Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a5c6f637a1a02dcc7ffaf9221661cd85b1333abef16fc488c6b215871a6822
+oid sha256:9b4228b55bb76fc15ca95505a3ef7ec1042cf993453b65da92e201da75ce6c8d
 size 734275920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c3777540c9cd45951a7ac81a4e2bd9cf7e915ec27607f40e65e0ff5e617376
+oid sha256:6a5846d1fe27e8749ffc72486781b7806ecb1483360bdd08c503170e6b013162
 size 1468687243

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bab46455b81fe89286c0ac46f8274ae8d3f1816023d3983b6a1b462f39004a0d
+oid sha256:7de62db38127a19f1b74e4caf4fa2c7f80e3db34a1364e6d48e3845081d03fad
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47566dba2923569afde0e0a5ff4f2c437f9949274f917cc17b4936577ce63ab0
+oid sha256:d65799baf1d2dfe04d0a138d3793b0b5a501104449fe070829112843354c238d
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3324888af4fe870d448514f0b37d040d89d6aebdf2c735d51b734b3cbec36311
+oid sha256:53e5e0e4abd3c70926da0534c109583a158a9ad33404eba4274e07ea784e7b91
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b762073c3a91474269912b3ac897e24094100f62acadd0675372ec65e569e0
+oid sha256:2ca52ef4191d31f82dcef0a542d277b30f0239b891949e489402bf4e36cbcb3b
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f51ed2846fc1924bdb38919225f48ce1c91d4b4e7f33ffeffcc034c81c3137
+oid sha256:9e477a794f5d1340be38828422d8ce148abb3584a23d53b93905b3bc505514f2
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3591e1beb54a633e255be3082ac8130dcb0fb2f006bfea6cd68b941d0fc906f
+oid sha256:86ba7bf6efe64ed70ecf29b7b1a438293fcbe5fba6a7fd4be175bb0a03ccba48
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d023a9bb27873f11f312f75e42b2c4fe8003df9343f38bb24a6ae408e1b22e14
+oid sha256:7a8720dd04ab0427bc7dc643de458ddb996dfa7c64ecd5d25e0538512b96776c
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04aea28178ef35e5c4d53227bf7103f8d69d1ab082c35d47cd15905005ed5538
+oid sha256:1a79b6ed8c9a33b7a01ec6af6b482537b5b012444212ea60980ce76bcac7ea0d
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49159d7a99a47c2c1201791bfa611289fd4e18fce3afc4b5f5914a4bf7836d08
+oid sha256:1a11b408b02a0c1a9e74618915c249c34fbb229118ef1abb560e9617d25e1c52
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04,
+  "epoch": 0.08,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -164,6 +164,162 @@
       "eval_samples_per_second": 10.88,
       "eval_steps_per_second": 0.544,
       "step": 2000
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 7411.40234375,
+      "learning_rate": 0.0004981165372376802,
+      "loss": 58.2853564453125,
+      "step": 2100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 33.24531173706055,
+      "learning_rate": 0.0004979185796562494,
+      "loss": 57.3351123046875,
+      "step": 2200
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 1044.70458984375,
+      "learning_rate": 0.0004977107756842668,
+      "loss": 55.583466796875,
+      "step": 2300
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 488.1427001953125,
+      "learning_rate": 0.0004974931335749219,
+      "loss": 53.566806640625,
+      "step": 2400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 949.36181640625,
+      "learning_rate": 0.000497265661972138,
+      "loss": 52.38724609375,
+      "step": 2500
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 1916.361328125,
+      "learning_rate": 0.0004970283699102291,
+      "loss": 55.593505859375,
+      "step": 2600
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 40184.4609375,
+      "learning_rate": 0.0004967812668135405,
+      "loss": 59.1807861328125,
+      "step": 2700
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 1653.9197998046875,
+      "learning_rate": 0.0004965243624960747,
+      "loss": 60.0856396484375,
+      "step": 2800
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 570.0091552734375,
+      "learning_rate": 0.0004962576671611021,
+      "loss": 55.3298486328125,
+      "step": 2900
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 767297.5625,
+      "learning_rate": 0.000495981191400755,
+      "loss": 59.248984375,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 65.7476806640625,
+      "eval_runtime": 1.8469,
+      "eval_samples_per_second": 10.829,
+      "eval_steps_per_second": 0.541,
+      "step": 3000
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 1796894.75,
+      "learning_rate": 0.0004956949461956074,
+      "loss": 61.4278955078125,
+      "step": 3100
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 372332.40625,
+      "learning_rate": 0.0004953989429142387,
+      "loss": 58.2212158203125,
+      "step": 3200
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 839582.25,
+      "learning_rate": 0.0004950931933127826,
+      "loss": 60.9759326171875,
+      "step": 3300
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 456507.9375,
+      "learning_rate": 0.0004947777095344596,
+      "loss": 60.5664697265625,
+      "step": 3400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 42298.0859375,
+      "learning_rate": 0.0004944525041090948,
+      "loss": 59.9312353515625,
+      "step": 3500
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 44746.13671875,
+      "learning_rate": 0.0004941175899526208,
+      "loss": 60.0662353515625,
+      "step": 3600
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 6649.8818359375,
+      "learning_rate": 0.0004937729803665643,
+      "loss": 61.2509716796875,
+      "step": 3700
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 15284.4833984375,
+      "learning_rate": 0.0004934186890375175,
+      "loss": 59.5713232421875,
+      "step": 3800
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 13539.5712890625,
+      "learning_rate": 0.0004930547300365956,
+      "loss": 58.5672265625,
+      "step": 3900
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 53576.8984375,
+      "learning_rate": 0.0004926811178188765,
+      "loss": 58.3544189453125,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 58.579750061035156,
+      "eval_runtime": 1.8442,
+      "eval_samples_per_second": 10.845,
+      "eval_steps_per_second": 0.542,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -183,7 +339,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.424901537792e+16,
+  "total_flos": 2.849803075584e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null