Training in progress, step 580000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a767a78fa4809e168b3ccdaca8245fdd800f92f9fb131a29e7c678020a7b2e1
+oid sha256:6b3c98677de897190cfb61fcdb47a41a233aacb3947cfaaf5565a6afc239a9e0
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f451f7904b0f8403b186893bae5bf08f2c2acf369a21d50224d0be67c5692d4
+oid sha256:a4bdcb08582dcc416cc4a3a9ae8bcb9040fe1e5dce27da0219c313edd1229bf9
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28edfca80c69ce874f473f07c4b7e161b12e6d09912377717af008dd4d50a13b
+oid sha256:0acf92adb8fe29e7f8f300892a64ae6b1061f78cbc741a04875cceecbd7627bb
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b65d15b0a371107c6c614a483d347936ef1bc44210919862c9b83a7094116f
-size 14503
+oid sha256:989d83467172119d42cc5db629615122c0d05d39b97d6151f3073b83b05e95f1
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916d53efc24960a2419b0c56ff522c7980d4be4e94feb1e3f3194d2ea4a6489c
+oid sha256:dbb6b551f6971cdac4e633aeb80c6604a5c29c6604766e95edb5b993ce689e66
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaddfaade81997be2461768daaef367db08e33d6fa1ca3618aadc35b99ca7474
+oid sha256:7228d0f23743ac31eeebdd713de3352c2963513ff68c7b3a41fefd85d589e485
 size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e62e41706c3cdebd0963ceae6fb24ae079cf26e6452a67e31e4c02f3a80456e6
+oid sha256:fe2528712b13528834db613d1453dd7fb04ea3b7a1940fa3521b7d0be4a96c0a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.704017591277658,
-  "global_step": 570000,
+  "epoch": 8.856719654282529,
+  "global_step": 580000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4224,11 +4224,85 @@
       "eval_samples_per_second": 954.187,
       "eval_steps_per_second": 15.267,
       "step": 570000
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 6.939267446224418e-05,
+      "loss": 0.2569,
+      "step": 571000
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 6.91639202643299e-05,
+      "loss": 0.2569,
+      "step": 572000
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 6.893528456804756e-05,
+      "loss": 0.2569,
+      "step": 573000
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 6.870676987372044e-05,
+      "loss": 0.2568,
+      "step": 574000
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 6.847837868034861e-05,
+      "loss": 0.257,
+      "step": 575000
+    },
+    {
+      "epoch": 8.78,
+      "eval_runtime": 1.0002,
+      "eval_samples_per_second": 999.79,
+      "eval_steps_per_second": 15.997,
+      "step": 575000
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 6.825011348558167e-05,
+      "loss": 0.2573,
+      "step": 576000
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 6.802197678569109e-05,
+      "loss": 0.2566,
+      "step": 577000
+    },
+    {
+      "epoch": 8.83,
+      "learning_rate": 6.779397107554339e-05,
+      "loss": 0.2562,
+      "step": 578000
+    },
+    {
+      "epoch": 8.84,
+      "learning_rate": 6.756609884857239e-05,
+      "loss": 0.2566,
+      "step": 579000
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 6.733836259675233e-05,
+      "loss": 0.2564,
+      "step": 580000
+    },
+    {
+      "epoch": 8.86,
+      "eval_runtime": 1.0727,
+      "eval_samples_per_second": 932.263,
+      "eval_steps_per_second": 14.916,
+      "step": 580000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.995709622184597e+22,
+  "total_flos": 4.065809883214944e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f451f7904b0f8403b186893bae5bf08f2c2acf369a21d50224d0be67c5692d4
+oid sha256:a4bdcb08582dcc416cc4a3a9ae8bcb9040fe1e5dce27da0219c313edd1229bf9
 size 449471589