Training in progress, step 450000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92e6cd0767ca59f1527b5967666a322afaf575c9af8775949662404da371092
+oid sha256:30290edc8628fd3c3ef18b3c5aeed7f069b37f58cee15ba21ffc0026c01c3730
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605e171de557600b4f9eab4567771d6f7b62053eb613a7b7ed22d56f357a201b
+oid sha256:cd9bd4abec55ec3aff5c6a63e004f193b84327f4dea19bd4c7a418c248e58ed7
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e4d0603158355ab30ed464162b9809f49d4b9fe387e337de95c9b6476ba9b3
+oid sha256:33d4cd7454368d736d737996ed03879986986a143829539c951d1987c1b5985b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926ff1f312d9731049e2cfd0827e2934c1dc272e72548666a5980946912e0647
-size 14439
+oid sha256:7336b286bfd4476ee4aa817ed5f237f90f8c52aba8afeb7d24431d41ce3a20dc
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69b501354d86430b18ce3c64120582562e9c52da9971d6a0efada8760b427f4
-size 14439
+oid sha256:1d3e44169554700b12ce1323e27998dd02eb610802144e6e40dc2e6668fa701b
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89dedfbbaf4906adbb87599ce42dab2b3412c2f3eed1c918df1f52570f878203
+oid sha256:b37e67e1cf58930910192e85abdd9cbaabe8e6e23dc6148e7d6f7fcf570a387a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa5fdd1e270251efa6239627ae6af3a9eb85be35af9f4cca7399ee33001083c
+oid sha256:6ca5b8ec583e6ebb62b2f3066d6bca2c46b8614e9cfbd4e5e7bfdb3a9d7a2d86
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.7188907722143325,
-  "global_step": 440000,
+  "epoch": 6.871592835219204,
+  "global_step": 450000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3262,11 +3262,85 @@
       "eval_samples_per_second": 976.131,
       "eval_steps_per_second": 15.618,
       "step": 440000
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 9.919569703270376e-05,
+      "loss": 0.2716,
+      "step": 441000
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 9.89729805310111e-05,
+      "loss": 0.2711,
+      "step": 442000
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 9.875005654384307e-05,
+      "loss": 0.2712,
+      "step": 443000
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 9.852692750906071e-05,
+      "loss": 0.2717,
+      "step": 444000
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 9.830359586676737e-05,
+      "loss": 0.2722,
+      "step": 445000
+    },
+    {
+      "epoch": 6.8,
+      "eval_runtime": 1.1145,
+      "eval_samples_per_second": 897.295,
+      "eval_steps_per_second": 14.357,
+      "step": 445000
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 9.808006405928215e-05,
+      "loss": 0.2703,
+      "step": 446000
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 9.785633453111306e-05,
+      "loss": 0.2705,
+      "step": 447000
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 9.763240972893037e-05,
+      "loss": 0.27,
+      "step": 448000
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 9.740829210153984e-05,
+      "loss": 0.2703,
+      "step": 449000
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 9.718398409985593e-05,
+      "loss": 0.27,
+      "step": 450000
+    },
+    {
+      "epoch": 6.87,
+      "eval_runtime": 0.9938,
+      "eval_samples_per_second": 1006.215,
+      "eval_steps_per_second": 16.099,
+      "step": 450000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.084407542926382e+22,
+  "total_flos": 3.154507803956729e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605e171de557600b4f9eab4567771d6f7b62053eb613a7b7ed22d56f357a201b
+oid sha256:cd9bd4abec55ec3aff5c6a63e004f193b84327f4dea19bd4c7a418c248e58ed7
 size 449471589