Training in progress, step 13000, checkpoint

last-checkpoint/README.md

@@ -1281,6 +1281,10 @@ You can finetune this model on your own dataset.
 | 0.2244 | 12700 | 0.4847        |
 | 0.2253 | 12750 | 0.4           |
 | 0.2262 | 12800 | 0.4755        |
+| 0.2271 | 12850 | 0.3399        |
+| 0.2280 | 12900 | 0.3297        |
+| 0.2288 | 12950 | 0.4071        |
+| 0.2297 | 13000 | 0.4069        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaffa127a39fd901b451a02082dd73e610a44a04250335e841bd1c868ed76e7e
+oid sha256:6a99dbe886ae3b48dcbc17c9add8a4bd329b9679468fb6c162134aa8463356d5
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3099f71f55b4d64c3a23404f7faf834041dd15d4ee0a70f3ac8b4ad68054749c
+oid sha256:172018835a66c5e0120e97d48b6c921f1ef2ffa9a8cbf21cd65db32f82f39fdc
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17530db209b84526ccd898abb8b9457fb6227f11278068f45b5d61574f612471
+oid sha256:d0a97494fc3a06e5f40c026a0f41674c967ae21ee669dae8157fc95b5874a10f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ad444446e22ff06cf0b10a8954472ffaf9e2730e13a164edba0cc9cb5b081cd
+oid sha256:c530f7e876503d8e13ff43d14d04017a4f2689d24e141257ebdc42956b0bd010
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef5f6a8cf979ba7b777c43842eed460a7fa788b746409fc99d6b1fe7576d8044
+oid sha256:f8a946928e63f8835465228f3f0df594649164b69e587f90a1cdfe3fc4f57565
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22618437560742874,
+  "epoch": 0.22971850647629483,
   "eval_steps": 500,
-  "global_step": 12800,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1800,6 +1800,34 @@
       "learning_rate": 4.299248002199054e-05,
       "loss": 0.4755,
       "step": 12800
+    },
+    {
+      "epoch": 0.22706790832464527,
+      "grad_norm": 1.7713844776153564,
+      "learning_rate": 4.2943394003652e-05,
+      "loss": 0.3399,
+      "step": 12850
+    },
+    {
+      "epoch": 0.22795144104186177,
+      "grad_norm": 1.2936394214630127,
+      "learning_rate": 4.289528970568024e-05,
+      "loss": 0.3297,
+      "step": 12900
+    },
+    {
+      "epoch": 0.2288349737590783,
+      "grad_norm": 1.6622658967971802,
+      "learning_rate": 4.28462036873417e-05,
+      "loss": 0.4071,
+      "step": 12950
+    },
+    {
+      "epoch": 0.22971850647629483,
+      "grad_norm": 1.3949196338653564,
+      "learning_rate": 4.279711766900316e-05,
+      "loss": 0.4069,
+      "step": 13000
     }
   ],
   "logging_steps": 50,