Training in progress, step 20800, checkpoint

last-checkpoint/README.md

@@ -1439,6 +1439,10 @@ You can finetune this model on your own dataset.
 | 0.3622 | 20500 | 0.3582        |
 | 0.3631 | 20550 | 0.4004        |
 | 0.3640 | 20600 | 0.33          |
+| 0.3649 | 20650 | 0.3072        |
+| 0.3658 | 20700 | 0.35          |
+| 0.3667 | 20750 | 0.3241        |
+| 0.3675 | 20800 | 0.37          |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97621d4e5f190418e5ade8172b856dbf29aec1661e21c76459517df300f5dd4b
+oid sha256:d579b6d5d93397921c89359b1645f6d237af8feaabf2808aa442f559f31fb4c0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be75d2187899c775b5671ab017796b70cd2d877b78c139a3ee2fbd3172e957b9
+oid sha256:674bd0a4229124de80961bd58f8a6981f214653c5975a0453bb6e383c35d6ff5
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6a169e48c0fa7774725b5e2e61834f9ebf4e77ad306763883a681dba8565aa
+oid sha256:78ea8f06d7607dd2ef63e1d5df423f0e12babf973592667a187334f294342238
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7b827b26a6c90ed6161d81717bb3711d81cb1be9e30f4a4b392ff6e398d8b0
+oid sha256:e95c7d02cae67a959a1e26802dda7eb773b84117a34d7a400f3d47ccf620db34
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82191afd9a6d7a471cf24d902e6f469df00ed0ce9e065a1aca219368120bb6fd
+oid sha256:4d533c21f945b003e7696031dabbdd090fa025b8305d207ee0a2aeeea78458b1
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3640154794932056,
+  "epoch": 0.36754961036207173,
   "eval_steps": 500,
-  "global_step": 20600,
+  "global_step": 20800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2892,6 +2892,34 @@
       "learning_rate": 3.533898804264593e-05,
       "loss": 0.33,
       "step": 20600
+    },
+    {
+      "epoch": 0.36489901221042215,
+      "grad_norm": 1.5064153671264648,
+      "learning_rate": 3.52899020243074e-05,
+      "loss": 0.3072,
+      "step": 20650
+    },
+    {
+      "epoch": 0.3657825449276387,
+      "grad_norm": 3.5023598670959473,
+      "learning_rate": 3.5240816005968865e-05,
+      "loss": 0.35,
+      "step": 20700
+    },
+    {
+      "epoch": 0.3666660776448552,
+      "grad_norm": 1.7911083698272705,
+      "learning_rate": 3.519172998763032e-05,
+      "loss": 0.3241,
+      "step": 20750
+    },
+    {
+      "epoch": 0.36754961036207173,
+      "grad_norm": 1.50026273727417,
+      "learning_rate": 3.514264396929179e-05,
+      "loss": 0.37,
+      "step": 20800
     }
   ],
   "logging_steps": 50,