Training in progress, step 30000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab89fbcd5cd837ff38661f8e6562d1e556debad1cf94429f314679699e56c75
+oid sha256:a06ffce25ec404e52367f5cc0b644052826374a7fdd783f9655fcd285df66d6d
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650de0629283aadbd2ed9c9c4e4fa6910cc48450c6a7d6491a018378e49a8f08
+oid sha256:c329e242cb4a3f96564fe11ec3eccc7274448a9d37d936eb1f9c1b5bcd37ec91
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5075119d983cedc61f9e794107c876257cfc00cbcd125777dcdfcea5b38678a0
+oid sha256:3050f6cd4e244bcfafaa04a6d1b955b9b5bab22bee349f2d0379131ff0874e3f
 size 15523

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f62cdfaeb53c638813006cc5b9f0699031a6115d20311906da58b054af32fe51
+oid sha256:4a980a1351c683c05bfb6454932005b70f1b4871d3735c6a11b55d7963483b96
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb733c4a27965716bd87114bf2e4699ec7082883b2e3998dcc83abb3d40f744
+oid sha256:dbf786375f854cc04cfc07ff0949c0fe8ff8ba67bd06f47c9df99e37ce7c9a9a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.741705129321606,
-  "global_step": 20000,
+  "epoch": 2.6125576939824087,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -278,11 +278,147 @@
       "eval_samples_per_second": 64.086,
       "eval_steps_per_second": 1.013,
       "step": 20000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 9.16930919656158e-05,
+      "loss": 0.4344,
+      "step": 20500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.126149821203012e-05,
+      "loss": 0.4318,
+      "step": 21000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.082019786191564e-05,
+      "loss": 0.4311,
+      "step": 21500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.037015579484156e-05,
+      "loss": 0.4303,
+      "step": 22000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 8.99114830519538e-05,
+      "loss": 0.4304,
+      "step": 22500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.944429280388843e-05,
+      "loss": 0.4295,
+      "step": 23000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 8.89687003228484e-05,
+      "loss": 0.4281,
+      "step": 23500
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 8.848482295416199e-05,
+      "loss": 0.4281,
+      "step": 24000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 8.799377224186928e-05,
+      "loss": 0.428,
+      "step": 24500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 8.749370124680773e-05,
+      "loss": 0.4271,
+      "step": 25000
+    },
+    {
+      "epoch": 2.18,
+      "eval_loss": 0.4083108901977539,
+      "eval_runtime": 56.8155,
+      "eval_samples_per_second": 88.004,
+      "eval_steps_per_second": 1.39,
+      "step": 25000
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 8.698570929805091e-05,
+      "loss": 0.4287,
+      "step": 25500
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.646992173501096e-05,
+      "loss": 0.4287,
+      "step": 26000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.594646582055114e-05,
+      "loss": 0.426,
+      "step": 26500
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.54165401371507e-05,
+      "loss": 0.4262,
+      "step": 27000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.487923561201862e-05,
+      "loss": 0.4247,
+      "step": 27500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.433358581553496e-05,
+      "loss": 0.4228,
+      "step": 28000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.37807947765529e-05,
+      "loss": 0.4234,
+      "step": 28500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 8.322099888798968e-05,
+      "loss": 0.4241,
+      "step": 29000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 8.265433627110443e-05,
+      "loss": 0.4237,
+      "step": 29500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.20809467414187e-05,
+      "loss": 0.4222,
+      "step": 30000
+    },
+    {
+      "epoch": 2.61,
+      "eval_loss": 0.4024658799171448,
+      "eval_runtime": 80.1786,
+      "eval_samples_per_second": 62.361,
+      "eval_steps_per_second": 0.985,
+      "step": 30000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 9.419374931572379e+20,
+  "total_flos": 1.4128888515849526e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650de0629283aadbd2ed9c9c4e4fa6910cc48450c6a7d6491a018378e49a8f08
+oid sha256:c329e242cb4a3f96564fe11ec3eccc7274448a9d37d936eb1f9c1b5bcd37ec91
 size 449471589