Training in progress, step 150000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcab0d8867b5b850ae68e36d8ef2c70a5dbfa9a4b065a13a6b362e3397cf3fe2
+oid sha256:23bcf588931894b4b3e5c35722962c0de8f54f9d9596c1f09a2a4e5a7a2d9f29
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f41bd458cd3584fbcfdfac193494afb86160004f3f15f4d7c8df5b7ded36762
+oid sha256:80d9dd260c6a1eea214a50fb35a68c126c97cfb31dd7f81eeaee885739a9a21c
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
+oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
+oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
+oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
+oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
+oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
+oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
+oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52dddb37e26c52f49ab4dce6c56c4f27359125886e16875691cfe50bcc29ef0
+oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed68d92642b5c57649c135331b8243d8047b1dee7f4eb5f6f68f9dc4d2f32821
+oid sha256:684030441e546f328363202be7e7a1e6d60b5494506eab9e81487ca712343e2e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.245538900785154,
-  "global_step": 140000,
+  "epoch": 6.691648822269808,
+  "global_step": 150000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2806,11 +2806,211 @@
       "eval_samples_per_second": 1031.628,
       "eval_steps_per_second": 16.168,
       "step": 140000
+    },
+    {
+      "epoch": 6.27,
+      "learning_rate": 0.00026899475121297924,
+      "loss": 0.3815,
+      "step": 140500
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.00026705904531820914,
+      "loss": 0.3815,
+      "step": 141000
+    },
+    {
+      "epoch": 6.29,
+      "eval_loss": 0.3550131618976593,
+      "eval_runtime": 2.1731,
+      "eval_samples_per_second": 1057.017,
+      "eval_steps_per_second": 16.566,
+      "step": 141000
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 0.0002651249990837085,
+      "loss": 0.3813,
+      "step": 141500
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00026319269711092485,
+      "loss": 0.3812,
+      "step": 142000
+    },
+    {
+      "epoch": 6.33,
+      "eval_loss": 0.3538789749145508,
+      "eval_runtime": 2.1483,
+      "eval_samples_per_second": 1069.198,
+      "eval_steps_per_second": 16.757,
+      "step": 142000
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 0.0002612622239250066,
+      "loss": 0.3809,
+      "step": 142500
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 0.0002593336639711046,
+      "loss": 0.3806,
+      "step": 143000
+    },
+    {
+      "epoch": 6.38,
+      "eval_loss": 0.35349225997924805,
+      "eval_runtime": 2.1799,
+      "eval_samples_per_second": 1053.718,
+      "eval_steps_per_second": 16.515,
+      "step": 143000
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 0.000257407101610679,
+      "loss": 0.3805,
+      "step": 143500
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 0.00025548262111780846,
+      "loss": 0.3804,
+      "step": 144000
+    },
+    {
+      "epoch": 6.42,
+      "eval_loss": 0.3532736003398895,
+      "eval_runtime": 2.2355,
+      "eval_samples_per_second": 1027.515,
+      "eval_steps_per_second": 16.104,
+      "step": 144000
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 0.0002535603066755043,
+      "loss": 0.3803,
+      "step": 144500
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 0.00025164024237202764,
+      "loss": 0.3799,
+      "step": 145000
+    },
+    {
+      "epoch": 6.47,
+      "eval_loss": 0.3539290130138397,
+      "eval_runtime": 2.1927,
+      "eval_samples_per_second": 1047.568,
+      "eval_steps_per_second": 16.418,
+      "step": 145000
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 0.00024972251219721115,
+      "loss": 0.38,
+      "step": 145500
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 0.00024780720003878557,
+      "loss": 0.3799,
+      "step": 146000
+    },
+    {
+      "epoch": 6.51,
+      "eval_loss": 0.3527817726135254,
+      "eval_runtime": 2.1772,
+      "eval_samples_per_second": 1055.009,
+      "eval_steps_per_second": 16.535,
+      "step": 146000
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 0.00024589438967870925,
+      "loss": 0.3795,
+      "step": 146500
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 0.00024398416478950394,
+      "loss": 0.3794,
+      "step": 147000
+    },
+    {
+      "epoch": 6.56,
+      "eval_loss": 0.3519304692745209,
+      "eval_runtime": 2.1956,
+      "eval_samples_per_second": 1046.2,
+      "eval_steps_per_second": 16.397,
+      "step": 147000
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 0.00024207660893059467,
+      "loss": 0.3793,
+      "step": 147500
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 0.0002401718055446543,
+      "loss": 0.3792,
+      "step": 148000
+    },
+    {
+      "epoch": 6.6,
+      "eval_loss": 0.3501195013523102,
+      "eval_runtime": 2.1687,
+      "eval_samples_per_second": 1059.172,
+      "eval_steps_per_second": 16.6,
+      "step": 148000
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 0.00023826983795395364,
+      "loss": 0.379,
+      "step": 148500
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 0.00023637078935671656,
+      "loss": 0.3791,
+      "step": 149000
+    },
+    {
+      "epoch": 6.65,
+      "eval_loss": 0.35130566358566284,
+      "eval_runtime": 2.1713,
+      "eval_samples_per_second": 1057.877,
+      "eval_steps_per_second": 16.58,
+      "step": 149000
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 0.00023447474282348085,
+      "loss": 0.3787,
+      "step": 149500
+    },
+    {
+      "epoch": 6.69,
+      "learning_rate": 0.00023258178129346424,
+      "loss": 0.3784,
+      "step": 150000
+    },
+    {
+      "epoch": 6.69,
+      "eval_loss": 0.35110124945640564,
+      "eval_runtime": 2.1647,
+      "eval_samples_per_second": 1061.094,
+      "eval_steps_per_second": 16.63,
+      "step": 150000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 2.2423092482282158e+21,
+  "total_flos": 2.40247725109402e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f41bd458cd3584fbcfdfac193494afb86160004f3f15f4d7c8df5b7ded36762
+oid sha256:80d9dd260c6a1eea214a50fb35a68c126c97cfb31dd7f81eeaee885739a9a21c
 size 25761253