Training in progress, step 320000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c38081c882988bad98fc3f3c119510cdcd90a9e84f912d6cad0cba15182d5589
+oid sha256:feec96829044f69c5632c270eedd009034bbe0cf717e555992fa10aeea97b864
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b2181d9db98eb1abf2e59d3ffca75b8922c4c585b17c4c50bcc63a5ba1af87
+oid sha256:d15795c67ef8a474ec8269e65cb5cae595586b0dd6a18f0656a533551a730789
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
+oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
+oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
+oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
+oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
+oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
+oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
+oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
+oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8c10dab6d3ee824fc8fe4628d3bf3ceea806ce0d2fbe513f32af4d508ab89e
+oid sha256:5673377a057c7734bd1a0ee14d972f6f3bfc67bb8208ac49ae618347d18d616b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.900504612875274,
-  "global_step": 310000,
+  "epoch": 8.15535960038738,
+  "global_step": 320000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6206,11 +6206,211 @@
       "eval_samples_per_second": 786.914,
       "eval_steps_per_second": 12.591,
       "step": 310000
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 0.00010973674410951567,
+      "loss": 0.281,
+      "step": 310500
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 0.00010928144739511337,
+      "loss": 0.281,
+      "step": 311000
+    },
+    {
+      "epoch": 7.93,
+      "eval_loss": 0.806954562664032,
+      "eval_runtime": 1.274,
+      "eval_samples_per_second": 784.956,
+      "eval_steps_per_second": 12.559,
+      "step": 311000
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 0.00010882665065147757,
+      "loss": 0.2805,
+      "step": 311500
+    },
+    {
+      "epoch": 7.95,
+      "learning_rate": 0.00010837235885219267,
+      "loss": 0.2807,
+      "step": 312000
+    },
+    {
+      "epoch": 7.95,
+      "eval_loss": 0.8041293621063232,
+      "eval_runtime": 1.273,
+      "eval_samples_per_second": 785.527,
+      "eval_steps_per_second": 12.568,
+      "step": 312000
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 0.00010791857696532089,
+      "loss": 0.2808,
+      "step": 312500
+    },
+    {
+      "epoch": 7.98,
+      "learning_rate": 0.00010746530995334832,
+      "loss": 0.2811,
+      "step": 313000
+    },
+    {
+      "epoch": 7.98,
+      "eval_loss": 0.8100136518478394,
+      "eval_runtime": 1.2743,
+      "eval_samples_per_second": 784.749,
+      "eval_steps_per_second": 12.556,
+      "step": 313000
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 0.0001070125627731304,
+      "loss": 0.2809,
+      "step": 313500
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0001065603403758377,
+      "loss": 0.2821,
+      "step": 314000
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.828373908996582,
+      "eval_runtime": 1.2715,
+      "eval_samples_per_second": 786.498,
+      "eval_steps_per_second": 12.584,
+      "step": 314000
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 0.00010610864770690196,
+      "loss": 0.2806,
+      "step": 314500
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 0.00010565748970596172,
+      "loss": 0.2808,
+      "step": 315000
+    },
+    {
+      "epoch": 8.03,
+      "eval_loss": 0.8072633743286133,
+      "eval_runtime": 1.2547,
+      "eval_samples_per_second": 796.999,
+      "eval_steps_per_second": 12.752,
+      "step": 315000
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 0.00010520687130680884,
+      "loss": 0.2809,
+      "step": 315500
+    },
+    {
+      "epoch": 8.05,
+      "learning_rate": 0.00010475679743733364,
+      "loss": 0.2805,
+      "step": 316000
+    },
+    {
+      "epoch": 8.05,
+      "eval_loss": 0.8141467571258545,
+      "eval_runtime": 1.2856,
+      "eval_samples_per_second": 777.823,
+      "eval_steps_per_second": 12.445,
+      "step": 316000
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 0.00010430727301947202,
+      "loss": 0.2804,
+      "step": 316500
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 0.00010385830296915104,
+      "loss": 0.2801,
+      "step": 317000
+    },
+    {
+      "epoch": 8.08,
+      "eval_loss": 0.8066883683204651,
+      "eval_runtime": 1.2502,
+      "eval_samples_per_second": 799.87,
+      "eval_steps_per_second": 12.798,
+      "step": 317000
+    },
+    {
+      "epoch": 8.09,
+      "learning_rate": 0.00010340989219623508,
+      "loss": 0.2803,
+      "step": 317500
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 0.0001029620456044727,
+      "loss": 0.28,
+      "step": 318000
+    },
+    {
+      "epoch": 8.1,
+      "eval_loss": 0.8122532963752747,
+      "eval_runtime": 1.2711,
+      "eval_samples_per_second": 786.71,
+      "eval_steps_per_second": 12.587,
+      "step": 318000
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 0.00010251476809144226,
+      "loss": 0.2801,
+      "step": 318500
+    },
+    {
+      "epoch": 8.13,
+      "learning_rate": 0.00010206806454849917,
+      "loss": 0.2802,
+      "step": 319000
+    },
+    {
+      "epoch": 8.13,
+      "eval_loss": 0.8077669143676758,
+      "eval_runtime": 1.2395,
+      "eval_samples_per_second": 806.793,
+      "eval_steps_per_second": 12.909,
+      "step": 319000
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 0.00010162193986072167,
+      "loss": 0.2805,
+      "step": 319500
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 0.00010117639890685795,
+      "loss": 0.2799,
+      "step": 320000
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": 0.8211207389831543,
+      "eval_runtime": 1.2456,
+      "eval_samples_per_second": 802.848,
+      "eval_steps_per_second": 12.846,
+      "step": 320000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 9.904006949618185e+21,
+  "total_flos": 1.022348060947964e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b2181d9db98eb1abf2e59d3ffca75b8922c4c585b17c4c50bcc63a5ba1af87
+oid sha256:d15795c67ef8a474ec8269e65cb5cae595586b0dd6a18f0656a533551a730789
 size 102501541