Training in progress, step 9000, checkpoint

last-checkpoint/README.md

@@ -1201,6 +1201,10 @@ You can finetune this model on your own dataset.
 | 0.1537 | 8700 | 0.3761        |
 | 0.1546 | 8750 | 0.5579        |
 | 0.1555 | 8800 | 0.441         |
+| 0.1564 | 8850 | 0.5877        |
+| 0.1573 | 8900 | 0.4081        |
+| 0.1582 | 8950 | 0.4648        |
+| 0.1590 | 9000 | 0.4321        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48362ba7fcb9b7f2c1aa7030a50c6258f1f4d6cc4f1665e7ca632872744db5c0
+oid sha256:6833db3941c48530d63f16a4641cb58d29681db52bfc4aaba9787486862f28a0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a1f68b3f77c2bf8fd6e4f0bdee7b8ce97a773c56cdc7093cbfde49c00998f8
+oid sha256:fc8f323339f8042019b8128089add42f66d2a56c4dfd5f02e68b4884b9f08cad
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14cd2e3712404ebb968f80623888d77e60a6a55be515062adfbd0e098660e63a
+oid sha256:d8b31b0e1d81266033020b3fd3836c1b6a14642adb57f047a1bc520e453a6aba
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6c0ca588079b6a2e8be7c5b7bc6af97572af78d73d1dce8d6f30fcc361b6a3
+oid sha256:c0a063eb0473b3b545a1a6d08a6917737011cdcb54e4175440233b96c566f83c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89db5df6d87e4cc0368652d8350a2c32d46bae130899047ae58e000eec6fa2a0
+oid sha256:f78894f5196d0952d3fc803e041442456b12fd7839191717af3aecab8279af9f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15550175823010726,
+  "epoch": 0.15903588909897334,
   "eval_steps": 500,
-  "global_step": 8800,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1240,6 +1240,34 @@
       "learning_rate": 4.691837976870668e-05,
       "loss": 0.441,
       "step": 8800
+    },
+    {
+      "epoch": 0.15638529094732379,
+      "grad_norm": 2.2241523265838623,
+      "learning_rate": 4.686929375036815e-05,
+      "loss": 0.5877,
+      "step": 8850
+    },
+    {
+      "epoch": 0.15726882366454029,
+      "grad_norm": 1.8084393739700317,
+      "learning_rate": 4.6820207732029605e-05,
+      "loss": 0.4081,
+      "step": 8900
+    },
+    {
+      "epoch": 0.15815235638175681,
+      "grad_norm": 1.5464160442352295,
+      "learning_rate": 4.677112171369108e-05,
+      "loss": 0.4648,
+      "step": 8950
+    },
+    {
+      "epoch": 0.15903588909897334,
+      "grad_norm": 1.7731395959854126,
+      "learning_rate": 4.672203569535254e-05,
+      "loss": 0.4321,
+      "step": 9000
     }
   ],
   "logging_steps": 50,