Training in progress, step 9600, checkpoint

last-checkpoint/README.md

@@ -1213,6 +1213,10 @@ You can finetune this model on your own dataset.
 | 0.1643 | 9300 | 0.4204        |
 | 0.1652 | 9350 | 0.5576        |
 | 0.1661 | 9400 | 0.4712        |
+| 0.1670 | 9450 | 0.366         |
+| 0.1679 | 9500 | 0.3932        |
+| 0.1688 | 9550 | 0.4836        |
+| 0.1696 | 9600 | 0.3989        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e974a383273411df15409a82c6a1b9f0831a59d058b967a3d435ccbc1f48583
+oid sha256:5d75f2ae04decbc38e9837063052796e9f2bb5b93ba4b3967ba78efa578f524f
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b870ccf7b86ba6d235904225aaace7fb586b191e7940b6dc707df695b5dd9282
+oid sha256:6d7bd92a04e9045a8d7bd34505c04408ff4f945e28a7e521fda8627bb4a5ffb8
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7adf907e945b62166980022a68a400535d3ff6272023bde8d2c138ada9021e2
+oid sha256:4991e7b45094aac9ff0a60591e26561675ae2318a690a5d07c69cdb47d8654a9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e1fb2bcfe11259f3983e51e8c93f656c6150bd91d84aeb3343965e94c4460e
+oid sha256:498b0c6fbe9530a64ad6460f8bb9ba5c88d4dacacfc84f82ced2672249165959
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d745bf9d75c40b1bcb1a39a8a08fa030d79ce77aa08ff337210102fd029a211
+oid sha256:b09b7aeb1f1c748a56856918139834bbfcfbfa3a7f47fdb7435e88f5b14f5a1d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1661041508367055,
+  "epoch": 0.16963828170557155,
   "eval_steps": 500,
-  "global_step": 9400,
+  "global_step": 9600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1324,6 +1324,34 @@
       "learning_rate": 4.6329347548644245e-05,
       "loss": 0.4712,
       "step": 9400
+    },
+    {
+      "epoch": 0.166987683553922,
+      "grad_norm": 1.8109374046325684,
+      "learning_rate": 4.628026153030571e-05,
+      "loss": 0.366,
+      "step": 9450
+    },
+    {
+      "epoch": 0.16787121627113852,
+      "grad_norm": 1.9352269172668457,
+      "learning_rate": 4.6231175511967175e-05,
+      "loss": 0.3932,
+      "step": 9500
+    },
+    {
+      "epoch": 0.16875474898835505,
+      "grad_norm": 1.7740451097488403,
+      "learning_rate": 4.618208949362864e-05,
+      "loss": 0.4836,
+      "step": 9550
+    },
+    {
+      "epoch": 0.16963828170557155,
+      "grad_norm": 2.0106916427612305,
+      "learning_rate": 4.61330034752901e-05,
+      "loss": 0.3989,
+      "step": 9600
     }
   ],
   "logging_steps": 50,