Training in progress, step 310000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff044e80c574241efa7089a5ec2f633f003713c3c6f5dd2b7df44302f14645b7
+oid sha256:c38081c882988bad98fc3f3c119510cdcd90a9e84f912d6cad0cba15182d5589
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5e4cc7c8890a029475b21a89ba73ee51bdbf0169ee989a07985e899b417451
+oid sha256:01b2181d9db98eb1abf2e59d3ffca75b8922c4c585b17c4c50bcc63a5ba1af87
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
+oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
+oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
+oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
+oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
+oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
+oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
+oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bee1da196beb31121585eda29e2f73fb8583fc7e72eb4a3d5453bf8facf2f9
+oid sha256:05ae8a4dd944da2b5707cf785065491f61bb5535f2394367e15da56fde42baa0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7914b9f1e3709b1198ec189eb9bb9105cd6b88dedbcbbdd4128934a703cf33e3
+oid sha256:9b8c10dab6d3ee824fc8fe4628d3bf3ceea806ce0d2fbe513f32af4d508ab89e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.645649625363168,
-  "global_step": 300000,
+  "epoch": 7.900504612875274,
+  "global_step": 310000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6006,11 +6006,211 @@
       "eval_samples_per_second": 755.698,
       "eval_steps_per_second": 12.091,
       "step": 300000
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 0.00011893996636109606,
+      "loss": 0.2819,
+      "step": 300500
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 0.00011847572270435852,
+      "loss": 0.2818,
+      "step": 301000
+    },
+    {
+      "epoch": 7.67,
+      "eval_loss": 0.8139034509658813,
+      "eval_runtime": 1.299,
+      "eval_samples_per_second": 769.829,
+      "eval_steps_per_second": 12.317,
+      "step": 301000
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 0.00011801187847126579,
+      "loss": 0.2821,
+      "step": 301500
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 0.00011754843873434411,
+      "loss": 0.2818,
+      "step": 302000
+    },
+    {
+      "epoch": 7.7,
+      "eval_loss": 0.8098216652870178,
+      "eval_runtime": 1.2656,
+      "eval_samples_per_second": 790.131,
+      "eval_steps_per_second": 12.642,
+      "step": 302000
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 0.00011708540856169612,
+      "loss": 0.2816,
+      "step": 302500
+    },
+    {
+      "epoch": 7.72,
+      "learning_rate": 0.00011662279301694567,
+      "loss": 0.2826,
+      "step": 303000
+    },
+    {
+      "epoch": 7.72,
+      "eval_loss": 0.8181115984916687,
+      "eval_runtime": 1.2294,
+      "eval_samples_per_second": 813.399,
+      "eval_steps_per_second": 13.014,
+      "step": 303000
+    },
+    {
+      "epoch": 7.73,
+      "learning_rate": 0.0001161605971591822,
+      "loss": 0.2817,
+      "step": 303500
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 0.00011569882604290559,
+      "loss": 0.2825,
+      "step": 304000
+    },
+    {
+      "epoch": 7.75,
+      "eval_loss": 0.8146129250526428,
+      "eval_runtime": 1.2431,
+      "eval_samples_per_second": 804.472,
+      "eval_steps_per_second": 12.872,
+      "step": 304000
+    },
+    {
+      "epoch": 7.76,
+      "learning_rate": 0.00011523748471797075,
+      "loss": 0.2816,
+      "step": 304500
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 0.00011477657822953255,
+      "loss": 0.2813,
+      "step": 305000
+    },
+    {
+      "epoch": 7.77,
+      "eval_loss": 0.8215622305870056,
+      "eval_runtime": 1.2616,
+      "eval_samples_per_second": 792.667,
+      "eval_steps_per_second": 12.683,
+      "step": 305000
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 0.00011431611161799043,
+      "loss": 0.2818,
+      "step": 305500
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 0.0001138560899189335,
+      "loss": 0.2814,
+      "step": 306000
+    },
+    {
+      "epoch": 7.8,
+      "eval_loss": 0.8133662343025208,
+      "eval_runtime": 1.3232,
+      "eval_samples_per_second": 755.725,
+      "eval_steps_per_second": 12.092,
+      "step": 306000
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 0.00011339651816308543,
+      "loss": 0.2818,
+      "step": 306500
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 0.00011293740137624925,
+      "loss": 0.2808,
+      "step": 307000
+    },
+    {
+      "epoch": 7.82,
+      "eval_loss": 0.811087429523468,
+      "eval_runtime": 1.3842,
+      "eval_samples_per_second": 722.427,
+      "eval_steps_per_second": 11.559,
+      "step": 307000
+    },
+    {
+      "epoch": 7.84,
+      "learning_rate": 0.00011247874457925261,
+      "loss": 0.281,
+      "step": 307500
+    },
+    {
+      "epoch": 7.85,
+      "learning_rate": 0.0001120205527878927,
+      "loss": 0.2808,
+      "step": 308000
+    },
+    {
+      "epoch": 7.85,
+      "eval_loss": 0.8111096620559692,
+      "eval_runtime": 1.3207,
+      "eval_samples_per_second": 757.185,
+      "eval_steps_per_second": 12.115,
+      "step": 308000
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 0.00011156283101288165,
+      "loss": 0.2813,
+      "step": 308500
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 0.00011110558425979132,
+      "loss": 0.2811,
+      "step": 309000
+    },
+    {
+      "epoch": 7.88,
+      "eval_loss": 0.8077411651611328,
+      "eval_runtime": 1.3568,
+      "eval_samples_per_second": 737.044,
+      "eval_steps_per_second": 11.793,
+      "step": 309000
+    },
+    {
+      "epoch": 7.89,
+      "learning_rate": 0.00011064881752899906,
+      "loss": 0.281,
+      "step": 309500
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 0.00011019253581563262,
+      "loss": 0.2812,
+      "step": 310000
+    },
+    {
+      "epoch": 7.9,
+      "eval_loss": 0.8111229538917542,
+      "eval_runtime": 1.2708,
+      "eval_samples_per_second": 786.914,
+      "eval_steps_per_second": 12.591,
+      "step": 310000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 9.584519810843685e+21,
+  "total_flos": 9.904006949618185e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5e4cc7c8890a029475b21a89ba73ee51bdbf0169ee989a07985e899b417451
+oid sha256:01b2181d9db98eb1abf2e59d3ffca75b8922c4c585b17c4c50bcc63a5ba1af87
 size 102501541