Training in progress, step 52800, checkpoint

last-checkpoint/README.md

@@ -1209,6 +1209,10 @@ You can finetune this model on your own dataset.
 | 0.9277 | 52500 | 0.2997        |
 | 0.9286 | 52550 | 0.2425        |
 | 0.9295 | 52600 | 0.2708        |
+| 0.9304 | 52650 | 0.2201        |
+| 0.9312 | 52700 | 0.2958        |
+| 0.9321 | 52750 | 0.2647        |
+| 0.9330 | 52800 | 0.2329        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d488dc3a5445f93dc6d891e374112fcf40bd92f3df49a02fa164a7b7e3f0939
+oid sha256:a329281b62dee04f25df2a1445a6d06e38a118403d00dfd2047a9f0451d6a236
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ade7229380655a5e5d3053eb6b8da0b8461494cbbd9ca16bd058175900faab5
+oid sha256:b1a7c65d7edd786206cd29e1711b41b5ec57296920cd7f0363e9e1febcd4786d
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8bc5e9aadcf53514c913a3f624aee68ac8959f84c12938e1ebd53df4add3fd5
+oid sha256:a39806bf7f5ccc564dfbcbf96185e5776a4d453cf6ceeebfa61e6b15fd77f05f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16fabdbfb525bb124af89aae1d7ac043f5eac6bfe2d8462a555cfc01bdf7a82a
+oid sha256:15f8eff2e31e5d461c8d76e9f3c73436b8f99cd51de4fc3b3a328f9ccbf1dbdd
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c8184ff5d3c53c23e51683855f8ef56aed39b4067ed958d2a6305ca37d4bf3
+oid sha256:7d76c0e19f4170b3811b1d648f816f3a3f40e357234c62ca57c1c93ddc1c338c
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9294764185117775,
+  "epoch": 0.9330105493806435,
   "eval_steps": 500,
-  "global_step": 52600,
+  "global_step": 52800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7372,6 +7372,34 @@
       "learning_rate": 3.938662111484165e-06,
       "loss": 0.2708,
       "step": 52600
+    },
+    {
+      "epoch": 0.9303599512289941,
+      "grad_norm": 2.747580051422119,
+      "learning_rate": 3.889576093145628e-06,
+      "loss": 0.2201,
+      "step": 52650
+    },
+    {
+      "epoch": 0.9312434839462105,
+      "grad_norm": 2.005228281021118,
+      "learning_rate": 3.840490074807092e-06,
+      "loss": 0.2958,
+      "step": 52700
+    },
+    {
+      "epoch": 0.932127016663427,
+      "grad_norm": 1.6022164821624756,
+      "learning_rate": 3.791404056468556e-06,
+      "loss": 0.2647,
+      "step": 52750
+    },
+    {
+      "epoch": 0.9330105493806435,
+      "grad_norm": 1.7913720607757568,
+      "learning_rate": 3.7423180381300193e-06,
+      "loss": 0.2329,
+      "step": 52800
     }
   ],
   "logging_steps": 50,