Training in progress, step 14800, checkpoint

last-checkpoint/README.md

@@ -1319,6 +1319,10 @@ You can finetune this model on your own dataset.
 | 0.2562 | 14500 | 0.3406        |
 | 0.2571 | 14550 | 0.4397        |
 | 0.2580 | 14600 | 0.411         |
+| 0.2589 | 14650 | 0.3742        |
+| 0.2598 | 14700 | 0.3622        |
+| 0.2606 | 14750 | 0.2782        |
+| 0.2615 | 14800 | 0.36          |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861228ee1e7303d55d206ed18a0e9a9f72cd4fceb74ae8597ddd8227ba4baaa6
+oid sha256:f8e3fa7de06aa25ef9e92bb424c00fdc808b42dd23a9e9bb43d0a3c2c3136371
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e800f5f76e35b4a2c15cb36bcf0bae4a36cc21e80874b3eade1a26b448ee14
+oid sha256:092bf8b9d76f58d80effc72b6148feaeea3102b809911377eb0d572cb5bf7575
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ffe6d2e694b6c2093052ae77ba6c6348d6c889151265b032757dc965de9eabd
+oid sha256:97edb58b8967751d3dda12e8eb802aa7613cd23fb975e45f9749685794078420
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2d1981a845c6e1942265cf518562623d63fa9e701ce29d4ce24d1e25e2691cb
+oid sha256:f13f9cc3a0ef2dfdf6369b4685eb176c05f57535fd4a80cceb72b81393a5eb1b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ef9de9a97c35ae1f236f3cf953b678aeb5931825d667a15b405ae0448fa416
+oid sha256:29d3d14fe806d58e2a7b675de49d429f0f4e1b8b1cfd250c3c74b902fbff4430
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2579915534272234,
+  "epoch": 0.26152568429608947,
   "eval_steps": 500,
-  "global_step": 14600,
+  "global_step": 14800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2052,6 +2052,34 @@
       "learning_rate": 4.122636508217e-05,
       "loss": 0.411,
       "step": 14600
+    },
+    {
+      "epoch": 0.25887508614443994,
+      "grad_norm": 1.5897334814071655,
+      "learning_rate": 4.117727906383146e-05,
+      "loss": 0.3742,
+      "step": 14650
+    },
+    {
+      "epoch": 0.25975861886165647,
+      "grad_norm": 3.667428970336914,
+      "learning_rate": 4.1128193045492924e-05,
+      "loss": 0.3622,
+      "step": 14700
+    },
+    {
+      "epoch": 0.26064215157887294,
+      "grad_norm": 1.7393996715545654,
+      "learning_rate": 4.107910702715439e-05,
+      "loss": 0.2782,
+      "step": 14750
+    },
+    {
+      "epoch": 0.26152568429608947,
+      "grad_norm": 1.6495802402496338,
+      "learning_rate": 4.103002100881585e-05,
+      "loss": 0.36,
+      "step": 14800
     }
   ],
   "logging_steps": 50,