Training in progress, step 29600, checkpoint

last-checkpoint/README.md

@@ -1249,6 +1249,10 @@ You can finetune this model on your own dataset.
 | 0.5178 | 29300 | 0.3492        |
 | 0.5186 | 29350 | 0.3304        |
 | 0.5195 | 29400 | 0.3557        |
+| 0.5204 | 29450 | 0.3389        |
+| 0.5213 | 29500 | 0.3322        |
+| 0.5222 | 29550 | 0.3053        |
+| 0.5231 | 29600 | 0.2486        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52be879aebe70d6a3b2a056beedca08f2be73f61ebc46f06911a85e46d41c0c2
+oid sha256:144dc908d4b1ad90ee4a018b09fcaa7382467917152ff08210428196e07231f5
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06028c42fad3044c4b23353b232592f0571645864a036fae7f9a4aff967be12e
+oid sha256:61ca3e8ce7625e03c0718ab68f669eeba24f2a5b3e90913a5232a2578f9fb9e5
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83cd1380c57226aa3ea98011ce1f02c69976c7ca7a80455b341682a640b1d651
+oid sha256:029654d250d0a06a53ab2b4254f6c488ff21281306f583e5ec84fbf77c6593a0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77541b39dbb71635c2f0939f339b7fa24c5c0af9ad45520c78a03f92ccdb59e
+oid sha256:b527e96b4627964f9c26d5047552177b51a31ae414fb5194c8647b133292f2b4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f226454d5f7fa5a1b29f0c7888dfe13f17698107b349cee7ac0fbf136bdbea6
+oid sha256:786920dde07982614e5d3db4362f9f0f309e2cae4493573be6138429ecf70b07
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5195172377233129,
+  "epoch": 0.5230513685921789,
   "eval_steps": 500,
-  "global_step": 29400,
+  "global_step": 29600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4124,6 +4124,34 @@
       "learning_rate": 2.6703775696530603e-05,
       "loss": 0.3557,
       "step": 29400
+    },
+    {
+      "epoch": 0.5204007704405295,
+      "grad_norm": 1.787463665008545,
+      "learning_rate": 2.665468967819206e-05,
+      "loss": 0.3389,
+      "step": 29450
+    },
+    {
+      "epoch": 0.5212843031577459,
+      "grad_norm": 3.174107789993286,
+      "learning_rate": 2.660560365985353e-05,
+      "loss": 0.3322,
+      "step": 29500
+    },
+    {
+      "epoch": 0.5221678358749624,
+      "grad_norm": 1.648913025856018,
+      "learning_rate": 2.6556517641514994e-05,
+      "loss": 0.3053,
+      "step": 29550
+    },
+    {
+      "epoch": 0.5230513685921789,
+      "grad_norm": 1.648561954498291,
+      "learning_rate": 2.6507431623176455e-05,
+      "loss": 0.2486,
+      "step": 29600
     }
   ],
   "logging_steps": 50,