Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98391a0521380bb21ece1b25437e8f0e22a2ece11cb925bb17b44175d91f4ab7
+oid sha256:8aa3494fcf8494e09510fdd6776d0909cf904525f8cd5f22a4471c95b1e88171
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de929b6132054e5553c54ef80554fea2c34b632811ebc810f1505bf53b13cb5
+oid sha256:c507e6a606d3533b83e8f04601bd517d0a24ef5e596488e4b831b5b264ac9765
 size 2911851147

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeec3ade264ba5d51043534463b9800cb8cf1d9ed837a72e775aca4faec2a962
+oid sha256:56cef4697856a0a8e07cf1660ddc1fd6c48ca916f45029dbbb478d8779a73641
 size 1383

last-checkpoint/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0057,
+  "epoch": 0.05,
   "eval_steps": 500,
   "global_step": 500,
   "is_hyper_param_search": false,
@@ -11,72 +11,72 @@
   "log_history": [
     {
       "epoch": 0.005,
-      "grad_norm": 2.776340961456299,
-      "learning_rate": 1.05e-05,
-      "loss": 8.684551391601563,
+      "grad_norm": 2.8277900218963623,
+      "learning_rate": 1.125e-05,
+      "loss": 7.685114135742188,
       "step": 50
     },
     {
       "epoch": 0.01,
-      "grad_norm": 2.655430555343628,
-      "learning_rate": 2.075e-05,
-      "loss": 6.158372192382813,
+      "grad_norm": 2.2731411457061768,
+      "learning_rate": 2.2250000000000002e-05,
+      "loss": 5.033958129882812,
       "step": 100
     },
     {
       "epoch": 0.015,
-      "grad_norm": 3.5645532608032227,
-      "learning_rate": 3.2250000000000005e-05,
-      "loss": 5.6899951171875,
+      "grad_norm": 3.3346173763275146,
+      "learning_rate": 3.35e-05,
+      "loss": 4.662413940429688,
       "step": 150
     },
     {
       "epoch": 0.02,
-      "grad_norm": 2.648423910140991,
-      "learning_rate": 4.375e-05,
-      "loss": 5.743831787109375,
+      "grad_norm": 3.638383626937866,
+      "learning_rate": 4.4750000000000004e-05,
+      "loss": 5.785809936523438,
       "step": 200
     },
     {
       "epoch": 0.025,
-      "grad_norm": 2.697211980819702,
+      "grad_norm": 2.827432632446289,
       "learning_rate": 4.999919714835816e-05,
-      "loss": 6.030469970703125,
+      "loss": 7.300284423828125,
       "step": 250
     },
     {
       "epoch": 0.03,
-      "grad_norm": 2.61139178276062,
+      "grad_norm": 2.6586380004882812,
       "learning_rate": 4.999277464461405e-05,
-      "loss": 6.761121215820313,
+      "loss": 8.245166625976562,
       "step": 300
     },
     {
       "epoch": 0.035,
-      "grad_norm": 2.6408164501190186,
+      "grad_norm": 2.42388653755188,
       "learning_rate": 4.9979931287121e-05,
-      "loss": 7.452212524414063,
+      "loss": 9.312975463867188,
       "step": 350
     },
     {
       "epoch": 0.04,
-      "grad_norm": 2.8878214359283447,
+      "grad_norm": 2.5717973709106445,
       "learning_rate": 4.996067037544542e-05,
-      "loss": 8.262448120117188,
+      "loss": 10.216683959960937,
       "step": 400
     },
     {
-      "epoch": 1.0007,
-      "grad_norm": 2.6936967372894287,
+      "epoch": 0.045,
+      "grad_norm": 2.759148120880127,
       "learning_rate": 4.9934996857877325e-05,
-      "loss": 9.289183349609376,
+      "loss": 11.017779541015624,
       "step": 450
     },
     {
-      "epoch": 1.0057,
-      "grad_norm": 2.5427498817443848,
+      "epoch": 0.05,
+      "grad_norm": 2.2197604179382324,
       "learning_rate": 4.9902917330159036e-05,
-      "loss": 9.672667236328126,
+      "loss": 11.715665283203125,
       "step": 500
     }
   ],
@@ -97,7 +97,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.115595044944282e+16,
+  "total_flos": 4.072103585483981e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null