Training in progress, step 90000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6549b8831a8d21c4b3c2b386a28446b2ce37cc6f787852240e01e32f6d8203df
+oid sha256:d002168cc69538373ab33244390da8c4a63690ab3ac7af2902d3df798e6bc748
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110afaa541a1db9aea3f110c7199f3cd8cb3fe67d765a912077dadceeb250867
+oid sha256:3a1b08538448c3955f9816afd9712587d226efc04ddd65ee0378bda9ad13a5ad
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3fa98632bcdd5161ea2f7fcf185a8dcabb5bcd97be6aef44120bf311d2da5b
+oid sha256:cfd06f2b98bc509f92f4e1415fd68ebc1b6603ab44f533199dd7ae056dc6b235
 size 15459

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b041d6180b48892d2b556bf262a3bda69776696494ed31b919625259633eaea
+oid sha256:1541b5ef2368a76e7bbd5980ca4a3faf491d955c90d4e8794732bf908704ed18
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8245462872e2df4ffab61c8b67deac00bb1e635e0f54dc0d80e699e895d54d0b
+oid sha256:f61de41cc564c25462ca0290993ffba1d92f72b28f091680e90a006d4be7a958
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.658570558022112,
-  "global_step": 85000,
+  "epoch": 7.0938452163315056,
+  "global_step": 90000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1162,11 +1162,79 @@
       "eval_samples_per_second": 64.674,
       "eval_steps_per_second": 1.022,
       "step": 85000
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 1.4647430616375366e-05,
+      "loss": 0.4042,
+      "step": 85500
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 1.433819250148215e-05,
+      "loss": 0.4049,
+      "step": 86000
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 1.4039083460027203e-05,
+      "loss": 0.4041,
+      "step": 86500
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 1.3750177292690856e-05,
+      "loss": 0.4038,
+      "step": 87000
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 1.347154528274688e-05,
+      "loss": 0.4047,
+      "step": 87500
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 1.3203782390038048e-05,
+      "loss": 0.4036,
+      "step": 88000
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 1.2945881505195709e-05,
+      "loss": 0.4044,
+      "step": 88500
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 1.2698453225696373e-05,
+      "loss": 0.4045,
+      "step": 89000
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 1.2461558600765676e-05,
+      "loss": 0.4031,
+      "step": 89500
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 1.2235256080607583e-05,
+      "loss": 0.4026,
+      "step": 90000
+    },
+    {
+      "epoch": 7.09,
+      "eval_loss": 0.3881285488605499,
+      "eval_runtime": 133.2371,
+      "eval_samples_per_second": 37.527,
+      "eval_steps_per_second": 0.593,
+      "step": 90000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.0033602388690993e+21,
+  "total_flos": 4.2388489249674913e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110afaa541a1db9aea3f110c7199f3cd8cb3fe67d765a912077dadceeb250867
+oid sha256:3a1b08538448c3955f9816afd9712587d226efc04ddd65ee0378bda9ad13a5ad
 size 449471589