Training in progress, step 120000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb8f4ee9932432a287ea513e3af3b078520ad61de1f8f7e44c83962a189c305
+oid sha256:f5c1a1f468fc2d342a23f1ac0d5752569966a310ca13ca1f923b43583a411e84
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:692f0849f73d31d0d7ef6f2f2af3ccd645c1956f15cf41f9debc0106e2cea5be
+oid sha256:65a92e8166f8fa9a54e98da57dbdf5c7d7bdbe9bb899a7638fe74e0582796f58
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2eacfeedd0bf9408bd36cab2e1c6eae31897175ab967af2fed6efe328f2b5f
+oid sha256:44b70180124cd582ce1fec2362a6c7b1500fac5e37241e6e64ee705ea6e177b8
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2eacfeedd0bf9408bd36cab2e1c6eae31897175ab967af2fed6efe328f2b5f
+oid sha256:44b70180124cd582ce1fec2362a6c7b1500fac5e37241e6e64ee705ea6e177b8
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2eacfeedd0bf9408bd36cab2e1c6eae31897175ab967af2fed6efe328f2b5f
+oid sha256:44b70180124cd582ce1fec2362a6c7b1500fac5e37241e6e64ee705ea6e177b8
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2eacfeedd0bf9408bd36cab2e1c6eae31897175ab967af2fed6efe328f2b5f
+oid sha256:44b70180124cd582ce1fec2362a6c7b1500fac5e37241e6e64ee705ea6e177b8
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2eacfeedd0bf9408bd36cab2e1c6eae31897175ab967af2fed6efe328f2b5f
+oid sha256:44b70180124cd582ce1fec2362a6c7b1500fac5e37241e6e64ee705ea6e177b8
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2eacfeedd0bf9408bd36cab2e1c6eae31897175ab967af2fed6efe328f2b5f
+oid sha256:44b70180124cd582ce1fec2362a6c7b1500fac5e37241e6e64ee705ea6e177b8
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2eacfeedd0bf9408bd36cab2e1c6eae31897175ab967af2fed6efe328f2b5f
+oid sha256:44b70180124cd582ce1fec2362a6c7b1500fac5e37241e6e64ee705ea6e177b8
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2eacfeedd0bf9408bd36cab2e1c6eae31897175ab967af2fed6efe328f2b5f
+oid sha256:44b70180124cd582ce1fec2362a6c7b1500fac5e37241e6e64ee705ea6e177b8
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe4bb2f202e1c5bfac6f58d7d7aff54991c6919cce0ee2976f31297f1718992f
+oid sha256:c534c69c702472a462ee5c5c8e40f09fd7295b5cb464c1c3364c271724c3d05b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.907209136331192,
-  "global_step": 110000,
+  "epoch": 5.353319057815845,
+  "global_step": 120000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2206,11 +2206,211 @@
       "eval_samples_per_second": 1041.083,
       "eval_steps_per_second": 16.316,
       "step": 110000
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.00038495756080926107,
+      "loss": 0.3933,
+      "step": 110500
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 0.0003830777659310416,
+      "loss": 0.3932,
+      "step": 111000
+    },
+    {
+      "epoch": 4.95,
+      "eval_loss": 0.36492955684661865,
+      "eval_runtime": 2.2207,
+      "eval_samples_per_second": 1034.354,
+      "eval_steps_per_second": 16.211,
+      "step": 111000
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 0.0003811945556784033,
+      "loss": 0.3931,
+      "step": 111500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00037930801242906366,
+      "loss": 0.3925,
+      "step": 112000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.36507272720336914,
+      "eval_runtime": 2.3005,
+      "eval_samples_per_second": 998.488,
+      "eval_steps_per_second": 15.649,
+      "step": 112000
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.00037741821870653576,
+      "loss": 0.3924,
+      "step": 112500
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 0.00037552525717651905,
+      "loss": 0.3919,
+      "step": 113000
+    },
+    {
+      "epoch": 5.04,
+      "eval_loss": 0.3649584650993347,
+      "eval_runtime": 2.1025,
+      "eval_samples_per_second": 1092.533,
+      "eval_steps_per_second": 17.123,
+      "step": 113000
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 0.0003736292106432834,
+      "loss": 0.3918,
+      "step": 113500
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 0.00037173016204604647,
+      "loss": 0.3915,
+      "step": 114000
+    },
+    {
+      "epoch": 5.09,
+      "eval_loss": 0.36355069279670715,
+      "eval_runtime": 2.1224,
+      "eval_samples_per_second": 1082.26,
+      "eval_steps_per_second": 16.962,
+      "step": 114000
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 0.0003698281944553456,
+      "loss": 0.3915,
+      "step": 114500
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 0.0003679233910694053,
+      "loss": 0.3911,
+      "step": 115000
+    },
+    {
+      "epoch": 5.13,
+      "eval_loss": 0.36546093225479126,
+      "eval_runtime": 2.202,
+      "eval_samples_per_second": 1043.148,
+      "eval_steps_per_second": 16.349,
+      "step": 115000
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 0.000366015835210496,
+      "loss": 0.3911,
+      "step": 115500
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 0.0003641056103212908,
+      "loss": 0.3905,
+      "step": 116000
+    },
+    {
+      "epoch": 5.17,
+      "eval_loss": 0.36497965455055237,
+      "eval_runtime": 2.1541,
+      "eval_samples_per_second": 1066.328,
+      "eval_steps_per_second": 16.712,
+      "step": 116000
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 0.00036219279996121446,
+      "loss": 0.3904,
+      "step": 116500
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 0.0003602774878027888,
+      "loss": 0.3905,
+      "step": 117000
+    },
+    {
+      "epoch": 5.22,
+      "eval_loss": 0.40538668632507324,
+      "eval_runtime": 2.1607,
+      "eval_samples_per_second": 1063.067,
+      "eval_steps_per_second": 16.661,
+      "step": 117000
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.00035835975762797245,
+      "loss": 0.3917,
+      "step": 117500
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 0.0003564396933244957,
+      "loss": 0.3894,
+      "step": 118000
+    },
+    {
+      "epoch": 5.26,
+      "eval_loss": 0.36090952157974243,
+      "eval_runtime": 2.2235,
+      "eval_samples_per_second": 1033.034,
+      "eval_steps_per_second": 16.19,
+      "step": 118000
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 0.0003545173788821915,
+      "loss": 0.3893,
+      "step": 118500
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 0.00035259289838932104,
+      "loss": 0.3889,
+      "step": 119000
+    },
+    {
+      "epoch": 5.31,
+      "eval_loss": 0.3599041998386383,
+      "eval_runtime": 2.1374,
+      "eval_samples_per_second": 1074.669,
+      "eval_steps_per_second": 16.843,
+      "step": 119000
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 0.0003506663360288954,
+      "loss": 0.3889,
+      "step": 119500
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 0.00034873777607499334,
+      "loss": 0.3888,
+      "step": 120000
+    },
+    {
+      "epoch": 5.35,
+      "eval_loss": 0.3593074679374695,
+      "eval_runtime": 2.1457,
+      "eval_samples_per_second": 1070.506,
+      "eval_steps_per_second": 16.778,
+      "step": 120000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 1.7618195035951506e+21,
+  "total_flos": 1.9219803744787812e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:692f0849f73d31d0d7ef6f2f2af3ccd645c1956f15cf41f9debc0106e2cea5be
+oid sha256:65a92e8166f8fa9a54e98da57dbdf5c7d7bdbe9bb899a7638fe74e0582796f58
 size 25761253