Training in progress, step 21600, checkpoint

last-checkpoint/README.md

@@ -1451,6 +1451,14 @@ You can finetune this model on your own dataset.
 | 0.3729 | 21100 | 0.2912        |
 | 0.3737 | 21150 | 0.3402        |
 | 0.3746 | 21200 | 0.3462        |
+| 0.3755 | 21250 | 0.2775        |
+| 0.3764 | 21300 | 0.3825        |
+| 0.3773 | 21350 | 0.3931        |
+| 0.3782 | 21400 | 0.4059        |
+| 0.3790 | 21450 | 0.3264        |
+| 0.3799 | 21500 | 0.2605        |
+| 0.3808 | 21550 | 0.3658        |
+| 0.3817 | 21600 | 0.3274        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb970c7628ca165b5a062a28ad2708c90ea109132db4b038f4972c1098f4cd3
+oid sha256:c445c6520c6e5f38ea82be358a6aa5ed9b820190229b0b058633fcc33d08a87d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ae8bcd2a7dafcb1ceb8e1ef8877981025e7fe727faad70bf73cbc035f46114
+oid sha256:b19db173fc766529b02b99cfb2249ee2f6c33d285fe8b221a72a08efcd3e58d8
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741bdb1704d229c73eec48b6812d828a33d2944f4e04e42ed9af5864cb8f4858
+oid sha256:4b87c442444260c01d6f6ddc3b986a278c1c2c567a0e9dfe7a512d3828e95a3e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6b2b89ac841094a59187934ba361ecf73eba3e326ef63976f096359b2648c3
+oid sha256:9c7f4b6f777ecf36ed08c5fe9d684383c44178ad62db77048c5678684b40b9a1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb71367724378f66d77db9556efcf84bf028b8330a0ff63dbe88a7a3d8a40e3
+oid sha256:00d6dd904f2193bc75011c53daf8f9374a62437ce21a5da2951c5f768935bcd3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37461787209980385,
+  "epoch": 0.381686133837536,
   "eval_steps": 500,
-  "global_step": 21200,
+  "global_step": 21600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2976,6 +2976,62 @@
       "learning_rate": 3.475093754295027e-05,
       "loss": 0.3462,
       "step": 21200
+    },
+    {
+      "epoch": 0.3755014048170204,
+      "grad_norm": 1.593705415725708,
+      "learning_rate": 3.470185152461173e-05,
+      "loss": 0.2775,
+      "step": 21250
+    },
+    {
+      "epoch": 0.3763849375342369,
+      "grad_norm": 2.1807069778442383,
+      "learning_rate": 3.465276550627319e-05,
+      "loss": 0.3825,
+      "step": 21300
+    },
+    {
+      "epoch": 0.37726847025145344,
+      "grad_norm": 1.6359409093856812,
+      "learning_rate": 3.460367948793466e-05,
+      "loss": 0.3931,
+      "step": 21350
+    },
+    {
+      "epoch": 0.3781520029686699,
+      "grad_norm": 1.5960018634796143,
+      "learning_rate": 3.455459346959612e-05,
+      "loss": 0.4059,
+      "step": 21400
+    },
+    {
+      "epoch": 0.37903553568588644,
+      "grad_norm": 3.367835283279419,
+      "learning_rate": 3.4505507451257585e-05,
+      "loss": 0.3264,
+      "step": 21450
+    },
+    {
+      "epoch": 0.37991906840310297,
+      "grad_norm": 1.5965161323547363,
+      "learning_rate": 3.445642143291905e-05,
+      "loss": 0.2605,
+      "step": 21500
+    },
+    {
+      "epoch": 0.3808026011203195,
+      "grad_norm": 1.5011396408081055,
+      "learning_rate": 3.440733541458051e-05,
+      "loss": 0.3658,
+      "step": 21550
+    },
+    {
+      "epoch": 0.381686133837536,
+      "grad_norm": 1.5021259784698486,
+      "learning_rate": 3.435824939624198e-05,
+      "loss": 0.3274,
+      "step": 21600
     }
   ],
   "logging_steps": 50,