Training in progress, step 10000, checkpoint

last-checkpoint/README.md

@@ -1187,40 +1187,44 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss |
-|:------:|:----:|:-------------:|
-| 0.1458 | 8250 | 0.4688        |
-| 0.1467 | 8300 | 0.3967        |
-| 0.1475 | 8350 | 0.4911        |
-| 0.1484 | 8400 | 0.4076        |
-| 0.1493 | 8450 | 0.398         |
-| 0.1502 | 8500 | 0.4203        |
-| 0.1511 | 8550 | 0.414         |
-| 0.1520 | 8600 | 0.3436        |
-| 0.1529 | 8650 | 0.436         |
-| 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        |
-| 0.1599 | 9050 | 0.4226        |
-| 0.1608 | 9100 | 0.3634        |
-| 0.1617 | 9150 | 0.4252        |
-| 0.1626 | 9200 | 0.3899        |
-| 0.1635 | 9250 | 0.4335        |
-| 0.1643 | 9300 | 0.4204        |
-| 0.1652 | 9350 | 0.5576        |
-| 0.1661 | 9400 | 0.4712        |
-| 0.1670 | 9450 | 0.366         |
-| 0.1679 | 9500 | 0.3932        |
-| 0.1688 | 9550 | 0.4836        |
-| 0.1696 | 9600 | 0.3989        |
-| 0.1705 | 9650 | 0.4025        |
-| 0.1714 | 9700 | 0.467         |
-| 0.1723 | 9750 | 0.3558        |
-| 0.1732 | 9800 | 0.3623        |
+| Epoch  | Step  | Training Loss |
+|:------:|:-----:|:-------------:|
+| 0.1458 | 8250  | 0.4688        |
+| 0.1467 | 8300  | 0.3967        |
+| 0.1475 | 8350  | 0.4911        |
+| 0.1484 | 8400  | 0.4076        |
+| 0.1493 | 8450  | 0.398         |
+| 0.1502 | 8500  | 0.4203        |
+| 0.1511 | 8550  | 0.414         |
+| 0.1520 | 8600  | 0.3436        |
+| 0.1529 | 8650  | 0.436         |
+| 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        |
+| 0.1599 | 9050  | 0.4226        |
+| 0.1608 | 9100  | 0.3634        |
+| 0.1617 | 9150  | 0.4252        |
+| 0.1626 | 9200  | 0.3899        |
+| 0.1635 | 9250  | 0.4335        |
+| 0.1643 | 9300  | 0.4204        |
+| 0.1652 | 9350  | 0.5576        |
+| 0.1661 | 9400  | 0.4712        |
+| 0.1670 | 9450  | 0.366         |
+| 0.1679 | 9500  | 0.3932        |
+| 0.1688 | 9550  | 0.4836        |
+| 0.1696 | 9600  | 0.3989        |
+| 0.1705 | 9650  | 0.4025        |
+| 0.1714 | 9700  | 0.467         |
+| 0.1723 | 9750  | 0.3558        |
+| 0.1732 | 9800  | 0.3623        |
+| 0.1741 | 9850  | 0.3438        |
+| 0.1749 | 9900  | 0.4193        |
+| 0.1758 | 9950  | 0.3173        |
+| 0.1767 | 10000 | 0.4569        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb531b99dca162667fb726e612e94c051018f779f5ff509bebfc939722f85886
+oid sha256:59544be7f17f690843a7b80096f64b1e3d29b5b39717cdc35f18b358c6aa330b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4671b0ce660e002e126649d2065bbd8f4633842c0c71f60f512ccc9dba9aba21
+oid sha256:7786e202caa6e3b4a367e42ca66bc274cb81d33f0bd440e8ec441d4bc4a6bbfb
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f0e0a231d2de9fe39fce57e75a586db12e27f102a687e2901f534fc55060b6
+oid sha256:6395e61165750a60c8ef153cec1804a8ff2db337ecba35b230075ccb363443da
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99e39c7d3d290833603a74523e3d4fc84b4f0f3056845fa8a3e71170347650dd
+oid sha256:e5f63680070bf507d18d4c264f788fe918fbe3f7f9774c4e8c816737dc3b4be4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a105c4972c9f577b54a9a86ea803b0dfd0803e1dbb9c812134e5869ca00a97d7
+oid sha256:84fcbd3212b661f15243c53e45a5f75752a67ffa024a0416b41d6014d2a1bc3d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17317241257443763,
+  "epoch": 0.1767065434433037,
   "eval_steps": 500,
-  "global_step": 9800,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1380,6 +1380,34 @@
       "learning_rate": 4.5936659401935956e-05,
       "loss": 0.3623,
       "step": 9800
+    },
+    {
+      "epoch": 0.17405594529165416,
+      "grad_norm": 2.1482434272766113,
+      "learning_rate": 4.588757338359742e-05,
+      "loss": 0.3438,
+      "step": 9850
+    },
+    {
+      "epoch": 0.17493947800887066,
+      "grad_norm": 1.458309531211853,
+      "learning_rate": 4.583848736525888e-05,
+      "loss": 0.4193,
+      "step": 9900
+    },
+    {
+      "epoch": 0.1758230107260872,
+      "grad_norm": 1.8698090314865112,
+      "learning_rate": 4.578940134692034e-05,
+      "loss": 0.3173,
+      "step": 9950
+    },
+    {
+      "epoch": 0.1767065434433037,
+      "grad_norm": 2.087970018386841,
+      "learning_rate": 4.574031532858181e-05,
+      "loss": 0.4569,
+      "step": 10000
     }
   ],
   "logging_steps": 50,