Training in progress, step 15400, checkpoint

last-checkpoint/README.md

@@ -1331,6 +1331,10 @@ You can finetune this model on your own dataset.
 | 0.2668 | 15100 | 0.352         |
 | 0.2677 | 15150 | 0.3638        |
 | 0.2686 | 15200 | 0.3727        |
+| 0.2695 | 15250 | 0.3842        |
+| 0.2704 | 15300 | 0.3625        |
+| 0.2712 | 15350 | 0.4088        |
+| 0.2721 | 15400 | 0.4126        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585fb1254320abf5fa3fead82b5bb8bfb1adda02efcaf21fd3bca945c95bb8cd
+oid sha256:04b7cbbd38574c6f644e5905e423ba3800976ac9f64a45f988dc986784e2d3c3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:533d32af8daf9f72c2f5acae406ece041eab382d9e444ec8876783f13534e8d9
+oid sha256:59832a48408250a010ff3eb06e85c9c23c780a3bb973e06cb22542561bf9a69f
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91bcb70f5dde9b132a8f4813819563f3e4a3ffe0599080085097bf651c34654e
+oid sha256:6316675c87304b6a869a973492a1f7d1ddc0dc21462eba7caa9df8741680bf41
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30577b072974c10d385ba88013a64c7f41f9003dbd098b2eb085609eff3dcb24
+oid sha256:8e2c8f643d81596fc9fb1ef1c4a6a6344df33962576f180d2561ffde1db918fd
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df63d8b4b8f4f625d8a4112d79b9bbc2733e8272c655434f7bca9c2ec612884
+oid sha256:0e73f97c88ee773669644b85dc0a5424564108e9b40aaaed168c2d9eee5ed22d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26859394603382164,
+  "epoch": 0.2721280769026877,
   "eval_steps": 500,
-  "global_step": 15200,
+  "global_step": 15400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2136,6 +2136,34 @@
       "learning_rate": 4.063831458247433e-05,
       "loss": 0.3727,
       "step": 15200
+    },
+    {
+      "epoch": 0.26947747875103817,
+      "grad_norm": 1.9209206104278564,
+      "learning_rate": 4.058922856413579e-05,
+      "loss": 0.3842,
+      "step": 15250
+    },
+    {
+      "epoch": 0.2703610114682547,
+      "grad_norm": 1.946022868156433,
+      "learning_rate": 4.054014254579726e-05,
+      "loss": 0.3625,
+      "step": 15300
+    },
+    {
+      "epoch": 0.27124454418547117,
+      "grad_norm": 1.4893426895141602,
+      "learning_rate": 4.049105652745872e-05,
+      "loss": 0.4088,
+      "step": 15350
+    },
+    {
+      "epoch": 0.2721280769026877,
+      "grad_norm": 1.7391968965530396,
+      "learning_rate": 4.0441970509120186e-05,
+      "loss": 0.4126,
+      "step": 15400
     }
   ],
   "logging_steps": 50,