Training in progress, step 140000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9dcc4ff2bc74ab69f0263634058bb8fb9cc796ba30099ac6af07a524413216
+oid sha256:dcab0d8867b5b850ae68e36d8ef2c70a5dbfa9a4b065a13a6b362e3397cf3fe2
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77770474995765e28cd3f772259c3b9f70956913fcf88d26cfbea63dec9f29f8
+oid sha256:5f41bd458cd3584fbcfdfac193494afb86160004f3f15f4d7c8df5b7ded36762
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3017ce4acc395c8911d9ef1e39e206b06d5a44dba6f5be7a0a365fda3aceface
+oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3017ce4acc395c8911d9ef1e39e206b06d5a44dba6f5be7a0a365fda3aceface
+oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3017ce4acc395c8911d9ef1e39e206b06d5a44dba6f5be7a0a365fda3aceface
+oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3017ce4acc395c8911d9ef1e39e206b06d5a44dba6f5be7a0a365fda3aceface
+oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3017ce4acc395c8911d9ef1e39e206b06d5a44dba6f5be7a0a365fda3aceface
+oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3017ce4acc395c8911d9ef1e39e206b06d5a44dba6f5be7a0a365fda3aceface
+oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3017ce4acc395c8911d9ef1e39e206b06d5a44dba6f5be7a0a365fda3aceface
+oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3017ce4acc395c8911d9ef1e39e206b06d5a44dba6f5be7a0a365fda3aceface
+oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa61e63d6ec853afa02e48d5167bab30a383bd9f05f192b20c686fb9a3478097
+oid sha256:ed68d92642b5c57649c135331b8243d8047b1dee7f4eb5f6f68f9dc4d2f32821
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.799428979300499,
-  "global_step": 130000,
+  "epoch": 6.245538900785154,
+  "global_step": 140000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2606,11 +2606,211 @@
       "eval_samples_per_second": 1064.4,
       "eval_steps_per_second": 16.682,
       "step": 130000
+    },
+    {
+      "epoch": 5.82,
+      "learning_rate": 0.00030792659356955893,
+      "loss": 0.3853,
+      "step": 130500
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 0.0003059755454143586,
+      "loss": 0.3849,
+      "step": 131000
+    },
+    {
+      "epoch": 5.84,
+      "eval_loss": 0.3566107451915741,
+      "eval_runtime": 2.2772,
+      "eval_samples_per_second": 1008.7,
+      "eval_steps_per_second": 15.809,
+      "step": 131000
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 0.00030402445458564144,
+      "loss": 0.3845,
+      "step": 131500
+    },
+    {
+      "epoch": 5.89,
+      "learning_rate": 0.0003020734064304411,
+      "loss": 0.3845,
+      "step": 132000
+    },
+    {
+      "epoch": 5.89,
+      "eval_loss": 0.35691574215888977,
+      "eval_runtime": 2.2557,
+      "eval_samples_per_second": 1018.294,
+      "eval_steps_per_second": 15.959,
+      "step": 132000
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 0.00030012248629392423,
+      "loss": 0.3842,
+      "step": 132500
+    },
+    {
+      "epoch": 5.93,
+      "learning_rate": 0.00029817177951565793,
+      "loss": 0.384,
+      "step": 133000
+    },
+    {
+      "epoch": 5.93,
+      "eval_loss": 0.35665038228034973,
+      "eval_runtime": 2.2062,
+      "eval_samples_per_second": 1041.164,
+      "eval_steps_per_second": 16.318,
+      "step": 133000
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 0.00029622137142587594,
+      "loss": 0.3837,
+      "step": 133500
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 0.0002942713473417466,
+      "loss": 0.3921,
+      "step": 134000
+    },
+    {
+      "epoch": 5.98,
+      "eval_loss": 0.3628464341163635,
+      "eval_runtime": 2.2578,
+      "eval_samples_per_second": 1017.356,
+      "eval_steps_per_second": 15.945,
+      "step": 134000
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00029232179256364054,
+      "loss": 0.3854,
+      "step": 134500
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 0.0002903727923713994,
+      "loss": 0.3844,
+      "step": 135000
+    },
+    {
+      "epoch": 6.02,
+      "eval_loss": 0.3565491735935211,
+      "eval_runtime": 2.2392,
+      "eval_samples_per_second": 1025.813,
+      "eval_steps_per_second": 16.077,
+      "step": 135000
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 0.00028842443202060556,
+      "loss": 0.383,
+      "step": 135500
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00028647679673885255,
+      "loss": 0.383,
+      "step": 136000
+    },
+    {
+      "epoch": 6.07,
+      "eval_loss": 0.35466697812080383,
+      "eval_runtime": 2.2168,
+      "eval_samples_per_second": 1036.2,
+      "eval_steps_per_second": 16.24,
+      "step": 136000
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 0.000284529971722017,
+      "loss": 0.3829,
+      "step": 136500
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 0.0002825840421305321,
+      "loss": 0.3828,
+      "step": 137000
+    },
+    {
+      "epoch": 6.11,
+      "eval_loss": 0.3585571050643921,
+      "eval_runtime": 2.2164,
+      "eval_samples_per_second": 1036.381,
+      "eval_steps_per_second": 16.243,
+      "step": 137000
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 0.00028063909308566196,
+      "loss": 0.3826,
+      "step": 137500
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 0.00027869520966577874,
+      "loss": 0.3824,
+      "step": 138000
+    },
+    {
+      "epoch": 6.16,
+      "eval_loss": 0.35530510544776917,
+      "eval_runtime": 2.2219,
+      "eval_samples_per_second": 1033.801,
+      "eval_steps_per_second": 16.202,
+      "step": 138000
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 0.00027675247690264027,
+      "loss": 0.3823,
+      "step": 138500
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 0.0002748109797776715,
+      "loss": 0.3825,
+      "step": 139000
+    },
+    {
+      "epoch": 6.2,
+      "eval_loss": 0.3549206256866455,
+      "eval_runtime": 2.1769,
+      "eval_samples_per_second": 1055.166,
+      "eval_steps_per_second": 16.537,
+      "step": 139000
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 0.0002728708032182461,
+      "loss": 0.382,
+      "step": 139500
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 0.0002709320320939721,
+      "loss": 0.3818,
+      "step": 140000
+    },
+    {
+      "epoch": 6.25,
+      "eval_loss": 0.3537048399448395,
+      "eval_runtime": 2.2266,
+      "eval_samples_per_second": 1031.628,
+      "eval_steps_per_second": 16.168,
+      "step": 140000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 2.0821483773445852e+21,
+  "total_flos": 2.2423092482282158e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77770474995765e28cd3f772259c3b9f70956913fcf88d26cfbea63dec9f29f8
+oid sha256:5f41bd458cd3584fbcfdfac193494afb86160004f3f15f4d7c8df5b7ded36762
 size 25761253