Training in progress, step 240000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9933ffb813c5e8d1b7ad33a26e8a3de9dffc68f6791dcaa9629fa1e8eaadacb6
+oid sha256:e03b1e6c9e8ebd7a68dc083465f79f8e9b65b3a76ab64f485e8ac5e4016f6196
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15446ffa2940837310c6fba47ec8a6ccafb4fee2ac5679b0655ceb901ddcc645
+oid sha256:e2bb60945557188c178a814d3de53e71d2ea19a106d73bdcc2bb4d0b52106ded
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e525c0defbe9a7f16b113a516e2192076e900a8cfc884a74159705d6da78fc
+oid sha256:0abb36119902d5f3d267790238b693fe309f88f350fb7d50de5f12b27466a3e7
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e525c0defbe9a7f16b113a516e2192076e900a8cfc884a74159705d6da78fc
+oid sha256:0abb36119902d5f3d267790238b693fe309f88f350fb7d50de5f12b27466a3e7
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e525c0defbe9a7f16b113a516e2192076e900a8cfc884a74159705d6da78fc
+oid sha256:0abb36119902d5f3d267790238b693fe309f88f350fb7d50de5f12b27466a3e7
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e525c0defbe9a7f16b113a516e2192076e900a8cfc884a74159705d6da78fc
+oid sha256:0abb36119902d5f3d267790238b693fe309f88f350fb7d50de5f12b27466a3e7
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e525c0defbe9a7f16b113a516e2192076e900a8cfc884a74159705d6da78fc
+oid sha256:0abb36119902d5f3d267790238b693fe309f88f350fb7d50de5f12b27466a3e7
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e525c0defbe9a7f16b113a516e2192076e900a8cfc884a74159705d6da78fc
+oid sha256:0abb36119902d5f3d267790238b693fe309f88f350fb7d50de5f12b27466a3e7
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e525c0defbe9a7f16b113a516e2192076e900a8cfc884a74159705d6da78fc
+oid sha256:0abb36119902d5f3d267790238b693fe309f88f350fb7d50de5f12b27466a3e7
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e525c0defbe9a7f16b113a516e2192076e900a8cfc884a74159705d6da78fc
+oid sha256:0abb36119902d5f3d267790238b693fe309f88f350fb7d50de5f12b27466a3e7
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2bb37359d05bc7917d91ab1261ba8c4d8f00648cd8cb2d11c677b6c91ddb27
+oid sha256:a310455c0ab00dbcb4f4c26c03e0304d748fbc8c3e547006fb15346d32ac70da
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.1302640970735185,
-  "global_step": 230000,
+  "epoch": 5.353319057815845,
+  "global_step": 240000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4606,11 +4606,211 @@
       "eval_samples_per_second": 1122.145,
       "eval_steps_per_second": 17.587,
       "step": 230000
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 0.00018545980690870903,
+      "loss": 0.2799,
+      "step": 230500
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 0.00018499083425600648,
+      "loss": 0.2791,
+      "step": 231000
+    },
+    {
+      "epoch": 5.15,
+      "eval_loss": 0.26100829243659973,
+      "eval_runtime": 1.9738,
+      "eval_samples_per_second": 1163.773,
+      "eval_steps_per_second": 18.239,
+      "step": 231000
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 0.00018452153362834552,
+      "loss": 0.2791,
+      "step": 231500
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 0.00018405191015792254,
+      "loss": 0.2829,
+      "step": 232000
+    },
+    {
+      "epoch": 5.17,
+      "eval_loss": 0.26664701104164124,
+      "eval_runtime": 2.018,
+      "eval_samples_per_second": 1138.267,
+      "eval_steps_per_second": 17.84,
+      "step": 232000
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 0.0001835819689804646,
+      "loss": 0.2818,
+      "step": 232500
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 0.0001831117152351732,
+      "loss": 0.2789,
+      "step": 233000
+    },
+    {
+      "epoch": 5.2,
+      "eval_loss": 0.2605225443840027,
+      "eval_runtime": 1.994,
+      "eval_samples_per_second": 1151.94,
+      "eval_steps_per_second": 18.054,
+      "step": 233000
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 0.00018264115406466778,
+      "loss": 0.2784,
+      "step": 233500
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 0.00018217029061493007,
+      "loss": 0.2816,
+      "step": 234000
+    },
+    {
+      "epoch": 5.22,
+      "eval_loss": 0.26246902346611023,
+      "eval_runtime": 2.0381,
+      "eval_samples_per_second": 1127.052,
+      "eval_steps_per_second": 17.664,
+      "step": 234000
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 0.00018169913003524717,
+      "loss": 0.2818,
+      "step": 234500
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.00018122767747815594,
+      "loss": 0.2791,
+      "step": 235000
+    },
+    {
+      "epoch": 5.24,
+      "eval_loss": 0.26137277483940125,
+      "eval_runtime": 2.0611,
+      "eval_samples_per_second": 1114.437,
+      "eval_steps_per_second": 17.466,
+      "step": 235000
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 0.00018075593809938574,
+      "loss": 0.2783,
+      "step": 235500
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 0.00018028391705780295,
+      "loss": 0.2782,
+      "step": 236000
+    },
+    {
+      "epoch": 5.26,
+      "eval_loss": 0.26220422983169556,
+      "eval_runtime": 2.0409,
+      "eval_samples_per_second": 1125.474,
+      "eval_steps_per_second": 17.639,
+      "step": 236000
+    },
+    {
+      "epoch": 5.28,
+      "learning_rate": 0.0001798116195153541,
+      "loss": 0.2782,
+      "step": 236500
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 0.0001793390506370094,
+      "loss": 0.2816,
+      "step": 237000
+    },
+    {
+      "epoch": 5.29,
+      "eval_loss": 0.2643316388130188,
+      "eval_runtime": 2.0022,
+      "eval_samples_per_second": 1147.236,
+      "eval_steps_per_second": 17.98,
+      "step": 237000
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 0.00017886621559070638,
+      "loss": 0.281,
+      "step": 237500
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 0.00017839311954729337,
+      "loss": 0.2799,
+      "step": 238000
+    },
+    {
+      "epoch": 5.31,
+      "eval_loss": 0.2624029219150543,
+      "eval_runtime": 1.9308,
+      "eval_samples_per_second": 1189.661,
+      "eval_steps_per_second": 18.645,
+      "step": 238000
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 0.00017791976768047292,
+      "loss": 0.28,
+      "step": 238500
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 0.00017744616516674518,
+      "loss": 0.2792,
+      "step": 239000
+    },
+    {
+      "epoch": 5.33,
+      "eval_loss": 0.2625776529312134,
+      "eval_runtime": 1.9068,
+      "eval_samples_per_second": 1204.635,
+      "eval_steps_per_second": 18.88,
+      "step": 239000
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 0.00017697231718535132,
+      "loss": 0.2807,
+      "step": 239500
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 0.00017649822891821707,
+      "loss": 0.2794,
+      "step": 240000
+    },
+    {
+      "epoch": 5.35,
+      "eval_loss": 0.26089775562286377,
+      "eval_runtime": 2.0641,
+      "eval_samples_per_second": 1112.856,
+      "eval_steps_per_second": 17.441,
+      "step": 240000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 7.348061920506424e+21,
+  "total_flos": 7.667549059280924e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15446ffa2940837310c6fba47ec8a6ccafb4fee2ac5679b0655ceb901ddcc645
+oid sha256:e2bb60945557188c178a814d3de53e71d2ea19a106d73bdcc2bb4d0b52106ded
 size 102501541