Training in progress, step 210000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1864e8b6d73df803d6169b4a02883f655f8f1f03dba67d279ba50bf4aec8c451
+oid sha256:378ba8062a28aa965b8015e80cac5a7e8c210f8eae62a9b35de790172a138b2c
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7193b0396efbae3c97d694737aabe6c7c60bae54e10275e5280d057220eeba1
+oid sha256:500bbe867ded0d4e115c70f239c6f305c19492ee5158d2b7bb72cd84b524f5aa
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
+oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
+oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
+oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
+oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
+oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
+oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
+oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
+oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e461416c63c82734faef19b4949af829ad430bff342d30400b1c1da0cafb58f
+oid sha256:de6aa60c12b8dbcda06c27a65ac30e45d66753f2960bee09a7c0ea364ae7e103
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.097099750242112,
-  "global_step": 200000,
+  "epoch": 5.351954737754218,
+  "global_step": 210000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4006,11 +4006,211 @@
       "eval_samples_per_second": 756.949,
       "eval_steps_per_second": 12.111,
       "step": 200000
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 0.000212806399860385,
+      "loss": 0.2949,
+      "step": 200500
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 0.00021236633098456196,
+      "loss": 0.2941,
+      "step": 201000
+    },
+    {
+      "epoch": 5.12,
+      "eval_loss": 0.81947922706604,
+      "eval_runtime": 1.576,
+      "eval_samples_per_second": 634.516,
+      "eval_steps_per_second": 10.152,
+      "step": 201000
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 0.0002119256347597342,
+      "loss": 0.295,
+      "step": 201500
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 0.000211484316005285,
+      "loss": 0.2938,
+      "step": 202000
+    },
+    {
+      "epoch": 5.15,
+      "eval_loss": 0.8285008668899536,
+      "eval_runtime": 1.3278,
+      "eval_samples_per_second": 753.153,
+      "eval_steps_per_second": 12.05,
+      "step": 202000
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 0.00021104237954740554,
+      "loss": 0.2936,
+      "step": 202500
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 0.00021059983021904215,
+      "loss": 0.2934,
+      "step": 203000
+    },
+    {
+      "epoch": 5.17,
+      "eval_loss": 0.8159323930740356,
+      "eval_runtime": 1.3067,
+      "eval_samples_per_second": 765.291,
+      "eval_steps_per_second": 12.245,
+      "step": 203000
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 0.00021015667285984336,
+      "loss": 0.2934,
+      "step": 203500
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 0.00020971291231610707,
+      "loss": 0.2932,
+      "step": 204000
+    },
+    {
+      "epoch": 5.2,
+      "eval_loss": 0.8072566986083984,
+      "eval_runtime": 1.4047,
+      "eval_samples_per_second": 711.906,
+      "eval_steps_per_second": 11.39,
+      "step": 204000
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 0.0002092685534407274,
+      "loss": 0.2938,
+      "step": 204500
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 0.00020882360109314197,
+      "loss": 0.2946,
+      "step": 205000
+    },
+    {
+      "epoch": 5.22,
+      "eval_loss": 0.8255318403244019,
+      "eval_runtime": 1.3095,
+      "eval_samples_per_second": 763.663,
+      "eval_steps_per_second": 12.219,
+      "step": 205000
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.0002083780601392783,
+      "loss": 0.293,
+      "step": 205500
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 0.0002079319354515008,
+      "loss": 0.2939,
+      "step": 206000
+    },
+    {
+      "epoch": 5.25,
+      "eval_loss": 0.8249548077583313,
+      "eval_runtime": 1.2456,
+      "eval_samples_per_second": 802.804,
+      "eval_steps_per_second": 12.845,
+      "step": 206000
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 0.00020748523190855772,
+      "loss": 0.2929,
+      "step": 206500
+    },
+    {
+      "epoch": 5.28,
+      "learning_rate": 0.0002070379543955273,
+      "loss": 0.2933,
+      "step": 207000
+    },
+    {
+      "epoch": 5.28,
+      "eval_loss": 0.8215068578720093,
+      "eval_runtime": 1.3095,
+      "eval_samples_per_second": 763.673,
+      "eval_steps_per_second": 12.219,
+      "step": 207000
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 0.00020659010780376487,
+      "loss": 0.2928,
+      "step": 207500
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 0.00020614169703084896,
+      "loss": 0.2927,
+      "step": 208000
+    },
+    {
+      "epoch": 5.3,
+      "eval_loss": 0.8152709007263184,
+      "eval_runtime": 1.2719,
+      "eval_samples_per_second": 786.201,
+      "eval_steps_per_second": 12.579,
+      "step": 208000
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 0.0002056927269805279,
+      "loss": 0.2928,
+      "step": 208500
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 0.00020524320256266635,
+      "loss": 0.2931,
+      "step": 209000
+    },
+    {
+      "epoch": 5.33,
+      "eval_loss": 0.8284364938735962,
+      "eval_runtime": 1.322,
+      "eval_samples_per_second": 756.405,
+      "eval_steps_per_second": 12.102,
+      "step": 209000
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 0.0002047931286931912,
+      "loss": 0.2923,
+      "step": 209500
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 0.00020434251029403824,
+      "loss": 0.2928,
+      "step": 210000
+    },
+    {
+      "epoch": 5.35,
+      "eval_loss": 0.8203576803207397,
+      "eval_runtime": 1.366,
+      "eval_samples_per_second": 732.046,
+      "eval_steps_per_second": 11.713,
+      "step": 210000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 6.389675380924775e+21,
+  "total_flos": 6.709162519699275e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7193b0396efbae3c97d694737aabe6c7c60bae54e10275e5280d057220eeba1
+oid sha256:500bbe867ded0d4e115c70f239c6f305c19492ee5158d2b7bb72cd84b524f5aa
 size 102501541