Training in progress, step 13800, checkpoint

last-checkpoint/README.md

@@ -1299,6 +1299,10 @@ You can finetune this model on your own dataset.
 | 0.2386 | 13500 | 0.3666        |
 | 0.2394 | 13550 | 0.3792        |
 | 0.2403 | 13600 | 0.3341        |
+| 0.2412 | 13650 | 0.4906        |
+| 0.2421 | 13700 | 0.541         |
+| 0.2430 | 13750 | 0.3936        |
+| 0.2439 | 13800 | 0.3871        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4084e1bfff0b99538c5f3a28b4d5c1e1e185739ef9b70378a9c51e1850e71288
+oid sha256:31148f752a25ceb10b5c213db27c39897a7101ce74c3a2bf632bddbac89942e4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8dc4ebf2f928553dc4ad0074e5667a33bafb03875d3b2cedcef46264b4d6a1
+oid sha256:4531c62c1edbd90a082131f940d6f09413598c9a48c2db99b1d4be025b30823d
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51aa928f18dc099dd2a30735dc4332b9f48a48dd04ae86490c1e2444ca246dd2
+oid sha256:645652864b8ca64a5c235d7c8d3b0d5b69daae205059b96d011831548d91d7f1
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979320729f9d3865290bdaaad2a8c03ebcf3b70e0f3a530f818585a8c564617e
+oid sha256:4a8dae4393c167bd70d32b16d8177fd63b4e64aff7df734eda7e1fde5cf1c852
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2936671a733ca2c04f8afa89dc17be4e7bd4f657d12145bb68896d055120fca2
+oid sha256:69637a5f3a8187f3f56ddcea39b1cc9e7b6880f429b26c35a70d27d68464427a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24032089908289303,
+  "epoch": 0.24385502995175912,
   "eval_steps": 500,
-  "global_step": 13600,
+  "global_step": 13800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1912,6 +1912,34 @@
       "learning_rate": 4.220808544894073e-05,
       "loss": 0.3341,
       "step": 13600
+    },
+    {
+      "epoch": 0.24120443180010956,
+      "grad_norm": 1.6648529767990112,
+      "learning_rate": 4.2158999430602194e-05,
+      "loss": 0.4906,
+      "step": 13650
+    },
+    {
+      "epoch": 0.2420879645173261,
+      "grad_norm": 2.034646987915039,
+      "learning_rate": 4.210991341226365e-05,
+      "loss": 0.541,
+      "step": 13700
+    },
+    {
+      "epoch": 0.2429714972345426,
+      "grad_norm": 1.2273883819580078,
+      "learning_rate": 4.2060827393925116e-05,
+      "loss": 0.3936,
+      "step": 13750
+    },
+    {
+      "epoch": 0.24385502995175912,
+      "grad_norm": 1.6031947135925293,
+      "learning_rate": 4.201174137558658e-05,
+      "loss": 0.3871,
+      "step": 13800
     }
   ],
   "logging_steps": 50,