Training in progress, step 17000, checkpoint

last-checkpoint/README.md

@@ -1363,6 +1363,10 @@ You can finetune this model on your own dataset.
 | 0.2951 | 16700 | 0.3299        |
 | 0.2960 | 16750 | 0.3493        |
 | 0.2969 | 16800 | 0.2752        |
+| 0.2978 | 16850 | 0.3254        |
+| 0.2986 | 16900 | 0.3352        |
+| 0.2995 | 16950 | 0.3812        |
+| 0.3004 | 17000 | 0.3332        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e1b391f33422456061353bd355bf2435eeb4195f81389af6dbc0e8fc66d25b
+oid sha256:38ad97b260860972b9730f175955e3ce530db8323f7dc5bcf0e90933d6b8fb84
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9de93effda738b0b5fd57692fb67723566f34b54c872aac7a9626fa31feaf70
+oid sha256:7fd7069f1a068fd2c2876d55655006ec19b8c2319d576c34cff13d207d6cb5d3
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3be6ab84a32000b2bae6b4e86032ac0554f86e01256b1d6d073b96f56c8ada
+oid sha256:8bbc5938b66b6b7b1cb7ca970b428c630e6141cd051d14e46bf204d25c3e87c0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caeb14c75258126c0a61054123d2b052c3f92789f4356192be834a257bdfec4c
+oid sha256:fa14b4995859788df7ef8bb3ac5bf3bef25e341abeaa5e3ae0de74c72a4065ee
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba1c971d0e3bd3fc6e84348fd8cbae570fbf4f01d4c3efacd1f9719190d9e71
+oid sha256:16324e1fa03eb15f85ccd89e40ca9aaf90eafb16b60693a1698d40074577c527
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2968669929847502,
+  "epoch": 0.3004011238536163,
   "eval_steps": 500,
-  "global_step": 16800,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2360,6 +2360,34 @@
       "learning_rate": 3.906756199564116e-05,
       "loss": 0.2752,
       "step": 16800
+    },
+    {
+      "epoch": 0.29775052570196675,
+      "grad_norm": 1.8846018314361572,
+      "learning_rate": 3.901847597730263e-05,
+      "loss": 0.3254,
+      "step": 16850
+    },
+    {
+      "epoch": 0.2986340584191833,
+      "grad_norm": 2.9167964458465576,
+      "learning_rate": 3.896938995896409e-05,
+      "loss": 0.3352,
+      "step": 16900
+    },
+    {
+      "epoch": 0.2995175911363998,
+      "grad_norm": 2.6470940113067627,
+      "learning_rate": 3.892128566099233e-05,
+      "loss": 0.3812,
+      "step": 16950
+    },
+    {
+      "epoch": 0.3004011238536163,
+      "grad_norm": 2.1021623611450195,
+      "learning_rate": 3.887219964265379e-05,
+      "loss": 0.3332,
+      "step": 17000
     }
   ],
   "logging_steps": 50,