Training in progress, step 14400, checkpoint

last-checkpoint/README.md

@@ -1311,6 +1311,10 @@ You can finetune this model on your own dataset.
 | 0.2492 | 14100 | 0.3853        |
 | 0.2500 | 14150 | 0.4068        |
 | 0.2509 | 14200 | 0.4071        |
+| 0.2518 | 14250 | 0.3588        |
+| 0.2527 | 14300 | 0.4161        |
+| 0.2536 | 14350 | 0.3431        |
+| 0.2545 | 14400 | 0.3576        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4503e7e25e7a5b0e3fa0b1c8a23c410d156686b9c3f0b8c96dc82d39a0e1b1c
+oid sha256:c70d1baeacb306a6e3e4e7da1daf6668ef9a846b36b36844f97182da49b7189d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5d943bf4dc121c9308255043fd16448b3eb77f764283d83e12427c3022fba6
+oid sha256:6c7cc231dc6a04e0cb1fde6371ac1117217c084c2ff5861f99992f6271b0b2ae
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215f5b0f373f4e3ad43a7c01ffdbf3925bbe7ae7185a457cfe9021eb94481c4b
+oid sha256:1575cd53f4b8b110d92e8c23aa79a7bcf9dc9c336882843030d5971034763624
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ca0c424595d60ecac702728b12c84553636fe40229728f0d7faf3360276035
+oid sha256:97511a6060aacb39a58a4067ef60a5d731c4117afaf40a314802e695ac048d50
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:639b76dd84e3ff9b63a4b686b5478e8730dc63d794913f7a823faab8ec6c2e15
+oid sha256:696c7475f37eb1308f8246ec63f84866eb3d506203673b38e04a231cb4eacd6d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25092329168949123,
+  "epoch": 0.25445742255835735,
   "eval_steps": 500,
-  "global_step": 14200,
+  "global_step": 14400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1996,6 +1996,34 @@
       "learning_rate": 4.161905322887829e-05,
       "loss": 0.4071,
       "step": 14200
+    },
+    {
+      "epoch": 0.25180682440670776,
+      "grad_norm": 1.7028473615646362,
+      "learning_rate": 4.156996721053975e-05,
+      "loss": 0.3588,
+      "step": 14250
+    },
+    {
+      "epoch": 0.2526903571239243,
+      "grad_norm": 1.6032434701919556,
+      "learning_rate": 4.1520881192201214e-05,
+      "loss": 0.4161,
+      "step": 14300
+    },
+    {
+      "epoch": 0.2535738898411408,
+      "grad_norm": 1.6103026866912842,
+      "learning_rate": 4.147179517386268e-05,
+      "loss": 0.3431,
+      "step": 14350
+    },
+    {
+      "epoch": 0.25445742255835735,
+      "grad_norm": 3.727078914642334,
+      "learning_rate": 4.142270915552414e-05,
+      "loss": 0.3576,
+      "step": 14400
     }
   ],
   "logging_steps": 50,