Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b4228b55bb76fc15ca95505a3ef7ec1042cf993453b65da92e201da75ce6c8d
+oid sha256:9bb532cf97353e876d3c07dafda9641b1330c0ef72b36326c6da98516454dc96
 size 734275920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5846d1fe27e8749ffc72486781b7806ecb1483360bdd08c503170e6b013162
+oid sha256:3471614dd25efffa34ced8adea663f06082eaa9ce06ff0ae502a2a2ce49dce6a
 size 1468687243

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de62db38127a19f1b74e4caf4fa2c7f80e3db34a1364e6d48e3845081d03fad
+oid sha256:15c2f1e87a9fcaf57351b335abc031c00c3adda5167bcf7ec0b18e183f3ee6ae
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65799baf1d2dfe04d0a138d3793b0b5a501104449fe070829112843354c238d
+oid sha256:da416040f48730a4d4754962dfc1cf7e84c988b051ed7995fad8903f5b75ce23
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e5e0e4abd3c70926da0534c109583a158a9ad33404eba4274e07ea784e7b91
+oid sha256:96b41d044a0b95f3d68b68c393e43b00c5ca90a1a9bc2f1272a5782f85171f5a
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca52ef4191d31f82dcef0a542d277b30f0239b891949e489402bf4e36cbcb3b
+oid sha256:7909009ee6bb6a7388a27f2195f9d99a87ca4bfa7948fb59ebcf32152929a165
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e477a794f5d1340be38828422d8ce148abb3584a23d53b93905b3bc505514f2
+oid sha256:8793849385d70eb0a4454019ee1dea79e0782bfac3827e1750c91bff2a4e5501
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ba7bf6efe64ed70ecf29b7b1a438293fcbe5fba6a7fd4be175bb0a03ccba48
+oid sha256:aa6203f4502122aa111ee64a6591a834d190fa04fcbd197aea65cf4f041f3e16
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a8720dd04ab0427bc7dc643de458ddb996dfa7c64ecd5d25e0538512b96776c
+oid sha256:b20e94508e1cbf7f79ffc938a6389a03f2f263a9d7c056df1a5c8567f12db613
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a79b6ed8c9a33b7a01ec6af6b482537b5b012444212ea60980ce76bcac7ea0d
+oid sha256:f8c8b444dac54dc5ad78a7292762380772bc71cffe63d34cd4898fae9fc500a4
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a11b408b02a0c1a9e74618915c249c34fbb229118ef1abb560e9617d25e1c52
+oid sha256:d36ffe8038dcfcbb1af52f768d5ded0e7902497baa765ea8664469f5c3a22aec
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08,
+  "epoch": 0.12,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -320,6 +320,162 @@
       "eval_samples_per_second": 10.845,
       "eval_steps_per_second": 0.542,
       "step": 4000
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 160393.71875,
+      "learning_rate": 0.000492297867222828,
+      "loss": 59.3321435546875,
+      "step": 4100
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 12930.431640625,
+      "learning_rate": 0.0004919049934697177,
+      "loss": 60.8889404296875,
+      "step": 4200
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 4836.6787109375,
+      "learning_rate": 0.0004915025121630086,
+      "loss": 61.493935546875,
+      "step": 4300
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 595.083984375,
+      "learning_rate": 0.0004910904392877396,
+      "loss": 58.8386474609375,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 12180.2373046875,
+      "learning_rate": 0.0004906687912098906,
+      "loss": 63.4604150390625,
+      "step": 4500
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 414.4292297363281,
+      "learning_rate": 0.0004902375846757322,
+      "loss": 59.018310546875,
+      "step": 4600
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 2297.899169921875,
+      "learning_rate": 0.0004897968368111611,
+      "loss": 57.6424853515625,
+      "step": 4700
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2821.689697265625,
+      "learning_rate": 0.0004893465651210193,
+      "loss": 58.3983154296875,
+      "step": 4800
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 2559.970947265625,
+      "learning_rate": 0.0004888867874883995,
+      "loss": 57.3033935546875,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 8444.46484375,
+      "learning_rate": 0.0004884175221739343,
+      "loss": 56.6698193359375,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 57.39847946166992,
+      "eval_runtime": 1.8416,
+      "eval_samples_per_second": 10.86,
+      "eval_steps_per_second": 0.543,
+      "step": 5000
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 6454.49658203125,
+      "learning_rate": 0.0004879387878150716,
+      "loss": 56.9357958984375,
+      "step": 5100
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 337538.0,
+      "learning_rate": 0.00048745060342533363,
+      "loss": 56.982119140625,
+      "step": 5200
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 68615.4609375,
+      "learning_rate": 0.0004869529883935625,
+      "loss": 56.92587890625,
+      "step": 5300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 116072.59375,
+      "learning_rate": 0.00048644596248314967,
+      "loss": 57.190751953125,
+      "step": 5400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 291359.625,
+      "learning_rate": 0.0004859295458312511,
+      "loss": 58.6766162109375,
+      "step": 5500
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 89412.578125,
+      "learning_rate": 0.0004854037589479878,
+      "loss": 58.688193359375,
+      "step": 5600
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 293593.4375,
+      "learning_rate": 0.0004848686227156309,
+      "loss": 59.063056640625,
+      "step": 5700
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 30479.330078125,
+      "learning_rate": 0.0004843241583877724,
+      "loss": 58.46580078125,
+      "step": 5800
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 89906.7734375,
+      "learning_rate": 0.000483770387588481,
+      "loss": 58.2409228515625,
+      "step": 5900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 630418.5,
+      "learning_rate": 0.00048320733231144354,
+      "loss": 58.333916015625,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 59.336669921875,
+      "eval_runtime": 1.8507,
+      "eval_samples_per_second": 10.807,
+      "eval_steps_per_second": 0.54,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -339,7 +495,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.849803075584e+16,
+  "total_flos": 4.274704613376e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null