Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd33a1577954e215c8437e7980add2f5f9574d602de488a6b0720d3ad4458fca
+oid sha256:aeed81ff957b2db542c361adc3c37054999526f67b2fdd08124045a7a9910110
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a460f3fbdd157653313f970d730a974ff0dafa62f6d47ebc7be418c29489b80d
+oid sha256:2a1e1eb146f1c0d6bafed7b37d2555b3cf3a9a1cec24e6e7b6230f23f01cccd4
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
+oid sha256:fb751814ba6ecdcd5c1c820cf948dc125ec28136a0f7891aedc4ea8d19c01bac
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
+oid sha256:fb751814ba6ecdcd5c1c820cf948dc125ec28136a0f7891aedc4ea8d19c01bac
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
+oid sha256:fb751814ba6ecdcd5c1c820cf948dc125ec28136a0f7891aedc4ea8d19c01bac
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
+oid sha256:fb751814ba6ecdcd5c1c820cf948dc125ec28136a0f7891aedc4ea8d19c01bac
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
+oid sha256:fb751814ba6ecdcd5c1c820cf948dc125ec28136a0f7891aedc4ea8d19c01bac
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
+oid sha256:fb751814ba6ecdcd5c1c820cf948dc125ec28136a0f7891aedc4ea8d19c01bac
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
+oid sha256:fb751814ba6ecdcd5c1c820cf948dc125ec28136a0f7891aedc4ea8d19c01bac
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e960d152fa8a2009412029824cd0038b06b011605abe65cb9b329a00e7e113e2
+oid sha256:fb751814ba6ecdcd5c1c820cf948dc125ec28136a0f7891aedc4ea8d19c01bac
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0439027dd6f55adc764cb1317d963df8ccf36442066dafecce10b3f538efa8e
+oid sha256:6e461416c63c82734faef19b4949af829ad430bff342d30400b1c1da0cafb58f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.426943777814022,
-  "global_step": 190000,
+  "epoch": 4.659940818751602,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3806,11 +3806,211 @@
       "eval_samples_per_second": 1514.384,
       "eval_steps_per_second": 24.114,
       "step": 190000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 0.00022146867474920118,
+      "loss": 0.2828,
+      "step": 190500
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 0.00022104215397571484,
+      "loss": 0.281,
+      "step": 191000
+    },
+    {
+      "epoch": 4.45,
+      "eval_loss": 0.2647937834262848,
+      "eval_runtime": 1.4216,
+      "eval_samples_per_second": 1546.121,
+      "eval_steps_per_second": 24.62,
+      "step": 191000
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.0002206149109758135,
+      "loss": 0.2816,
+      "step": 191500
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 0.00022018695042175818,
+      "loss": 0.2812,
+      "step": 192000
+    },
+    {
+      "epoch": 4.47,
+      "eval_loss": 0.2635156512260437,
+      "eval_runtime": 1.4081,
+      "eval_samples_per_second": 1560.959,
+      "eval_steps_per_second": 24.856,
+      "step": 192000
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 0.00021975827699365693,
+      "loss": 0.2807,
+      "step": 192500
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.00021932889537941365,
+      "loss": 0.2809,
+      "step": 193000
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 0.2628609240055084,
+      "eval_runtime": 1.4036,
+      "eval_samples_per_second": 1565.967,
+      "eval_steps_per_second": 24.936,
+      "step": 193000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 0.0002188988102746769,
+      "loss": 0.2806,
+      "step": 193500
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 0.0002184680263827885,
+      "loss": 0.2809,
+      "step": 194000
+    },
+    {
+      "epoch": 4.52,
+      "eval_loss": 0.26426324248313904,
+      "eval_runtime": 1.4613,
+      "eval_samples_per_second": 1504.163,
+      "eval_steps_per_second": 23.952,
+      "step": 194000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 0.00021803654841473204,
+      "loss": 0.2805,
+      "step": 194500
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 0.00021760438108908142,
+      "loss": 0.2805,
+      "step": 195000
+    },
+    {
+      "epoch": 4.54,
+      "eval_loss": 0.2624601125717163,
+      "eval_runtime": 1.4471,
+      "eval_samples_per_second": 1518.947,
+      "eval_steps_per_second": 24.187,
+      "step": 195000
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 0.0002171715291319494,
+      "loss": 0.2809,
+      "step": 195500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 0.0002167379972769355,
+      "loss": 0.2806,
+      "step": 196000
+    },
+    {
+      "epoch": 4.57,
+      "eval_loss": 0.26392462849617004,
+      "eval_runtime": 1.3978,
+      "eval_samples_per_second": 1572.46,
+      "eval_steps_per_second": 25.039,
+      "step": 196000
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 0.0002163037902650747,
+      "loss": 0.2801,
+      "step": 196500
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 0.0002158689128447853,
+      "loss": 0.2805,
+      "step": 197000
+    },
+    {
+      "epoch": 4.59,
+      "eval_loss": 0.262777715921402,
+      "eval_runtime": 1.4828,
+      "eval_samples_per_second": 1482.293,
+      "eval_steps_per_second": 23.603,
+      "step": 197000
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 0.00021543336977181704,
+      "loss": 0.2805,
+      "step": 197500
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 0.00021499716580919933,
+      "loss": 0.2799,
+      "step": 198000
+    },
+    {
+      "epoch": 4.61,
+      "eval_loss": 0.26294538378715515,
+      "eval_runtime": 1.4108,
+      "eval_samples_per_second": 1557.962,
+      "eval_steps_per_second": 24.808,
+      "step": 198000
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 0.00021456030572718866,
+      "loss": 0.2797,
+      "step": 198500
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 0.000214122794303217,
+      "loss": 0.2802,
+      "step": 199000
+    },
+    {
+      "epoch": 4.64,
+      "eval_loss": 0.2624069154262543,
+      "eval_runtime": 1.4063,
+      "eval_samples_per_second": 1562.932,
+      "eval_steps_per_second": 24.887,
+      "step": 199000
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 0.00021368463632183912,
+      "loss": 0.2799,
+      "step": 199500
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 0.00021324583657468055,
+      "loss": 0.2799,
+      "step": 200000
+    },
+    {
+      "epoch": 4.66,
+      "eval_loss": 0.2646183967590332,
+      "eval_runtime": 1.4232,
+      "eval_samples_per_second": 1544.399,
+      "eval_steps_per_second": 24.592,
+      "step": 200000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 6.070245648751873e+21,
+  "total_flos": 6.389732787526373e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a460f3fbdd157653313f970d730a974ff0dafa62f6d47ebc7be418c29489b80d
+oid sha256:2a1e1eb146f1c0d6bafed7b37d2555b3cf3a9a1cec24e6e7b6230f23f01cccd4
 size 102501541