Training in progress, step 36200, checkpoint

last-checkpoint/README.md

@@ -1237,6 +1237,10 @@ You can finetune this model on your own dataset.
 | 0.6344 | 35900 | 0.3392        |
 | 0.6353 | 35950 | 0.2856        |
 | 0.6361 | 36000 | 0.286         |
+| 0.6370 | 36050 | 0.3555        |
+| 0.6379 | 36100 | 0.3065        |
+| 0.6388 | 36150 | 0.3696        |
+| 0.6397 | 36200 | 0.2626        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b384b5f887acee5a6096737f368c3613e7537b072283344d0460f9ee33683f
+oid sha256:0c9d5f4c75c0e59ead8c90d7f477a6c4f2a76d4f920d64487f7b3f0f977bf04b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f7c656111e857b9a5964461ddb67ba8434de7b657a0de6cf811249e9f135c7
+oid sha256:af000b0347dc95901909529dc9cfdc24424b2749e401e23c461b99b8dd8404e4
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83863be742a336d65a58bf9026fc223fa44e5cc37215b2331b9a723f209bc947
+oid sha256:e6e48436107029949f024f9a54ee806776f3466bbed0983b649683798572c860
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b02513987752f55c2a09cb46fb561fd6490aaf9c1a9fb121a08671c8653dcd
+oid sha256:6de71f94cd2950bde11e0c308e88441a6d73f11c2bf00a620f09d97b4f7e685a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e587de7316b1032258fa34321e4e4cbe60d0a5d83b11f22c68cdcdf7469e3a42
+oid sha256:607bd3d0f644e74e9c8b0820519aa8b98e93f1767aaaa77fb01d3c971b1c38de
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6361435563958934,
+  "epoch": 0.6396776872647594,
   "eval_steps": 500,
-  "global_step": 36000,
+  "global_step": 36200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5048,6 +5048,34 @@
       "learning_rate": 2.02273664369441e-05,
       "loss": 0.286,
       "step": 36000
+    },
+    {
+      "epoch": 0.6370270891131099,
+      "grad_norm": 1.3550012111663818,
+      "learning_rate": 2.0178280418605568e-05,
+      "loss": 0.3555,
+      "step": 36050
+    },
+    {
+      "epoch": 0.6379106218303264,
+      "grad_norm": 1.9244177341461182,
+      "learning_rate": 2.012919440026703e-05,
+      "loss": 0.3065,
+      "step": 36100
+    },
+    {
+      "epoch": 0.6387941545475428,
+      "grad_norm": 2.1921980381011963,
+      "learning_rate": 2.008010838192849e-05,
+      "loss": 0.3696,
+      "step": 36150
+    },
+    {
+      "epoch": 0.6396776872647594,
+      "grad_norm": 1.6438093185424805,
+      "learning_rate": 2.0031022363589955e-05,
+      "loss": 0.2626,
+      "step": 36200
     }
   ],
   "logging_steps": 50,