Training in progress, step 26800, checkpoint

last-checkpoint/README.md

@@ -1193,6 +1193,10 @@ You can finetune this model on your own dataset.
 | 0.4683 | 26500 | 0.3204        |
 | 0.4692 | 26550 | 0.2698        |
 | 0.4700 | 26600 | 0.3019        |
+| 0.4709 | 26650 | 0.276         |
+| 0.4718 | 26700 | 0.2572        |
+| 0.4727 | 26750 | 0.2821        |
+| 0.4736 | 26800 | 0.2753        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efcfe5aa0c5005b2003bf869f963a20c876745fa7f627f40c3819a73de45b137
+oid sha256:6af9e8fc53f229d8df337a8754e2d3d5b113d4716605b013bad83e9e09dacdb0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e583966410e9fff5f8ac46b24676c49f860c538a27398df242344bd0d2a7d08c
+oid sha256:de6d4daedba612d713f9144d945bcc7668fddc99a7c572a8a7ecdaadfce55d9f
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bea9f5fcadeb0cd0d9a943463b72fc5766ebc9e57169008c5a18a91f57902fe
+oid sha256:bd90d4d272f52093bcd166fb2fee1129e8da49cd6cade68a0c1872a9ab44bae6
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc231b83c50d1c7b06b068e6375671742fac1a054d31705297b772d1dffbf9a2
+oid sha256:9102615210716abefe38c971af7617c4ceba795e3412ef59968e79b6fe53891e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93fabb93104e1056a717edb04db9d7d8955bbdc038b375db1506268b873e6fee
+oid sha256:4ca320c82587b083501742caf7cc80ec1a98ca247bf4b8c7cd91053ff97a2d44
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4700394055591879,
+  "epoch": 0.47357353642805394,
   "eval_steps": 500,
-  "global_step": 26600,
+  "global_step": 26800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3732,6 +3732,34 @@
       "learning_rate": 2.9452592723488643e-05,
       "loss": 0.3019,
       "step": 26600
+    },
+    {
+      "epoch": 0.47092293827640436,
+      "grad_norm": 1.6362017393112183,
+      "learning_rate": 2.9403506705150108e-05,
+      "loss": 0.276,
+      "step": 26650
+    },
+    {
+      "epoch": 0.4718064709936209,
+      "grad_norm": 1.5143210887908936,
+      "learning_rate": 2.935442068681157e-05,
+      "loss": 0.2572,
+      "step": 26700
+    },
+    {
+      "epoch": 0.4726900037108374,
+      "grad_norm": 2.1000730991363525,
+      "learning_rate": 2.9305334668473034e-05,
+      "loss": 0.2821,
+      "step": 26750
+    },
+    {
+      "epoch": 0.47357353642805394,
+      "grad_norm": 1.9400396347045898,
+      "learning_rate": 2.9256248650134498e-05,
+      "loss": 0.2753,
+      "step": 26800
     }
   ],
   "logging_steps": 50,