Training in progress, step 240000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc34397f53638aed3e1f7a8fec48fd945fe9d9a65862e2d30b0c18c847384362
+oid sha256:21c21b20fb8c80d8819d148082ca4735a2ddcf51c6d5bd15312d293ac83a63c8
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6f4b993c3e5de4e91e3f11164ead7579089c5cd884e3548feacf51898e103a
+oid sha256:398ac2faeaf62d164de8b0d15d7dce648669506924aad7a65bb21212c9dd95dd
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d51ee7e5bc13fe73a3bcf57ad347fa22b3599a7d682e2e8a541926fd4330c8
+oid sha256:675c1da6a29e5de200fb272be2a868637018c999addc56c161958a25c0a5349b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d56ac9935105b68f299f8fa21719a2673f088d35488fddd5fa62d8866469f5f5
+oid sha256:3612d2c4e947f05578cbcbc2e6074dbe6180f6b3ff976664366be3670d8b1d56
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2738bd73d910d7af8da2f55f99c628d098f5213ea57df8ec541f1d8d067bf6de
-size 14503
+oid sha256:d433144714402feaf6a20e1bebd60563ad86ca2c8b3c2397a63d836b6b3aee95
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2c56ac3ff977fd6146b9151ff886620564565fb7b6256b4c917e31e654c4ed6
+oid sha256:24627e975d8a309c60a5796ee3829db81bd4fe576d49e1ab91aa7f4b4645e7d4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77be04c57a43b741a7c74fdd71f54e13c7f455ba94a43817c822b41fc4e2570c
+oid sha256:a59cfcefded7a2b207187159c019180f873df3dbebd125628eee7537065bae35
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5121474491120375,
-  "global_step": 230000,
+  "epoch": 3.6648495121169087,
+  "global_step": 240000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1708,11 +1708,85 @@
       "eval_samples_per_second": 978.715,
       "eval_steps_per_second": 15.659,
       "step": 230000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 0.00013783050393360768,
+      "loss": 0.3048,
+      "step": 231000
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 0.0001376997572617282,
+      "loss": 0.305,
+      "step": 232000
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 0.00013756837959454766,
+      "loss": 0.3042,
+      "step": 233000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.0001374363723687911,
+      "loss": 0.3042,
+      "step": 234000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.00013730373702806846,
+      "loss": 0.304,
+      "step": 235000
+    },
+    {
+      "epoch": 3.59,
+      "eval_runtime": 1.0392,
+      "eval_samples_per_second": 962.319,
+      "eval_steps_per_second": 15.397,
+      "step": 235000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.00013717047502285855,
+      "loss": 0.3036,
+      "step": 236000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.0001370365878104933,
+      "loss": 0.3036,
+      "step": 237000
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 0.00013690207685514185,
+      "loss": 0.3031,
+      "step": 238000
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.0001367669436277944,
+      "loss": 0.3032,
+      "step": 239000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 0.0001366311896062463,
+      "loss": 0.3036,
+      "step": 240000
+    },
+    {
+      "epoch": 3.66,
+      "eval_runtime": 1.0097,
+      "eval_samples_per_second": 990.396,
+      "eval_steps_per_second": 15.846,
+      "step": 240000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.612304032493538e+22,
+  "total_flos": 1.6824042935238852e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6f4b993c3e5de4e91e3f11164ead7579089c5cd884e3548feacf51898e103a
+oid sha256:398ac2faeaf62d164de8b0d15d7dce648669506924aad7a65bb21212c9dd95dd
 size 449471589