Training in progress, step 160000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23bcf588931894b4b3e5c35722962c0de8f54f9d9596c1f09a2a4e5a7a2d9f29
+oid sha256:46bff3dba845cd7e7f19ae9dbbe463bda3e2fa6806365056b512226d84f8fe42
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d9dd260c6a1eea214a50fb35a68c126c97cfb31dd7f81eeaee885739a9a21c
+oid sha256:8fd59d7cfb5049e46570c40bfa98b1ab6951678f21e1e8ee02bf24082eee2565
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
+oid sha256:dd053fb6d27885aadc27c02a534d4a05640e7e350d6bb076a775c2584889f6ac
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
+oid sha256:dd053fb6d27885aadc27c02a534d4a05640e7e350d6bb076a775c2584889f6ac
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
+oid sha256:dd053fb6d27885aadc27c02a534d4a05640e7e350d6bb076a775c2584889f6ac
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
+oid sha256:dd053fb6d27885aadc27c02a534d4a05640e7e350d6bb076a775c2584889f6ac
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
+oid sha256:dd053fb6d27885aadc27c02a534d4a05640e7e350d6bb076a775c2584889f6ac
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
+oid sha256:dd053fb6d27885aadc27c02a534d4a05640e7e350d6bb076a775c2584889f6ac
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
+oid sha256:dd053fb6d27885aadc27c02a534d4a05640e7e350d6bb076a775c2584889f6ac
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
+oid sha256:dd053fb6d27885aadc27c02a534d4a05640e7e350d6bb076a775c2584889f6ac
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684030441e546f328363202be7e7a1e6d60b5494506eab9e81487ca712343e2e
+oid sha256:dc071f88617eb6afe60581ffbadbc2441a73aeec527e5556ce742e0646660ab9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.691648822269808,
-  "global_step": 150000,
+  "epoch": 7.137758743754461,
+  "global_step": 160000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3006,11 +3006,211 @@
       "eval_samples_per_second": 1061.094,
       "eval_steps_per_second": 16.63,
       "step": 150000
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 0.00023069198757093631,
+      "loss": 0.379,
+      "step": 150500
+    },
+    {
+      "epoch": 6.74,
+      "learning_rate": 0.00022880544432159663,
+      "loss": 0.3833,
+      "step": 151000
+    },
+    {
+      "epoch": 6.74,
+      "eval_loss": 0.3517898917198181,
+      "eval_runtime": 2.2,
+      "eval_samples_per_second": 1044.076,
+      "eval_steps_per_second": 16.363,
+      "step": 151000
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 0.00022692223406895848,
+      "loss": 0.3782,
+      "step": 151500
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 0.000225042439190739,
+      "loss": 0.3805,
+      "step": 152000
+    },
+    {
+      "epoch": 6.78,
+      "eval_loss": 0.35134270787239075,
+      "eval_runtime": 2.2005,
+      "eval_samples_per_second": 1043.87,
+      "eval_steps_per_second": 16.36,
+      "step": 152000
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 0.00022316614191525587,
+      "loss": 0.3788,
+      "step": 152500
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 0.00022129342431783026,
+      "loss": 0.3785,
+      "step": 153000
+    },
+    {
+      "epoch": 6.83,
+      "eval_loss": 0.35215121507644653,
+      "eval_runtime": 2.2421,
+      "eval_samples_per_second": 1024.496,
+      "eval_steps_per_second": 16.057,
+      "step": 153000
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 0.00021942436831719677,
+      "loss": 0.3776,
+      "step": 153500
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 0.00021755905567191967,
+      "loss": 0.3772,
+      "step": 154000
+    },
+    {
+      "epoch": 6.87,
+      "eval_loss": 0.34930697083473206,
+      "eval_runtime": 2.254,
+      "eval_samples_per_second": 1019.092,
+      "eval_steps_per_second": 15.972,
+      "step": 154000
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 0.00021569756797681686,
+      "loss": 0.3775,
+      "step": 154500
+    },
+    {
+      "epoch": 6.91,
+      "learning_rate": 0.00021383998665939054,
+      "loss": 0.3772,
+      "step": 155000
+    },
+    {
+      "epoch": 6.91,
+      "eval_loss": 0.35032403469085693,
+      "eval_runtime": 2.2005,
+      "eval_samples_per_second": 1043.877,
+      "eval_steps_per_second": 16.36,
+      "step": 155000
+    },
+    {
+      "epoch": 6.94,
+      "learning_rate": 0.00021198639297626516,
+      "loss": 0.3769,
+      "step": 155500
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 0.0002101368680096334,
+      "loss": 0.3771,
+      "step": 156000
+    },
+    {
+      "epoch": 6.96,
+      "eval_loss": 0.35130995512008667,
+      "eval_runtime": 2.2636,
+      "eval_samples_per_second": 1014.77,
+      "eval_steps_per_second": 15.904,
+      "step": 156000
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 0.00020829149266370862,
+      "loss": 0.377,
+      "step": 156500
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00020645034766118703,
+      "loss": 0.3769,
+      "step": 157000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.35048824548721313,
+      "eval_runtime": 2.2749,
+      "eval_samples_per_second": 1009.702,
+      "eval_steps_per_second": 15.825,
+      "step": 157000
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 0.00020461351353971526,
+      "loss": 0.3766,
+      "step": 157500
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 0.00020278107064836847,
+      "loss": 0.3766,
+      "step": 158000
+    },
+    {
+      "epoch": 7.05,
+      "eval_loss": 0.3498741090297699,
+      "eval_runtime": 2.2625,
+      "eval_samples_per_second": 1015.239,
+      "eval_steps_per_second": 15.911,
+      "step": 158000
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 0.00020095309914413485,
+      "loss": 0.3764,
+      "step": 158500
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 0.00019912967898840997,
+      "loss": 0.3762,
+      "step": 159000
+    },
+    {
+      "epoch": 7.09,
+      "eval_loss": 0.34895479679107666,
+      "eval_runtime": 2.1885,
+      "eval_samples_per_second": 1049.579,
+      "eval_steps_per_second": 16.45,
+      "step": 159000
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 0.00019731088994349834,
+      "loss": 0.3763,
+      "step": 159500
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.0001954968115691248,
+      "loss": 0.376,
+      "step": 160000
+    },
+    {
+      "epoch": 7.14,
+      "eval_loss": 0.3464561402797699,
+      "eval_runtime": 2.2955,
+      "eval_samples_per_second": 1000.637,
+      "eval_steps_per_second": 15.683,
+      "step": 160000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 2.40247725109402e+21,
+  "total_flos": 2.5626381219776503e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d9dd260c6a1eea214a50fb35a68c126c97cfb31dd7f81eeaee885739a9a21c
+oid sha256:8fd59d7cfb5049e46570c40bfa98b1ab6951678f21e1e8ee02bf24082eee2565
 size 25761253