Training in progress, step 80000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b0acd993b58e7380979a32d60d902e29b0237163228000964967ed569f4694
+oid sha256:ca7b30dd7d3cd1b36c3fa0208b9738aaffe2cc51d1a7feb434cdea790af51c1c
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6589d1615ce90e186fa8aa811fe1eac2541e5dd82ff7b826939fd09b74c6d4
+oid sha256:2721d72b42462f692fdf3de82485b9d24d7776a465480990b2df5c24285a8e05
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
+oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
+oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
+oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
+oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
+oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
+oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
+oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
+oid sha256:7bf0ceabc8cac9357e0c979c52b36fdfc5cf30a4d8ec50dea1b83b540b532596
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a21aa935b59f32e80e60eb114e1441ce82daea46fee66d7b5b4fedbaaa6094
+oid sha256:8ff31836ff2c96f7fb19d95df664b507273477e3a4f87dcce611b28b7e31820b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6309792865630608,
-  "global_step": 70000,
+  "epoch": 1.863976327500641,
+  "global_step": 80000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1406,11 +1406,211 @@
       "eval_samples_per_second": 1537.403,
       "eval_steps_per_second": 24.481,
       "step": 70000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002934838153624519,
+      "loss": 0.3166,
+      "step": 70500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00029334092796560427,
+      "loss": 0.3161,
+      "step": 71000
+    },
+    {
+      "epoch": 1.65,
+      "eval_loss": 0.2996619939804077,
+      "eval_runtime": 1.4139,
+      "eval_samples_per_second": 1554.517,
+      "eval_steps_per_second": 24.753,
+      "step": 71000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0002931965276945326,
+      "loss": 0.3159,
+      "step": 71500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002930506161283751,
+      "loss": 0.3156,
+      "step": 72000
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 0.29820874333381653,
+      "eval_runtime": 1.408,
+      "eval_samples_per_second": 1561.093,
+      "eval_steps_per_second": 24.858,
+      "step": 72000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00029290319486279724,
+      "loss": 0.3152,
+      "step": 72500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002927542655099744,
+      "loss": 0.3148,
+      "step": 73000
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 0.2982105612754822,
+      "eval_runtime": 1.3918,
+      "eval_samples_per_second": 1579.253,
+      "eval_steps_per_second": 25.147,
+      "step": 73000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00029260382969857417,
+      "loss": 0.3148,
+      "step": 73500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00029245188907373845,
+      "loss": 0.3143,
+      "step": 74000
+    },
+    {
+      "epoch": 1.72,
+      "eval_loss": 0.2960808277130127,
+      "eval_runtime": 1.4226,
+      "eval_samples_per_second": 1545.079,
+      "eval_steps_per_second": 24.603,
+      "step": 74000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0002922984452970655,
+      "loss": 0.3141,
+      "step": 74500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.000292143500046592,
+      "loss": 0.3137,
+      "step": 75000
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 0.2935367524623871,
+      "eval_runtime": 1.3992,
+      "eval_samples_per_second": 1570.943,
+      "eval_steps_per_second": 25.015,
+      "step": 75000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0002919870550167743,
+      "loss": 0.3133,
+      "step": 75500
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0002918291119184702,
+      "loss": 0.3132,
+      "step": 76000
+    },
+    {
+      "epoch": 1.77,
+      "eval_loss": 0.2974264919757843,
+      "eval_runtime": 1.3828,
+      "eval_samples_per_second": 1589.484,
+      "eval_steps_per_second": 25.31,
+      "step": 76000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0002916696724789201,
+      "loss": 0.3134,
+      "step": 76500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00029150873844172823,
+      "loss": 0.313,
+      "step": 77000
+    },
+    {
+      "epoch": 1.79,
+      "eval_loss": 0.29650062322616577,
+      "eval_runtime": 1.4037,
+      "eval_samples_per_second": 1565.884,
+      "eval_steps_per_second": 24.934,
+      "step": 77000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00029134631156684334,
+      "loss": 0.3128,
+      "step": 77500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002911823936305398,
+      "loss": 0.3147,
+      "step": 78000
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 0.2946864664554596,
+      "eval_runtime": 1.3928,
+      "eval_samples_per_second": 1578.113,
+      "eval_steps_per_second": 25.129,
+      "step": 78000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0002910169864253979,
+      "loss": 0.3123,
+      "step": 78500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.0002908500917602842,
+      "loss": 0.3118,
+      "step": 79000
+    },
+    {
+      "epoch": 1.84,
+      "eval_loss": 0.2940049469470978,
+      "eval_runtime": 1.405,
+      "eval_samples_per_second": 1564.438,
+      "eval_steps_per_second": 24.911,
+      "step": 79000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00029068171146033226,
+      "loss": 0.3115,
+      "step": 79500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0002905118473669218,
+      "loss": 0.3113,
+      "step": 80000
+    },
+    {
+      "epoch": 1.86,
+      "eval_loss": 0.293503075838089,
+      "eval_runtime": 1.4595,
+      "eval_samples_per_second": 1505.956,
+      "eval_steps_per_second": 23.98,
+      "step": 80000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 2.2364074744305932e+21,
+  "total_flos": 2.555894613205093e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6589d1615ce90e186fa8aa811fe1eac2541e5dd82ff7b826939fd09b74c6d4
+oid sha256:2721d72b42462f692fdf3de82485b9d24d7776a465480990b2df5c24285a8e05
 size 102501541