Training in progress, step 28000, checkpoint

last-checkpoint/README.md

@@ -1217,6 +1217,10 @@ You can finetune this model on your own dataset.
 | 0.4895 | 27700 | 0.3397        |
 | 0.4904 | 27750 | 0.3853        |
 | 0.4912 | 27800 | 0.2568        |
+| 0.4921 | 27850 | 0.3108        |
+| 0.4930 | 27900 | 0.4098        |
+| 0.4939 | 27950 | 0.3364        |
+| 0.4948 | 28000 | 0.3354        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdfacab69b0182b267f66ce210afc2a929861f8a381fcb609abe7250efbad353
+oid sha256:de68ecb62cb177a69e2ea7a2d8815c238cc32cec342188055a5fefa4de66dcc5
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d101e20d6391c1d00393694ed7c13a8ed5d54b7059e36795228521dd1687fa5d
+oid sha256:e99ec639b3e9bec0cbb3889051137c9795f5cf34c03f83c5e27e4203004378a8
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ca64734da2f01bf95a86973d81c98cfbac0699ced506e6f5d14bfc6d5da161
+oid sha256:9b2bb1065a03f3a3cc81b13be34dd1b158c384419d61db5c56d91448ea10ea2e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43246be50aae83c1910a5dc4ce6db1d2f843a5836c33c56704984643d301b0e
+oid sha256:b46b4db6042cc9cc0d2e82b27079ac2205bbc9a103068ad0178d3c56c11b3021
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ed64f7e529220ff21286b422216dac7ffe45f3b61319d3fedf56a8725ea92a
+oid sha256:2b4cd14cf09830d2d2a5966f0c329a3b566132e79593057303cd71a113d5be9d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4912441907723843,
+  "epoch": 0.49477832164125035,
   "eval_steps": 500,
-  "global_step": 27800,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3900,6 +3900,34 @@
       "learning_rate": 2.8274528283363765e-05,
       "loss": 0.2568,
       "step": 27800
+    },
+    {
+      "epoch": 0.4921277234896008,
+      "grad_norm": 1.727280855178833,
+      "learning_rate": 2.8225442265025233e-05,
+      "loss": 0.3108,
+      "step": 27850
+    },
+    {
+      "epoch": 0.49301125620681735,
+      "grad_norm": 1.4632737636566162,
+      "learning_rate": 2.8176356246686697e-05,
+      "loss": 0.4098,
+      "step": 27900
+    },
+    {
+      "epoch": 0.4938947889240339,
+      "grad_norm": 1.5443991422653198,
+      "learning_rate": 2.812727022834816e-05,
+      "loss": 0.3364,
+      "step": 27950
+    },
+    {
+      "epoch": 0.49477832164125035,
+      "grad_norm": 1.7304097414016724,
+      "learning_rate": 2.8078184210009623e-05,
+      "loss": 0.3354,
+      "step": 28000
     }
   ],
   "logging_steps": 50,