Training in progress, step 33200, checkpoint

last-checkpoint/README.md

@@ -1323,6 +1323,10 @@ You can finetune this model on your own dataset.
 | 0.5814 | 32900 | 0.3106        |
 | 0.5822 | 32950 | 0.2841        |
 | 0.5831 | 33000 | 0.2786        |
+| 0.5840 | 33050 | 0.3576        |
+| 0.5849 | 33100 | 0.2475        |
+| 0.5858 | 33150 | 0.348         |
+| 0.5867 | 33200 | 0.2779        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b30dec528d42a5a4b58c0779ef0039999b571e7dcbffef2ce111e2a8ea9c9a
+oid sha256:99a52192178bbce89ad50c778d4f9bf6832b1481f86c47e744cf7ba729322eed
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ca6048b5b24e0bf5be4461f7f2142898161795f74ad16a156816bab1b72a69
+oid sha256:5d206f55adca7413c00e9799da5a83e0d7eb862fb2cf37236c2e4b104f35bcc0
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f49fa5ae18072a5e2dded1d5d47789d5b789b12fb1067e4364304bf9f3ffb85
+oid sha256:e84175a067ef9ea1b90f9c520af471e35f0e36e402ca9c6d4d4252339d961a0e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bbae4a00cda14f6ae28057ccdaac068a27c16d42d3b8e6b2ea21512dca904e3
+oid sha256:965065b740d957921866df8f0457265c0a3e6b7684746ca495482effad4548c9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:956ff3c13215961a07ede8fd0b963f4f72d5b8c4c7c87011ef7e07dba7cddb0e
+oid sha256:ffb425c5828f81b7dea1abb11cdabe1e52bb8172393d755ab6f7986190b2e5fb
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5831315933629022,
+  "epoch": 0.5866657242317683,
   "eval_steps": 500,
-  "global_step": 33000,
+  "global_step": 33200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4628,6 +4628,34 @@
       "learning_rate": 2.3171545816889518e-05,
       "loss": 0.2786,
       "step": 33000
+    },
+    {
+      "epoch": 0.5840151260801187,
+      "grad_norm": 1.4881165027618408,
+      "learning_rate": 2.3122459798550982e-05,
+      "loss": 0.3576,
+      "step": 33050
+    },
+    {
+      "epoch": 0.5848986587973353,
+      "grad_norm": 2.8615384101867676,
+      "learning_rate": 2.3073373780212447e-05,
+      "loss": 0.2475,
+      "step": 33100
+    },
+    {
+      "epoch": 0.5857821915145518,
+      "grad_norm": 1.819924235343933,
+      "learning_rate": 2.302428776187391e-05,
+      "loss": 0.348,
+      "step": 33150
+    },
+    {
+      "epoch": 0.5866657242317683,
+      "grad_norm": 1.5402089357376099,
+      "learning_rate": 2.297520174353537e-05,
+      "loss": 0.2779,
+      "step": 33200
     }
   ],
   "logging_steps": 50,