Training in progress, step 70000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3457b112e12db877a42c46fac58e3d5e20d221b80033f44297d02f1bf0a29bbe
-size 202193937
+oid sha256:52c5dc947e6cf77a2f13cd5b7f75774d9ee18e8bb1706815f27839917ebc139f
+size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c079ca10e4f5074932186a3283d50bcc598bd582a7cd9edd91714e4c65dfd6
+oid sha256:fd6143f947ad34a118a277142b729e7aec8108ac65db132781f90f89fd6d2d7d
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e76b9e301f7b0cb22b85fec18227db354fe14cc5bb0bac90d3b2a5337f4cfb
+oid sha256:b6fe73b1b40978075c02727ad4956e4d1b16707096f7223f142676127872cbe0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f01862087338bfbd20acfb7c33a70b3489e0a5ef9dae3d8a1be43686b8375ef
-size 14503
+oid sha256:dc72bddb53bad0049947d6480bf573724b62938239cf1810454d762aa23edd89
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c4fb9cb08b2fb5e7c87f09e0ad5cd788c7c092793db04c47d6d764cec33eaf
+oid sha256:3dac322e61dd5ec1258ef6267f0eb26ddd545115f42b9dd4d8d424f54644612b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6aba86ae8ce52debffa93be97b7a876db9a94eebefae3b2b0e6b949b39a05e
+oid sha256:f401fa11e5a9225fec902704af9ab763f5d60dd51eae4b0592a34621c9a469e2
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f6fe510afc4f0762f2f366a0873b87dc0eb54ac8956217e4dd97eb82d82822
+oid sha256:b90a7924f074d2835ad5940aa65be7efd984818695ea768631ffe6ce95141de0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8e8b5929e9213579996a620f084555093e802a48735f0426b630b1b890dd65
-size 14439
+oid sha256:f0a6bfbbc7a2b661e5e8652e559ad6f4c64c79db32e2bc10cca19b276788c2b6
+size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea3829be57439a52e1f652bee0bd8412efb9460e9e607102830248cd7073d65
+oid sha256:a373660ab148daebea2355c821d057c46749d2baadf42884aac334d565f1e5ae
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a2ff2402a89a08691d66fefb0a4ebd6e4077409e1db9d9b06b5d8cf10952a6
+oid sha256:35d3442500daea86a3c50feeabd94befbadee050f02e7edb3bf2746c36f1a779
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afd4be721b18cec2bad25f6a60e1c3abb5c311277f62eb3e2f010bc31239df1
+oid sha256:c6a21aa935b59f32e80e60eb114e1441ce82daea46fee66d7b5b4fedbaaa6094
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8382916143264194,
-  "global_step": 60000,
+  "epoch": 2.1446735500474894,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1206,11 +1206,211 @@
       "eval_samples_per_second": 1857.26,
       "eval_steps_per_second": 29.716,
       "step": 60000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00029602157489814693,
+      "loss": 0.4084,
+      "step": 60500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00029590925100598365,
+      "loss": 0.4077,
+      "step": 61000
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 0.7871591448783875,
+      "eval_runtime": 0.5252,
+      "eval_samples_per_second": 1904.035,
+      "eval_steps_per_second": 30.465,
+      "step": 61000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.000295795386152827,
+      "loss": 0.4068,
+      "step": 61500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0002956799815838848,
+      "loss": 0.4061,
+      "step": 62000
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 0.7920863032341003,
+      "eval_runtime": 0.5271,
+      "eval_samples_per_second": 1897.169,
+      "eval_steps_per_second": 30.355,
+      "step": 62000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0002955630385612029,
+      "loss": 0.4056,
+      "step": 62500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.0002954445583636515,
+      "loss": 0.405,
+      "step": 63000
+    },
+    {
+      "epoch": 1.93,
+      "eval_loss": 0.7836641073226929,
+      "eval_runtime": 0.5362,
+      "eval_samples_per_second": 1864.939,
+      "eval_steps_per_second": 29.839,
+      "step": 63000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00029532454228691103,
+      "loss": 0.4043,
+      "step": 63500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.0002952029916434581,
+      "loss": 0.4036,
+      "step": 64000
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.7819440960884094,
+      "eval_runtime": 0.5223,
+      "eval_samples_per_second": 1914.709,
+      "eval_steps_per_second": 30.635,
+      "step": 64000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00029507990776255107,
+      "loss": 0.403,
+      "step": 64500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00029495529199021555,
+      "loss": 0.4023,
+      "step": 65000
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 0.7944305539131165,
+      "eval_runtime": 0.5274,
+      "eval_samples_per_second": 1896.133,
+      "eval_steps_per_second": 30.338,
+      "step": 65000
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.0002948291456892296,
+      "loss": 0.4018,
+      "step": 65500
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00029470147023910907,
+      "loss": 0.4009,
+      "step": 66000
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.7896050214767456,
+      "eval_runtime": 0.514,
+      "eval_samples_per_second": 1945.63,
+      "eval_steps_per_second": 31.13,
+      "step": 66000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002945722670360921,
+      "loss": 0.4006,
+      "step": 66500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.0002944415374931243,
+      "loss": 0.4003,
+      "step": 67000
+    },
+    {
+      "epoch": 2.05,
+      "eval_loss": 0.7898439168930054,
+      "eval_runtime": 0.5343,
+      "eval_samples_per_second": 1871.754,
+      "eval_steps_per_second": 29.948,
+      "step": 67000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00029430928303984295,
+      "loss": 0.3993,
+      "step": 67500
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.0002941755051225616,
+      "loss": 0.3988,
+      "step": 68000
+    },
+    {
+      "epoch": 2.08,
+      "eval_loss": 0.7866422533988953,
+      "eval_runtime": 0.5273,
+      "eval_samples_per_second": 1896.599,
+      "eval_steps_per_second": 30.346,
+      "step": 68000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00029404020520425417,
+      "loss": 0.3984,
+      "step": 68500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002939033847645388,
+      "loss": 0.3979,
+      "step": 69000
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 0.7866395711898804,
+      "eval_runtime": 0.5223,
+      "eval_samples_per_second": 1914.777,
+      "eval_steps_per_second": 30.636,
+      "step": 69000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.00029376504529966195,
+      "loss": 0.3974,
+      "step": 69500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00029362518832248184,
+      "loss": 0.3968,
+      "step": 70000
+    },
+    {
+      "epoch": 2.14,
+      "eval_loss": 0.7869418263435364,
+      "eval_runtime": 0.52,
+      "eval_samples_per_second": 1922.99,
+      "eval_steps_per_second": 30.768,
+      "step": 70000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.916914844695024e+21,
+  "total_flos": 2.2363939955175483e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c079ca10e4f5074932186a3283d50bcc598bd582a7cd9edd91714e4c65dfd6
+oid sha256:fd6143f947ad34a118a277142b729e7aec8108ac65db132781f90f89fd6d2d7d
 size 102501541