Training in progress, step 220000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:378ba8062a28aa965b8015e80cac5a7e8c210f8eae62a9b35de790172a138b2c
+oid sha256:62c0ec040ee2456e61ab40311e486f10de42e153791678bf443f54fc8893f828
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:500bbe867ded0d4e115c70f239c6f305c19492ee5158d2b7bb72cd84b524f5aa
+oid sha256:027aff93cad77a00849e3e1032a09ce43e2d9d45511b5e4cbbe8559338ed73ad
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
+oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
+oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
+oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
+oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
+oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
+oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
+oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
+oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6aa60c12b8dbcda06c27a65ac30e45d66753f2960bee09a7c0ea364ae7e103
+oid sha256:a05d01a7b2f868e6f0e645a01ef2a1ba3ad5ea16b1bff8e9cf0cf653b106d64f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.351954737754218,
-  "global_step": 210000,
+  "epoch": 5.606809725266324,
+  "global_step": 220000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4206,11 +4206,211 @@
       "eval_samples_per_second": 732.046,
       "eval_steps_per_second": 11.713,
       "step": 210000
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 0.00020389135229309803,
+      "loss": 0.2923,
+      "step": 210500
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 0.00020343965962416229,
+      "loss": 0.2923,
+      "step": 211000
+    },
+    {
+      "epoch": 5.38,
+      "eval_loss": 0.8264955878257751,
+      "eval_runtime": 1.329,
+      "eval_samples_per_second": 752.449,
+      "eval_steps_per_second": 12.039,
+      "step": 211000
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 0.00020298743722686958,
+      "loss": 0.2922,
+      "step": 211500
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 0.0002025346900466516,
+      "loss": 0.2925,
+      "step": 212000
+    },
+    {
+      "epoch": 5.4,
+      "eval_loss": 0.826949954032898,
+      "eval_runtime": 1.2977,
+      "eval_samples_per_second": 770.59,
+      "eval_steps_per_second": 12.329,
+      "step": 212000
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 0.0002020814230346791,
+      "loss": 0.2932,
+      "step": 212500
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 0.00020162764114780733,
+      "loss": 0.2926,
+      "step": 213000
+    },
+    {
+      "epoch": 5.43,
+      "eval_loss": 0.8337197303771973,
+      "eval_runtime": 1.293,
+      "eval_samples_per_second": 773.389,
+      "eval_steps_per_second": 12.374,
+      "step": 213000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 0.0002011733493485224,
+      "loss": 0.2923,
+      "step": 213500
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 0.00020071855260488664,
+      "loss": 0.292,
+      "step": 214000
+    },
+    {
+      "epoch": 5.45,
+      "eval_loss": 0.8254857063293457,
+      "eval_runtime": 1.2323,
+      "eval_samples_per_second": 811.466,
+      "eval_steps_per_second": 12.983,
+      "step": 214000
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 0.0002002632558904843,
+      "loss": 0.2919,
+      "step": 214500
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 0.00019980746418436736,
+      "loss": 0.292,
+      "step": 215000
+    },
+    {
+      "epoch": 5.48,
+      "eval_loss": 0.8224061131477356,
+      "eval_runtime": 1.2655,
+      "eval_samples_per_second": 790.229,
+      "eval_steps_per_second": 12.644,
+      "step": 215000
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 0.00019935118247100088,
+      "loss": 0.2919,
+      "step": 215500
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.00019889441574020864,
+      "loss": 0.2915,
+      "step": 216000
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.8216863870620728,
+      "eval_runtime": 1.2862,
+      "eval_samples_per_second": 777.468,
+      "eval_steps_per_second": 12.439,
+      "step": 216000
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 0.0001984371689871183,
+      "loss": 0.2918,
+      "step": 216500
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 0.00019797944721210725,
+      "loss": 0.2916,
+      "step": 217000
+    },
+    {
+      "epoch": 5.53,
+      "eval_loss": 0.8251473307609558,
+      "eval_runtime": 1.3615,
+      "eval_samples_per_second": 734.51,
+      "eval_steps_per_second": 11.752,
+      "step": 217000
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 0.00019752125542074736,
+      "loss": 0.2913,
+      "step": 217500
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 0.00019706259862375074,
+      "loss": 0.291,
+      "step": 218000
+    },
+    {
+      "epoch": 5.56,
+      "eval_loss": 0.8243631720542908,
+      "eval_runtime": 1.2451,
+      "eval_samples_per_second": 803.116,
+      "eval_steps_per_second": 12.85,
+      "step": 218000
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 0.00019660348183691453,
+      "loss": 0.292,
+      "step": 218500
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 0.0001961439100810664,
+      "loss": 0.2918,
+      "step": 219000
+    },
+    {
+      "epoch": 5.58,
+      "eval_loss": 0.8229220509529114,
+      "eval_runtime": 1.3199,
+      "eval_samples_per_second": 757.608,
+      "eval_steps_per_second": 12.122,
+      "step": 219000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 0.00019568388838200952,
+      "loss": 0.2916,
+      "step": 219500
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 0.00019522342177046744,
+      "loss": 0.2911,
+      "step": 220000
+    },
+    {
+      "epoch": 5.61,
+      "eval_loss": 0.824487566947937,
+      "eval_runtime": 1.2486,
+      "eval_samples_per_second": 800.922,
+      "eval_steps_per_second": 12.815,
+      "step": 220000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 6.709162519699275e+21,
+  "total_flos": 7.028649658473775e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:500bbe867ded0d4e115c70f239c6f305c19492ee5158d2b7bb72cd84b524f5aa
+oid sha256:027aff93cad77a00849e3e1032a09ce43e2d9d45511b5e4cbbe8559338ed73ad
 size 102501541