Training in progress, step 46800, checkpoint

last-checkpoint/README.md

@@ -1225,6 +1225,10 @@ You can finetune this model on your own dataset.
 | 0.8217 | 46500 | 0.299         |
 | 0.8226 | 46550 | 0.2908        |
 | 0.8235 | 46600 | 0.3134        |
+| 0.8243 | 46650 | 0.2603        |
+| 0.8252 | 46700 | 0.2965        |
+| 0.8261 | 46750 | 0.2506        |
+| 0.8270 | 46800 | 0.2258        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142d4c8ad016790fcbcb6bf5e68a5dcbdef2e9705f12fb07f181ef927a93333a
+oid sha256:06c3f18fa41ad103d30f8534ab7132db4ee0061b54edf40285b4af72b13eb56f
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9041e81c6e0019831198e6ff3f401abd14ed00e89f927bc706b188ab63b76d
+oid sha256:7fd6c1d98fe362a0c2eb43d38b5cdf5892278019bdee6a0ede5aba69437e6bc1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b3c6e69019b821213bf9d49d5b01da485427d6ae65f3fc1547d69ab36ff927
+oid sha256:bc474fa5fa7ccd3f751905ccba31cf8241a798bcffde04ca50c28aabfb2c8fc4
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c76708a6769f6750a136317961002a8e94193f536a6dd070918f7e493fa54130
+oid sha256:7f4d5223b0e67d5c0eb5511f7b2157df3119d42796d741c478e1b9dd9b2daa03
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9203611a5650cd81962fd740668d81290ec5b3a4f3232d739000dc19f94e073
+oid sha256:deb3a6b85091a07e122d9b08dbed39a677740be0c318acc9f799b2491273dc34
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8234524924457952,
+  "epoch": 0.8269866233146613,
   "eval_steps": 500,
-  "global_step": 46600,
+  "global_step": 46800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6532,6 +6532,34 @@
       "learning_rate": 9.826039151008228e-06,
       "loss": 0.3134,
       "step": 46600
+    },
+    {
+      "epoch": 0.8243360251630117,
+      "grad_norm": 1.4541929960250854,
+      "learning_rate": 9.776953132669691e-06,
+      "loss": 0.2603,
+      "step": 46650
+    },
+    {
+      "epoch": 0.8252195578802283,
+      "grad_norm": 1.499306559562683,
+      "learning_rate": 9.727867114331154e-06,
+      "loss": 0.2965,
+      "step": 46700
+    },
+    {
+      "epoch": 0.8261030905974448,
+      "grad_norm": 2.7763867378234863,
+      "learning_rate": 9.678781095992617e-06,
+      "loss": 0.2506,
+      "step": 46750
+    },
+    {
+      "epoch": 0.8269866233146613,
+      "grad_norm": 1.4240554571151733,
+      "learning_rate": 9.629695077654082e-06,
+      "loss": 0.2258,
+      "step": 46800
     }
   ],
   "logging_steps": 50,