Training in progress, step 95000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d002168cc69538373ab33244390da8c4a63690ab3ac7af2902d3df798e6bc748
+oid sha256:cb0a61ab643c18ccf5b4cde2db1687dfb3353ac9730e884873954f6a4914ee49
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1b08538448c3955f9816afd9712587d226efc04ddd65ee0378bda9ad13a5ad
+oid sha256:e8beb25b1f0bcf41b4de421e9957ad88915f0b34dec0216d6304d37fb6ed0fc2
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd06f2b98bc509f92f4e1415fd68ebc1b6603ab44f533199dd7ae056dc6b235
+oid sha256:bc2ae884d96e2e98bf3a22796a951063fc339dc13602ff01679fb67e0849a907
 size 15459

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1541b5ef2368a76e7bbd5980ca4a3faf491d955c90d4e8794732bf908704ed18
+oid sha256:bb8cb9021f3a60f9e715cf2cfd338061faee5a6bd0df4d32e00e1489dc2742d6
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61de41cc564c25462ca0290993ffba1d92f72b28f091680e90a006d4be7a958
+oid sha256:1fa03e39186130ec116897cef176842ce103a90b1b243dfa00171a77a06fae55
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0938452163315056,
-  "global_step": 90000,
+  "epoch": 7.529119874640898,
+  "global_step": 95000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1230,11 +1230,79 @@
       "eval_samples_per_second": 37.527,
       "eval_steps_per_second": 0.593,
       "step": 90000
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 1.20196015019827e-05,
+      "loss": 0.4036,
+      "step": 90500
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 1.1815047267485115e-05,
+      "loss": 0.4037,
+      "step": 91000
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 1.162082400805151e-05,
+      "loss": 0.4048,
+      "step": 91500
+    },
+    {
+      "epoch": 7.27,
+      "learning_rate": 1.1437400292071077e-05,
+      "loss": 0.4032,
+      "step": 92000
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 1.126482137660111e-05,
+      "loss": 0.4032,
+      "step": 92500
+    },
+    {
+      "epoch": 7.36,
+      "learning_rate": 1.1103129842906643e-05,
+      "loss": 0.4029,
+      "step": 93000
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 1.0952365585954172e-05,
+      "loss": 0.4023,
+      "step": 93500
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 1.0812565804568168e-05,
+      "loss": 0.4027,
+      "step": 94000
+    },
+    {
+      "epoch": 7.49,
+      "learning_rate": 1.0683764992252818e-05,
+      "loss": 0.4022,
+      "step": 94500
+    },
+    {
+      "epoch": 7.53,
+      "learning_rate": 1.0566219440353348e-05,
+      "loss": 0.4027,
+      "step": 95000
+    },
+    {
+      "epoch": 7.53,
+      "eval_loss": 0.38710081577301025,
+      "eval_runtime": 65.4468,
+      "eval_samples_per_second": 76.398,
+      "eval_steps_per_second": 1.207,
+      "step": 95000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.2388489249674913e+21,
+  "total_flos": 4.474341992332253e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1b08538448c3955f9816afd9712587d226efc04ddd65ee0378bda9ad13a5ad
+oid sha256:e8beb25b1f0bcf41b4de421e9957ad88915f0b34dec0216d6304d37fb6ed0fc2
 size 449471589