Training in progress, step 41400, checkpoint

last-checkpoint/README.md

@@ -1343,6 +1343,10 @@ You can finetune this model on your own dataset.
 | 0.7263 | 41100 | 0.2924        |
 | 0.7271 | 41150 | 0.3982        |
 | 0.7280 | 41200 | 0.3379        |
+| 0.7289 | 41250 | 0.2876        |
+| 0.7298 | 41300 | 0.3289        |
+| 0.7307 | 41350 | 0.3119        |
+| 0.7316 | 41400 | 0.3007        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822f3843e5d129c0bef56a9f39c1ba41bc1fa63adfc0cc1868ef514ec0e5351b
+oid sha256:f43c6066a3ed8a797462ed1304e6dd3a538745bae56d08936296e98af5636e68
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086abfb2bf298dfb180a5caff3f861d5e6d3d3f4b12f1b97c28016e45648410e
+oid sha256:a1672d02aa4d93aaa27f89d6d65e2a20859a6cb3dd9c4432eeb82f6752f1dfc2
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9af559530a0818383bd31a393ecc6f9d55de4b1055f24c5ea4deb160850318
+oid sha256:7960809e3d7046461ba4b9405b6f71ec0619b99775d0184c422fcc4823ed73f8
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:360bf556a97129543cdfd5bc8f9267eddea0b0255ab50b0df912124a90a12812
+oid sha256:590d2263ee28ffeb3fc18603d4b5a73198cf1c208cbf77110c99f455e29bc8ec
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be053631e025ff40e9a33566316f50efe9d70bdf16e7a6393f50270033d19672
+oid sha256:1b3482c7848cfcb119d950c3c5d13bc2dc1e7095a6ad4e7fc2a9ca4e5c264983
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7280309589864112,
+  "epoch": 0.7315650898552774,
   "eval_steps": 500,
-  "global_step": 41200,
+  "global_step": 41400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5776,6 +5776,34 @@
       "learning_rate": 1.5125365690836625e-05,
       "loss": 0.3379,
       "step": 41200
+    },
+    {
+      "epoch": 0.7289144917036278,
+      "grad_norm": 2.0417702198028564,
+      "learning_rate": 1.5076279672498086e-05,
+      "loss": 0.2876,
+      "step": 41250
+    },
+    {
+      "epoch": 0.7297980244208443,
+      "grad_norm": 1.7424287796020508,
+      "learning_rate": 1.5027193654159549e-05,
+      "loss": 0.3289,
+      "step": 41300
+    },
+    {
+      "epoch": 0.7306815571380608,
+      "grad_norm": 1.1353446245193481,
+      "learning_rate": 1.4978107635821015e-05,
+      "loss": 0.3119,
+      "step": 41350
+    },
+    {
+      "epoch": 0.7315650898552774,
+      "grad_norm": 1.4479618072509766,
+      "learning_rate": 1.4929021617482478e-05,
+      "loss": 0.3007,
+      "step": 41400
     }
   ],
   "logging_steps": 50,