Training in progress, step 130000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3290fe37a91479d6ab7f5943f720695a90f016b8ef2878f4eacc19dec412ccde
+oid sha256:d58d76c1f639c31e7ba95d3fafba4b0b4df7581368e50e5257ae58a95439515c
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afb485a315cb6d1cbb995c2e4e8a5bda0967bae5d1ca0bd5b33331f6f3244fc
+oid sha256:f5e03d62fb4f6a3907627a7fbc89817395c675b306818e9086c488f63d3ab7cd
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf719b3415ea1dec9edabeceb77eb2a8f1be572542366e9bda15c1bceda980
+oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf719b3415ea1dec9edabeceb77eb2a8f1be572542366e9bda15c1bceda980
+oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf719b3415ea1dec9edabeceb77eb2a8f1be572542366e9bda15c1bceda980
+oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf719b3415ea1dec9edabeceb77eb2a8f1be572542366e9bda15c1bceda980
+oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf719b3415ea1dec9edabeceb77eb2a8f1be572542366e9bda15c1bceda980
+oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf719b3415ea1dec9edabeceb77eb2a8f1be572542366e9bda15c1bceda980
+oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf719b3415ea1dec9edabeceb77eb2a8f1be572542366e9bda15c1bceda980
+oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf719b3415ea1dec9edabeceb77eb2a8f1be572542366e9bda15c1bceda980
+oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ddf5c33f60196860027b40e8443017b8ed479cc5dfb73f8a076fe07f546fd4
+oid sha256:f1c3de3c2d66025eca4b56b8d5efacb781ba1e9b4daae40acd9c92c0f7cbe98c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7959644912509614,
-  "global_step": 120000,
+  "epoch": 3.028961532188541,
+  "global_step": 130000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2406,11 +2406,211 @@
       "eval_samples_per_second": 1524.849,
       "eval_steps_per_second": 24.281,
       "step": 120000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.0002720249765698123,
+      "loss": 0.2963,
+      "step": 120500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.0002717412091888626,
+      "loss": 0.2958,
+      "step": 121000
+    },
+    {
+      "epoch": 2.82,
+      "eval_loss": 0.2785983681678772,
+      "eval_runtime": 1.4123,
+      "eval_samples_per_second": 1556.34,
+      "eval_steps_per_second": 24.782,
+      "step": 121000
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.00027145616514475274,
+      "loss": 0.2963,
+      "step": 121500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002711698475546788,
+      "loss": 0.2968,
+      "step": 122000
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 0.27918389439582825,
+      "eval_runtime": 1.4238,
+      "eval_samples_per_second": 1543.71,
+      "eval_steps_per_second": 24.581,
+      "step": 122000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 0.00027088225954976407,
+      "loss": 0.2965,
+      "step": 122500
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 0.0002705934042750249,
+      "loss": 0.2956,
+      "step": 123000
+    },
+    {
+      "epoch": 2.87,
+      "eval_loss": 0.27785566449165344,
+      "eval_runtime": 1.3994,
+      "eval_samples_per_second": 1570.623,
+      "eval_steps_per_second": 25.01,
+      "step": 123000
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 0.00027030328488933625,
+      "loss": 0.2962,
+      "step": 123500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00027001190456539726,
+      "loss": 0.2948,
+      "step": 124000
+    },
+    {
+      "epoch": 2.89,
+      "eval_loss": 0.2769564390182495,
+      "eval_runtime": 1.4165,
+      "eval_samples_per_second": 1551.741,
+      "eval_steps_per_second": 24.709,
+      "step": 124000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.0002697192664896965,
+      "loss": 0.295,
+      "step": 124500
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 0.00026942537386247706,
+      "loss": 0.2952,
+      "step": 125000
+    },
+    {
+      "epoch": 2.91,
+      "eval_loss": 0.27958372235298157,
+      "eval_runtime": 1.3901,
+      "eval_samples_per_second": 1581.168,
+      "eval_steps_per_second": 25.178,
+      "step": 125000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.0002691302298977016,
+      "loss": 0.2948,
+      "step": 125500
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.0002688338378230173,
+      "loss": 0.2943,
+      "step": 126000
+    },
+    {
+      "epoch": 2.94,
+      "eval_loss": 0.2770977318286896,
+      "eval_runtime": 1.4225,
+      "eval_samples_per_second": 1545.165,
+      "eval_steps_per_second": 24.605,
+      "step": 126000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 0.00026853620087972035,
+      "loss": 0.2945,
+      "step": 126500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.00026823732232272065,
+      "loss": 0.2945,
+      "step": 127000
+    },
+    {
+      "epoch": 2.96,
+      "eval_loss": 0.27677854895591736,
+      "eval_runtime": 1.4513,
+      "eval_samples_per_second": 1514.548,
+      "eval_steps_per_second": 24.117,
+      "step": 127000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 0.0002679372054205063,
+      "loss": 0.2949,
+      "step": 127500
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0002676358534551076,
+      "loss": 0.2945,
+      "step": 128000
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 0.27655109763145447,
+      "eval_runtime": 1.4264,
+      "eval_samples_per_second": 1540.932,
+      "eval_steps_per_second": 24.537,
+      "step": 128000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.00026733326972206133,
+      "loss": 0.2942,
+      "step": 128500
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0002670294575303748,
+      "loss": 0.2944,
+      "step": 129000
+    },
+    {
+      "epoch": 3.01,
+      "eval_loss": 0.2760108709335327,
+      "eval_runtime": 1.4342,
+      "eval_samples_per_second": 1532.608,
+      "eval_steps_per_second": 24.405,
+      "step": 129000
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0002667244202024894,
+      "loss": 0.2942,
+      "step": 129500
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 0.00026641816107424453,
+      "loss": 0.2944,
+      "step": 130000
+    },
+    {
+      "epoch": 3.03,
+      "eval_loss": 0.2757641077041626,
+      "eval_runtime": 1.4126,
+      "eval_samples_per_second": 1555.976,
+      "eval_steps_per_second": 24.777,
+      "step": 130000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 3.8338406713121864e+21,
+  "total_flos": 4.15332531309578e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afb485a315cb6d1cbb995c2e4e8a5bda0967bae5d1ca0bd5b33331f6f3244fc
+oid sha256:f5e03d62fb4f6a3907627a7fbc89817395c675b306818e9086c488f63d3ab7cd
 size 102501541