05,
+      "loss": 0.3747,
+      "step": 10150
+    },
+    {
+      "epoch": 0.18024067431216978,
+      "grad_norm": 2.2167670726776123,
+      "learning_rate": 4.5543971255227666e-05,
+      "loss": 0.3989,
+      "step": 10200
     }
   ],
   "logging_steps": 50,