Training in progress, step 25000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98bc95b3264bd457f2f822f8bff3c25921dcd820b2ab11607b18dca44e5ccdc8
+oid sha256:78c410b30ed46201dc76b3758a8f05ba2befb17e53aabac920b8594900bf6e8f
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b4f4d147bd2f30b9ef842bfdf3fee1e6165115164d8a1391c9c747271d8965
+oid sha256:793325251fa149e905afc5251e0311b4cc842e9f6cbb39aa46ab80628503d14f
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21343af8626647d218ed09443d9afdff2e884071902e842787b88cc7208f1f68
+oid sha256:138259c5b6d4472016db54172bb7e725edf4c52d33cd44c90cb79184c02490ab
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd5a73d368b8347a9555d7b94e42b0bfbb251b0b8d4142bfa4cf49d9c2e9ffd
+oid sha256:9d302e2bbe5f8cc1de61c1cfd61605591d0eb14f9a715e2ddd90f5a8190314e3
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6464ca3b88e496d5d945a7955ac6cabd3c94f9611fe337e2e8a9af945aa679a
+oid sha256:afdbfcefcd9e1661e5368ed0a7d4915dce2e8bd6a92fd4d33ed45da578d95703
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7412502176562772,
-  "global_step": 20000,
+  "epoch": 2.1765627720703464,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -278,11 +278,79 @@
       "eval_samples_per_second": 268.894,
       "eval_steps_per_second": 4.249,
       "step": 20000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 9.169480392040811e-05,
+      "loss": 0.4408,
+      "step": 20500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.126237198035999e-05,
+      "loss": 0.441,
+      "step": 21000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.082108922350493e-05,
+      "loss": 0.4382,
+      "step": 21500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.037106452976014e-05,
+      "loss": 0.439,
+      "step": 22000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 8.991240893598493e-05,
+      "loss": 0.4387,
+      "step": 22500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.944617837966915e-05,
+      "loss": 0.4385,
+      "step": 23000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 8.897157870163552e-05,
+      "loss": 0.4385,
+      "step": 23500
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 8.848872653432954e-05,
+      "loss": 0.4373,
+      "step": 24000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 8.799674851241666e-05,
+      "loss": 0.4363,
+      "step": 24500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 8.749672541742298e-05,
+      "loss": 0.4355,
+      "step": 25000
+    },
+    {
+      "epoch": 2.18,
+      "eval_loss": 0.41616591811180115,
+      "eval_runtime": 16.3301,
+      "eval_samples_per_second": 306.184,
+      "eval_steps_per_second": 4.838,
+      "step": 25000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 9.419536490769757e+20,
+  "total_flos": 1.1774280960596666e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b4f4d147bd2f30b9ef842bfdf3fee1e6165115164d8a1391c9c747271d8965
+oid sha256:793325251fa149e905afc5251e0311b4cc842e9f6cbb39aa46ab80628503d14f
 size 449471589