Training in progress, step 390000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241d9085c124b3eba48c530116f68f59d85b2df3443facaec6ea11dc49d55a64
+oid sha256:d1df67f6183cc09f42fe2f0f37f8357c9b8e65f61395be8418801628a4f2e406
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4bc41779e2d6304b9419d2772739a130d22e86fd6c9f3afbd2e0c3ee5419e4
+oid sha256:a319b7f2b744152a6d0b7c7b011dcbab2f50e31847aad07fbf0452468b5c5506
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e37ec2ad84f7ba85cc772e99cb8545a4cbfaa7381a41ddd4a3aa91e0ce61e68
+oid sha256:2b801257833dcb303ed75576841dd61289770bb2e540d74ef6ab937039253da2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85519fa51d75acbbb3048d7882484da3d5005c19c2db1456cbcb7c7e288fefdc
-size 14439
+oid sha256:b6243d1d6e37c5feee8bc48e8b6c7c5cd2d209aa34c8943a605523b56be5d5e4
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb0afece5c8069cc11f1d74f2cbe0cc7ca51acd29eabfe984c5004653b66638
-size 14439
+oid sha256:1abc03aa32f692919d10687fb19b346a26a86c47bfcdc5586f5937683d9a753d
+size 14567

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7a8a69ea84c76c1ba62360211ec1aee5a43eb5be6b28be19dd35082fc0f872
-size 14503
+oid sha256:05b257bebecd01fe3120913d4e730e44697707b0fb5a5618a441dd1149c501fa
+size 14439

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9dfd822ea158ad304a36506ae43c2b1a7adf656df5c9032384a0d9d826989e
+oid sha256:593b188cbaecd147825c6ab6a7428985fef9dedd306035b01be6e3046807b5ca
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd61e923aa53357f018bb8f972acd03e5e22cec973afb7a44242ee37ecdd9eac
+oid sha256:ab242969f427542b52610398ae9f7ae92f28c7f51c41a80b11d327fe5508415b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:358496c77d19a4e645872ac224e8695ee5602a8fd7b41e2a32b9cf0a419156c8
+oid sha256:d23f4669a6b401e22fd0094f76b78d30e5af5448c611b04bb84563f4723f22b5
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a344adc4e56950e93eda7f993a6791867b71bbebf0dede9e3e7fb6302a4626eb
+oid sha256:c94a5e21ff6cb02edd9d7611a60f73f17f810262fe1570be2488fda0b577fd53
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2047b5f47fc3de929bb0738f7fbdd248300ab063f6fd4eddcabc29f5482852
+oid sha256:864647684ab3694f7aa2a258c1806e10c4abf99f67ed5e54443050e485ac9436
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.642513557400656,
-  "global_step": 380000,
+  "epoch": 11.948895493121725,
+  "global_step": 390000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7606,11 +7606,211 @@
       "eval_samples_per_second": 1953.621,
       "eval_steps_per_second": 31.258,
       "step": 380000
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 5.2979369233306834e-05,
+      "loss": 0.3201,
+      "step": 380500
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 5.26391878673975e-05,
+      "loss": 0.32,
+      "step": 381000
+    },
+    {
+      "epoch": 11.67,
+      "eval_loss": 0.7779923677444458,
+      "eval_runtime": 0.495,
+      "eval_samples_per_second": 2020.075,
+      "eval_steps_per_second": 32.321,
+      "step": 381000
+    },
+    {
+      "epoch": 11.69,
+      "learning_rate": 5.230012590292987e-05,
+      "loss": 0.3199,
+      "step": 381500
+    },
+    {
+      "epoch": 11.7,
+      "learning_rate": 5.1962187047831517e-05,
+      "loss": 0.32,
+      "step": 382000
+    },
+    {
+      "epoch": 11.7,
+      "eval_loss": 0.7783936858177185,
+      "eval_runtime": 0.517,
+      "eval_samples_per_second": 1934.07,
+      "eval_steps_per_second": 30.945,
+      "step": 382000
+    },
+    {
+      "epoch": 11.72,
+      "learning_rate": 5.162537499774743e-05,
+      "loss": 0.3201,
+      "step": 382500
+    },
+    {
+      "epoch": 11.73,
+      "learning_rate": 5.128969343600032e-05,
+      "loss": 0.32,
+      "step": 383000
+    },
+    {
+      "epoch": 11.73,
+      "eval_loss": 0.7770859599113464,
+      "eval_runtime": 0.5158,
+      "eval_samples_per_second": 1938.792,
+      "eval_steps_per_second": 31.021,
+      "step": 383000
+    },
+    {
+      "epoch": 11.75,
+      "learning_rate": 5.09551460335499e-05,
+      "loss": 0.3199,
+      "step": 383500
+    },
+    {
+      "epoch": 11.77,
+      "learning_rate": 5.062173644895296e-05,
+      "loss": 0.3199,
+      "step": 384000
+    },
+    {
+      "epoch": 11.77,
+      "eval_loss": 0.7772809863090515,
+      "eval_runtime": 0.526,
+      "eval_samples_per_second": 1901.052,
+      "eval_steps_per_second": 30.417,
+      "step": 384000
+    },
+    {
+      "epoch": 11.78,
+      "learning_rate": 5.0289468328323434e-05,
+      "loss": 0.32,
+      "step": 384500
+    },
+    {
+      "epoch": 11.8,
+      "learning_rate": 4.995834530529208e-05,
+      "loss": 0.3198,
+      "step": 385000
+    },
+    {
+      "epoch": 11.8,
+      "eval_loss": 0.7799978852272034,
+      "eval_runtime": 0.5198,
+      "eval_samples_per_second": 1923.762,
+      "eval_steps_per_second": 30.78,
+      "step": 385000
+    },
+    {
+      "epoch": 11.81,
+      "learning_rate": 4.9628371000967394e-05,
+      "loss": 0.3198,
+      "step": 385500
+    },
+    {
+      "epoch": 11.83,
+      "learning_rate": 4.929954902389534e-05,
+      "loss": 0.3196,
+      "step": 386000
+    },
+    {
+      "epoch": 11.83,
+      "eval_loss": 0.7772753834724426,
+      "eval_runtime": 0.5182,
+      "eval_samples_per_second": 1929.679,
+      "eval_steps_per_second": 30.875,
+      "step": 386000
+    },
+    {
+      "epoch": 11.84,
+      "learning_rate": 4.897188297002046e-05,
+      "loss": 0.3194,
+      "step": 386500
+    },
+    {
+      "epoch": 11.86,
+      "learning_rate": 4.8645376422646226e-05,
+      "loss": 0.3194,
+      "step": 387000
+    },
+    {
+      "epoch": 11.86,
+      "eval_loss": 0.7773513197898865,
+      "eval_runtime": 0.5104,
+      "eval_samples_per_second": 1959.206,
+      "eval_steps_per_second": 31.347,
+      "step": 387000
+    },
+    {
+      "epoch": 11.87,
+      "learning_rate": 4.832003295239591e-05,
+      "loss": 0.3194,
+      "step": 387500
+    },
+    {
+      "epoch": 11.89,
+      "learning_rate": 4.7995856117173624e-05,
+      "loss": 0.3198,
+      "step": 388000
+    },
+    {
+      "epoch": 11.89,
+      "eval_loss": 0.7708141803741455,
+      "eval_runtime": 0.5167,
+      "eval_samples_per_second": 1935.457,
+      "eval_steps_per_second": 30.967,
+      "step": 388000
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 4.767284946212521e-05,
+      "loss": 0.3192,
+      "step": 388500
+    },
+    {
+      "epoch": 11.92,
+      "learning_rate": 4.735101651959977e-05,
+      "loss": 0.3191,
+      "step": 389000
+    },
+    {
+      "epoch": 11.92,
+      "eval_loss": 0.7765528559684753,
+      "eval_runtime": 0.5105,
+      "eval_samples_per_second": 1958.826,
+      "eval_steps_per_second": 31.341,
+      "step": 389000
+    },
+    {
+      "epoch": 11.93,
+      "learning_rate": 4.7030360809110754e-05,
+      "loss": 0.3195,
+      "step": 389500
+    },
+    {
+      "epoch": 11.95,
+      "learning_rate": 4.6710885837297726e-05,
+      "loss": 0.3193,
+      "step": 390000
+    },
+    {
+      "epoch": 11.95,
+      "eval_loss": 0.7797139883041382,
+      "eval_runtime": 0.5113,
+      "eval_samples_per_second": 1955.764,
+      "eval_steps_per_second": 31.292,
+      "step": 390000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.2140423405959266e+22,
+  "total_flos": 1.2459910544733766e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4bc41779e2d6304b9419d2772739a130d22e86fd6c9f3afbd2e0c3ee5419e4
+oid sha256:a319b7f2b744152a6d0b7c7b011dcbab2f50e31847aad07fbf0452468b5c5506
 size 102501541