Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb532cf97353e876d3c07dafda9641b1330c0ef72b36326c6da98516454dc96
+oid sha256:1697d53984b439e7327a0da7030659bcc191c89124216fe8240d43fb004110ba
 size 734275920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3471614dd25efffa34ced8adea663f06082eaa9ce06ff0ae502a2a2ce49dce6a
+oid sha256:0e24effe110ebba34f42d63b80eaccb2a97fbe0e91f4e1d0d25d0823af27f34a
 size 1468687243

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15c2f1e87a9fcaf57351b335abc031c00c3adda5167bcf7ec0b18e183f3ee6ae
+oid sha256:48e42e78ee2689141db2aa36168809ae145b2ea351a4978872644c5587b84ff8
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da416040f48730a4d4754962dfc1cf7e84c988b051ed7995fad8903f5b75ce23
+oid sha256:8f78aa7de166ae1b78898a061c80c7d73724dc9fcfb5269ef4e7807084cda31d
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b41d044a0b95f3d68b68c393e43b00c5ca90a1a9bc2f1272a5782f85171f5a
+oid sha256:8b4fa473a13a8055ecd91a792ceedace9b305b095bc0470e8680559c4564e704
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7909009ee6bb6a7388a27f2195f9d99a87ca4bfa7948fb59ebcf32152929a165
+oid sha256:db461a9dee610efe78caa588c54fcc74909ce5d166ca7a4133f3f5f5280e91e7
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8793849385d70eb0a4454019ee1dea79e0782bfac3827e1750c91bff2a4e5501
+oid sha256:ea3c4dae1a9a132985c2fe8a16f00f00e6a75b0a89bc641b65e6029f630cc7a8
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6203f4502122aa111ee64a6591a834d190fa04fcbd197aea65cf4f041f3e16
+oid sha256:dc262f4ad8cdaf2d5605f4ed5f2d19a6c8cdcfe8bb557c95eb12f35788aa1a91
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20e94508e1cbf7f79ffc938a6389a03f2f263a9d7c056df1a5c8567f12db613
+oid sha256:0d6e02967c943c7285054ff2d6e85583a0d50e230c4d165759e0c7efb0cb6cc2
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c8b444dac54dc5ad78a7292762380772bc71cffe63d34cd4898fae9fc500a4
+oid sha256:c48aca1aa4552b505c8ba0582648eccb7e876162d1d989a4ff2948e15d0afefb
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36ffe8038dcfcbb1af52f768d5ded0e7902497baa765ea8664469f5c3a22aec
+oid sha256:091bf8841b544ca817b2c69c4d32e29435f0e7a64d1c3b7d04899e50753a7dbf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12,
+  "epoch": 0.16,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -476,6 +476,162 @@
       "eval_samples_per_second": 10.807,
       "eval_steps_per_second": 0.54,
       "step": 6000
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 462631.5,
+      "learning_rate": 0.000482635014919091,
+      "loss": 59.005234375,
+      "step": 6100
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 273326.59375,
+      "learning_rate": 0.00048205345814171074,
+      "loss": 58.9213232421875,
+      "step": 6200
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 36951.60546875,
+      "learning_rate": 0.00048146268507654377,
+      "loss": 58.82025390625,
+      "step": 6300
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 103255.4765625,
+      "learning_rate": 0.00048086271918686716,
+      "loss": 58.84619140625,
+      "step": 6400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 102904.96875,
+      "learning_rate": 0.00048025358430106227,
+      "loss": 58.514482421875,
+      "step": 6500
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 368401.625,
+      "learning_rate": 0.00047963530461166826,
+      "loss": 58.3533984375,
+      "step": 6600
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 307524.84375,
+      "learning_rate": 0.0004790079046744218,
+      "loss": 58.44912109375,
+      "step": 6700
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 218012.390625,
+      "learning_rate": 0.000478371409407281,
+      "loss": 58.45431640625,
+      "step": 6800
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 1243047.5,
+      "learning_rate": 0.0004777258440894362,
+      "loss": 58.24828125,
+      "step": 6900
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 158677.6875,
+      "learning_rate": 0.0004770712343603062,
+      "loss": 58.133662109375,
+      "step": 7000
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 58.2567138671875,
+      "eval_runtime": 1.8382,
+      "eval_samples_per_second": 10.88,
+      "eval_steps_per_second": 0.544,
+      "step": 7000
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 237161.1875,
+      "learning_rate": 0.0004764076062185194,
+      "loss": 58.3987744140625,
+      "step": 7100
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 60140.4921875,
+      "learning_rate": 0.00047573498602088154,
+      "loss": 58.801220703125,
+      "step": 7200
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 494529.25,
+      "learning_rate": 0.00047505340048132916,
+      "loss": 58.503544921875,
+      "step": 7300
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 561465.625,
+      "learning_rate": 0.00047436287666986803,
+      "loss": 58.614169921875,
+      "step": 7400
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 572518.4375,
+      "learning_rate": 0.00047366344201149856,
+      "loss": 58.28416015625,
+      "step": 7500
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 1078630.125,
+      "learning_rate": 0.0004729551242851264,
+      "loss": 58.4676513671875,
+      "step": 7600
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 70299.53125,
+      "learning_rate": 0.00047223795162245886,
+      "loss": 58.200947265625,
+      "step": 7700
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 68182.265625,
+      "learning_rate": 0.0004715119525068883,
+      "loss": 58.55353515625,
+      "step": 7800
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 82698.640625,
+      "learning_rate": 0.00047077715577236015,
+      "loss": 58.704990234375,
+      "step": 7900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 375052.03125,
+      "learning_rate": 0.0004700335906022283,
+      "loss": 58.521640625,
+      "step": 8000
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 57.7498779296875,
+      "eval_runtime": 1.8363,
+      "eval_samples_per_second": 10.892,
+      "eval_steps_per_second": 0.545,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -495,7 +651,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.274704613376e+16,
+  "total_flos": 5.699606151168e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null