Training in progress, step 270000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:406ff60c9fbc96f08fa188658defda9ad6b5e381b6cf799e20366bdf81afbd2a
+oid sha256:2db59304ac09b28bcb3c65afafd5ee1982c926ae9e5b3be0a3041e16925dc09d
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e0c29fd1ad93ebeb1e95f532ec268fb56806f7c232e1c94e4622474be46744f
+oid sha256:6481ae1099357d8bcf88c484382e1abee67e04204a9282cec0553dec29988327
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b23f32e817f69e70978a71b81655fa6e8769bb16cbe73bed041ad33f8df64bb
+oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b23f32e817f69e70978a71b81655fa6e8769bb16cbe73bed041ad33f8df64bb
+oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b23f32e817f69e70978a71b81655fa6e8769bb16cbe73bed041ad33f8df64bb
+oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b23f32e817f69e70978a71b81655fa6e8769bb16cbe73bed041ad33f8df64bb
+oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b23f32e817f69e70978a71b81655fa6e8769bb16cbe73bed041ad33f8df64bb
+oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b23f32e817f69e70978a71b81655fa6e8769bb16cbe73bed041ad33f8df64bb
+oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b23f32e817f69e70978a71b81655fa6e8769bb16cbe73bed041ad33f8df64bb
+oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b23f32e817f69e70978a71b81655fa6e8769bb16cbe73bed041ad33f8df64bb
+oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7fe86b6bf62db9f7989d6e264b9b70447a29a8d4bbea419af77ab1989ca356
+oid sha256:6cb61348726887e329b19406ea4e3e39ac391edeec6dfd8508b3cb524aa33e28
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.057923064377082,
-  "global_step": 260000,
+  "epoch": 6.290920105314663,
+  "global_step": 270000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5206,11 +5206,211 @@
       "eval_samples_per_second": 1533.386,
       "eval_steps_per_second": 24.417,
       "step": 260000
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00015691796905504187,
+      "loss": 0.2712,
+      "step": 260500
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 0.00015643849514435944,
+      "loss": 0.2709,
+      "step": 261000
+    },
+    {
+      "epoch": 6.08,
+      "eval_loss": 0.2548723816871643,
+      "eval_runtime": 1.4314,
+      "eval_samples_per_second": 1535.607,
+      "eval_steps_per_second": 24.452,
+      "step": 261000
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 0.00015595900550252463,
+      "loss": 0.2707,
+      "step": 261500
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 0.00015547950537315926,
+      "loss": 0.2708,
+      "step": 262000
+    },
+    {
+      "epoch": 6.1,
+      "eval_loss": 0.2543224096298218,
+      "eval_runtime": 1.4239,
+      "eval_samples_per_second": 1543.639,
+      "eval_steps_per_second": 24.58,
+      "step": 262000
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 0.00015499999999999997,
+      "loss": 0.2708,
+      "step": 262500
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 0.00015452049462684068,
+      "loss": 0.2719,
+      "step": 263000
+    },
+    {
+      "epoch": 6.13,
+      "eval_loss": 0.25397995114326477,
+      "eval_runtime": 1.4586,
+      "eval_samples_per_second": 1506.925,
+      "eval_steps_per_second": 23.996,
+      "step": 263000
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 0.00015404099449747535,
+      "loss": 0.2712,
+      "step": 263500
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 0.0001535615048556405,
+      "loss": 0.2706,
+      "step": 264000
+    },
+    {
+      "epoch": 6.15,
+      "eval_loss": 0.2522125244140625,
+      "eval_runtime": 1.474,
+      "eval_samples_per_second": 1491.135,
+      "eval_steps_per_second": 23.744,
+      "step": 264000
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 0.0001530820309449581,
+      "loss": 0.2705,
+      "step": 264500
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 0.00015260257800887798,
+      "loss": 0.2705,
+      "step": 265000
+    },
+    {
+      "epoch": 6.17,
+      "eval_loss": 0.25516122579574585,
+      "eval_runtime": 1.3844,
+      "eval_samples_per_second": 1587.692,
+      "eval_steps_per_second": 25.282,
+      "step": 265000
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 0.0001521231512906207,
+      "loss": 0.2709,
+      "step": 265500
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 0.00015164375603311998,
+      "loss": 0.2708,
+      "step": 266000
+    },
+    {
+      "epoch": 6.2,
+      "eval_loss": 0.25247690081596375,
+      "eval_runtime": 1.4156,
+      "eval_samples_per_second": 1552.724,
+      "eval_steps_per_second": 24.725,
+      "step": 266000
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 0.00015116439747896553,
+      "loss": 0.271,
+      "step": 266500
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 0.00015068508087034578,
+      "loss": 0.2704,
+      "step": 267000
+    },
+    {
+      "epoch": 6.22,
+      "eval_loss": 0.25168919563293457,
+      "eval_runtime": 1.4279,
+      "eval_samples_per_second": 1539.31,
+      "eval_steps_per_second": 24.511,
+      "step": 267000
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 0.00015020581144899027,
+      "loss": 0.2702,
+      "step": 267500
+    },
+    {
+      "epoch": 6.24,
+      "learning_rate": 0.0001497265944561127,
+      "loss": 0.2701,
+      "step": 268000
+    },
+    {
+      "epoch": 6.24,
+      "eval_loss": 0.2535783052444458,
+      "eval_runtime": 1.4078,
+      "eval_samples_per_second": 1561.345,
+      "eval_steps_per_second": 24.862,
+      "step": 268000
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 0.00014924743513235327,
+      "loss": 0.2703,
+      "step": 268500
+    },
+    {
+      "epoch": 6.27,
+      "learning_rate": 0.0001487683387177216,
+      "loss": 0.2704,
+      "step": 269000
+    },
+    {
+      "epoch": 6.27,
+      "eval_loss": 0.25389179587364197,
+      "eval_runtime": 1.4483,
+      "eval_samples_per_second": 1517.622,
+      "eval_steps_per_second": 24.166,
+      "step": 269000
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 0.00014828931045153928,
+      "loss": 0.2703,
+      "step": 269500
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.00014781035557238272,
+      "loss": 0.2702,
+      "step": 270000
+    },
+    {
+      "epoch": 6.29,
+      "eval_loss": 0.2548398971557617,
+      "eval_runtime": 1.4524,
+      "eval_samples_per_second": 1513.389,
+      "eval_steps_per_second": 24.099,
+      "step": 270000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 8.30665062619156e+21,
+  "total_flos": 8.626137764966059e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e0c29fd1ad93ebeb1e95f532ec268fb56806f7c232e1c94e4622474be46744f
+oid sha256:6481ae1099357d8bcf88c484382e1abee67e04204a9282cec0553dec29988327
 size 102501541