Training in progress, step 33000, checkpoint

last-checkpoint/README.md

@@ -1319,6 +1319,10 @@ You can finetune this model on your own dataset.
 | 0.5778 | 32700 | 0.3167        |
 | 0.5787 | 32750 | 0.3249        |
 | 0.5796 | 32800 | 0.2443        |
+| 0.5805 | 32850 | 0.4113        |
+| 0.5814 | 32900 | 0.3106        |
+| 0.5822 | 32950 | 0.2841        |
+| 0.5831 | 33000 | 0.2786        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c149da7590ac756041ddcfa88541f8f1672d3db78462e24c5f353c18f8cebb1d
+oid sha256:c8b30dec528d42a5a4b58c0779ef0039999b571e7dcbffef2ce111e2a8ea9c9a
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e3fdce41c8faa034bc2a86a395da561d04329337006adacae71b20e28f454b
+oid sha256:05ca6048b5b24e0bf5be4461f7f2142898161795f74ad16a156816bab1b72a69
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd0555a80b9ec33d03df384178c64ec05cac6166fd02e539edd48eaea584c82
+oid sha256:6f49fa5ae18072a5e2dded1d5d47789d5b789b12fb1067e4364304bf9f3ffb85
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd929e14e8b21c3d41ba7c4043d8f146abd5c239c07932d39cf0ff21021e6682
+oid sha256:6bbae4a00cda14f6ae28057ccdaac068a27c16d42d3b8e6b2ea21512dca904e3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14aac029153ded9414487d954464b6a95a9d2baa46bd0202f6e9ea6df2629338
+oid sha256:956ff3c13215961a07ede8fd0b963f4f72d5b8c4c7c87011ef7e07dba7cddb0e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5795974624940362,
+  "epoch": 0.5831315933629022,
   "eval_steps": 500,
-  "global_step": 32800,
+  "global_step": 33000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4600,6 +4600,34 @@
       "learning_rate": 2.3367889890243662e-05,
       "loss": 0.2443,
       "step": 32800
+    },
+    {
+      "epoch": 0.5804809952112526,
+      "grad_norm": 1.316084384918213,
+      "learning_rate": 2.331880387190513e-05,
+      "loss": 0.4113,
+      "step": 32850
+    },
+    {
+      "epoch": 0.5813645279284692,
+      "grad_norm": 1.8195414543151855,
+      "learning_rate": 2.3269717853566592e-05,
+      "loss": 0.3106,
+      "step": 32900
+    },
+    {
+      "epoch": 0.5822480606456857,
+      "grad_norm": 1.1715435981750488,
+      "learning_rate": 2.3220631835228053e-05,
+      "loss": 0.2841,
+      "step": 32950
+    },
+    {
+      "epoch": 0.5831315933629022,
+      "grad_norm": 1.3928303718566895,
+      "learning_rate": 2.3171545816889518e-05,
+      "loss": 0.2786,
+      "step": 33000
     }
   ],
   "logging_steps": 50,