Training in progress, step 130000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0147a34f11e7c1f08c8f5a1a7b664f7685f6024ff50f7e310c340458a7ae47df
+oid sha256:8b61f0fcd50875833fb0e1f9ce51cdf7d430e60b619e76669b19c533bc334c88
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fe95a3571e9df68816ac46ccf405f0fd55b7d69662da0acabe531bd8d6e1a7
+oid sha256:39c23cb20328d6cd580ce88942d789c9a02552a95a268d89326d508421abbe4a
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13dfeb18522f460b3bcc4a8a207781907714f968fa9018d9e319a8e4cb1a2731
-size 14439
+oid sha256:a8e29d5733f7ec570f71140fb29faf2306a82ee45c27c9eb9c785e5d73fa8382
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93d998395352ee5e4e32f058b4acd76a3b9750cf1106a383769865ab27f4f83
-size 14503
+oid sha256:dabc5ed16f76e0d1a8c7f2b2c2a3619addb4d0c3eca0a88fa6e7b0ba2beea5dd
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0bf23f928568c7a3122050cfa99355815fe8c7f93429bc6536f64596e3cd0c
+oid sha256:7531b762a4f77385b5cf4054c1324ef1475bf3e0305baf6834591cd7a2e6b325
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea81d3c492be115b8468d1cd1e3438b2c19fcafe21dc467d287c05e9211418f
-size 14503
+oid sha256:95971fab031e1bc0e074238eeb9bb97d0dce735f44e80bc1ac009c7c3e11e0ef
+size 14439

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccdbb1080343e6446b837638f679019013e2908bdad70d4dd13ba9861cbc74c
+oid sha256:6b5759d26021494b175082e8aa472aecf989df6cf2e73cc13099dc5f04e8a3a7
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b675771b8e40ada562deddfe20382c77a27fda6482714c03a215febc190e3d96
+oid sha256:437af33cac768d06b94a7ff819e2415c2d01a6cb933eea2964edd87e0a74d2a3
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6547f6037906559622b01a609d68d147aca5926d35d56c61c1cb91881c5b9c16
+oid sha256:5f46bc5befc0dd2669aebf64aa0216b1a5da79235f03660685ed5378a375aacc
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e726e73c63cfe3e121582d5f26c95cee1a06ebdb69c1f3b859e1406e64a4d59
-size 14439
+oid sha256:10d615ff7d950e30ec30974f2cf78479d745d92e39a0b3ba0bec5c1a7fb2cdeb
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ddf5c33f60196860027b40e8443017b8ed479cc5dfb73f8a076fe07f546fd4
+oid sha256:f1c3de3c2d66025eca4b56b8d5efacb781ba1e9b4daae40acd9c92c0f7cbe98c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.676583228652839,
-  "global_step": 120000,
+  "epoch": 3.9829651643739084,
+  "global_step": 130000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2406,11 +2406,211 @@
       "eval_samples_per_second": 1855.209,
       "eval_steps_per_second": 29.683,
       "step": 120000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.0002720249765698123,
+      "loss": 0.3661,
+      "step": 120500
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.0002717412091888626,
+      "loss": 0.3663,
+      "step": 121000
+    },
+    {
+      "epoch": 3.71,
+      "eval_loss": 0.7859072089195251,
+      "eval_runtime": 0.5189,
+      "eval_samples_per_second": 1927.188,
+      "eval_steps_per_second": 30.835,
+      "step": 121000
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 0.00027145616514475274,
+      "loss": 0.3656,
+      "step": 121500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 0.0002711698475546788,
+      "loss": 0.3656,
+      "step": 122000
+    },
+    {
+      "epoch": 3.74,
+      "eval_loss": 0.7800880074501038,
+      "eval_runtime": 0.5426,
+      "eval_samples_per_second": 1842.936,
+      "eval_steps_per_second": 29.487,
+      "step": 122000
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.00027088225954976407,
+      "loss": 0.3653,
+      "step": 122500
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.0002705934042750249,
+      "loss": 0.3653,
+      "step": 123000
+    },
+    {
+      "epoch": 3.77,
+      "eval_loss": 0.7793842554092407,
+      "eval_runtime": 0.5318,
+      "eval_samples_per_second": 1880.356,
+      "eval_steps_per_second": 30.086,
+      "step": 123000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 0.00027030328488933625,
+      "loss": 0.3649,
+      "step": 123500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.00027001190456539726,
+      "loss": 0.3648,
+      "step": 124000
+    },
+    {
+      "epoch": 3.8,
+      "eval_loss": 0.7881133556365967,
+      "eval_runtime": 0.507,
+      "eval_samples_per_second": 1972.529,
+      "eval_steps_per_second": 31.56,
+      "step": 124000
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.0002697192664896965,
+      "loss": 0.3648,
+      "step": 124500
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.00026942537386247706,
+      "loss": 0.3644,
+      "step": 125000
+    },
+    {
+      "epoch": 3.83,
+      "eval_loss": 0.7862609624862671,
+      "eval_runtime": 0.5236,
+      "eval_samples_per_second": 1909.846,
+      "eval_steps_per_second": 30.558,
+      "step": 125000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.0002691302298977016,
+      "loss": 0.3643,
+      "step": 125500
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.0002688338378230173,
+      "loss": 0.3642,
+      "step": 126000
+    },
+    {
+      "epoch": 3.86,
+      "eval_loss": 0.7819104194641113,
+      "eval_runtime": 0.5098,
+      "eval_samples_per_second": 1961.492,
+      "eval_steps_per_second": 31.384,
+      "step": 126000
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 0.00026853620087972035,
+      "loss": 0.3636,
+      "step": 126500
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.00026823732232272065,
+      "loss": 0.3638,
+      "step": 127000
+    },
+    {
+      "epoch": 3.89,
+      "eval_loss": 0.7886289358139038,
+      "eval_runtime": 0.5488,
+      "eval_samples_per_second": 1822.211,
+      "eval_steps_per_second": 29.155,
+      "step": 127000
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.0002679372054205063,
+      "loss": 0.3637,
+      "step": 127500
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 0.0002676358534551076,
+      "loss": 0.3637,
+      "step": 128000
+    },
+    {
+      "epoch": 3.92,
+      "eval_loss": 0.7856259942054749,
+      "eval_runtime": 0.5448,
+      "eval_samples_per_second": 1835.504,
+      "eval_steps_per_second": 29.368,
+      "step": 128000
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.00026733326972206133,
+      "loss": 0.3631,
+      "step": 128500
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.0002670294575303748,
+      "loss": 0.3631,
+      "step": 129000
+    },
+    {
+      "epoch": 3.95,
+      "eval_loss": 0.7774640917778015,
+      "eval_runtime": 0.5451,
+      "eval_samples_per_second": 1834.446,
+      "eval_steps_per_second": 29.351,
+      "step": 129000
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.0002667244202024894,
+      "loss": 0.3629,
+      "step": 129500
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 0.00026641816107424453,
+      "loss": 0.363,
+      "step": 130000
+    },
+    {
+      "epoch": 3.98,
+      "eval_loss": 0.7824729084968567,
+      "eval_runtime": 0.5158,
+      "eval_samples_per_second": 1938.903,
+      "eval_steps_per_second": 31.022,
+      "step": 130000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 3.8338217014380724e+21,
+  "total_flos": 4.1533088402125724e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fe95a3571e9df68816ac46ccf405f0fd55b7d69662da0acabe531bd8d6e1a7
+oid sha256:39c23cb20328d6cd580ce88942d789c9a02552a95a268d89326d508421abbe4a
 size 102501541