Training in progress, step 30000, checkpoint

last-checkpoint/README.md

@@ -1257,6 +1257,10 @@ You can finetune this model on your own dataset.
 | 0.5248 | 29700 | 0.3791        |
 | 0.5257 | 29750 | 0.3346        |
 | 0.5266 | 29800 | 0.2743        |
+| 0.5275 | 29850 | 0.2927        |
+| 0.5284 | 29900 | 0.3775        |
+| 0.5292 | 29950 | 0.3114        |
+| 0.5301 | 30000 | 0.2383        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f825b875fd3411a67519723584f534dbb07906a94fc074203b6899cfdda34fb1
+oid sha256:7bb95ae4ccdc1225fa61fa51177153a06dac70457a68aef666cd0a1eed08ba1a
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4f7f00258615a01948f967086a40fe67b9d0f30411b6eeb7956c1d0e25c22c
+oid sha256:71a7aa1c487fa54454696db788c6e152307a22042949edfa76090e98becd066e
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c8b292b591500813d59792390c9a1e49d14483b29c2cccf2081a971b6f3cb9
+oid sha256:fb7e98986a27a407adbceaabeb5013a890ed1e6ec34d83926bcddbcf669ec678
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701ad9ee8b64e03a45e44d6fd168805d271251720d2ba20141feedf9e8d7209a
+oid sha256:571d19b834362983e79e52affef058f87dcf5429e544d22e5fa9121931e62b84
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1bd9cc4f297f5700001cd99fe1f86afbb411b53d2ea438dae9c8e2c077cfdb
+oid sha256:c9f6718e4a878b8d1ac645f468a8f963dffffaa70e597cacccbc9fdb9c7011a3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.526585499461045,
+  "epoch": 0.5301196303299112,
   "eval_steps": 500,
-  "global_step": 29800,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4180,6 +4180,34 @@
       "learning_rate": 2.631108754982231e-05,
       "loss": 0.2743,
       "step": 29800
+    },
+    {
+      "epoch": 0.5274690321782616,
+      "grad_norm": 1.63582181930542,
+      "learning_rate": 2.6262001531483772e-05,
+      "loss": 0.2927,
+      "step": 29850
+    },
+    {
+      "epoch": 0.5283525648954781,
+      "grad_norm": 1.843386173248291,
+      "learning_rate": 2.6212915513145237e-05,
+      "loss": 0.3775,
+      "step": 29900
+    },
+    {
+      "epoch": 0.5292360976126946,
+      "grad_norm": 1.236327886581421,
+      "learning_rate": 2.61638294948067e-05,
+      "loss": 0.3114,
+      "step": 29950
+    },
+    {
+      "epoch": 0.5301196303299112,
+      "grad_norm": 1.5327879190444946,
+      "learning_rate": 2.6114743476468162e-05,
+      "loss": 0.2383,
+      "step": 30000
     }
   ],
   "logging_steps": 50,