Training in progress, step 140000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d58d76c1f639c31e7ba95d3fafba4b0b4df7581368e50e5257ae58a95439515c
+oid sha256:aca41469954b0cdd00c93c46873cd2afb5a1a523ea77c504489bc7efcf8bf668
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e03d62fb4f6a3907627a7fbc89817395c675b306818e9086c488f63d3ab7cd
+oid sha256:9af6be3972f3b3e2c13dce429397ece13973069648d233609e51fd1be73a404a
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
+oid sha256:5f52d61c93314d406f5efbb593d2fee6f58fe805cd1be44b93e8b9a7a77fd617
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
+oid sha256:5f52d61c93314d406f5efbb593d2fee6f58fe805cd1be44b93e8b9a7a77fd617
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
+oid sha256:5f52d61c93314d406f5efbb593d2fee6f58fe805cd1be44b93e8b9a7a77fd617
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
+oid sha256:5f52d61c93314d406f5efbb593d2fee6f58fe805cd1be44b93e8b9a7a77fd617
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
+oid sha256:5f52d61c93314d406f5efbb593d2fee6f58fe805cd1be44b93e8b9a7a77fd617
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
+oid sha256:5f52d61c93314d406f5efbb593d2fee6f58fe805cd1be44b93e8b9a7a77fd617
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
+oid sha256:5f52d61c93314d406f5efbb593d2fee6f58fe805cd1be44b93e8b9a7a77fd617
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8be656d703ff88efddcc4ceee60baffceb98bce707f489ada7dcfd797db0102
+oid sha256:5f52d61c93314d406f5efbb593d2fee6f58fe805cd1be44b93e8b9a7a77fd617
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c3de3c2d66025eca4b56b8d5efacb781ba1e9b4daae40acd9c92c0f7cbe98c
+oid sha256:f9522f343e5b1c37fe7e600f7b39d619e850350d8948dc240940a440582a0eb9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.028961532188541,
-  "global_step": 130000,
+  "epoch": 3.261958573126121,
+  "global_step": 140000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2606,11 +2606,211 @@
       "eval_samples_per_second": 1555.976,
       "eval_steps_per_second": 24.777,
       "step": 130000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.0002661106834948409,
+      "loss": 0.2939,
+      "step": 130500
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 0.0002658019908268041,
+      "loss": 0.2937,
+      "step": 131000
+    },
+    {
+      "epoch": 3.05,
+      "eval_loss": 0.27508604526519775,
+      "eval_runtime": 1.4205,
+      "eval_samples_per_second": 1547.302,
+      "eval_steps_per_second": 24.639,
+      "step": 131000
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 0.00026549208644594766,
+      "loss": 0.294,
+      "step": 131500
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.00026518097374133627,
+      "loss": 0.2935,
+      "step": 132000
+    },
+    {
+      "epoch": 3.08,
+      "eval_loss": 0.2736782431602478,
+      "eval_runtime": 1.4305,
+      "eval_samples_per_second": 1536.563,
+      "eval_steps_per_second": 24.468,
+      "step": 132000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 0.00026486865611524853,
+      "loss": 0.2932,
+      "step": 132500
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.00026455513698314003,
+      "loss": 0.2931,
+      "step": 133000
+    },
+    {
+      "epoch": 3.1,
+      "eval_loss": 0.27545085549354553,
+      "eval_runtime": 1.4136,
+      "eval_samples_per_second": 1554.95,
+      "eval_steps_per_second": 24.76,
+      "step": 133000
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 0.0002642404197736058,
+      "loss": 0.2931,
+      "step": 133500
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 0.0002639245079283428,
+      "loss": 0.2936,
+      "step": 134000
+    },
+    {
+      "epoch": 3.12,
+      "eval_loss": 0.27676478028297424,
+      "eval_runtime": 1.4314,
+      "eval_samples_per_second": 1535.602,
+      "eval_steps_per_second": 24.452,
+      "step": 134000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 0.00026360740490211234,
+      "loss": 0.2932,
+      "step": 134500
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.0002632891141627023,
+      "loss": 0.2934,
+      "step": 135000
+    },
+    {
+      "epoch": 3.15,
+      "eval_loss": 0.2775753438472748,
+      "eval_runtime": 1.4316,
+      "eval_samples_per_second": 1535.332,
+      "eval_steps_per_second": 24.448,
+      "step": 135000
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 0.00026296963919088923,
+      "loss": 0.2927,
+      "step": 135500
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 0.00026264898348040024,
+      "loss": 0.2925,
+      "step": 136000
+    },
+    {
+      "epoch": 3.17,
+      "eval_loss": 0.27160218358039856,
+      "eval_runtime": 1.4163,
+      "eval_samples_per_second": 1551.918,
+      "eval_steps_per_second": 24.712,
+      "step": 136000
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 0.0002623271505378748,
+      "loss": 0.2926,
+      "step": 136500
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 0.00026200414388282637,
+      "loss": 0.2924,
+      "step": 137000
+    },
+    {
+      "epoch": 3.19,
+      "eval_loss": 0.2737308442592621,
+      "eval_runtime": 1.4266,
+      "eval_samples_per_second": 1540.705,
+      "eval_steps_per_second": 24.534,
+      "step": 137000
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 0.00026167996704760406,
+      "loss": 0.2929,
+      "step": 137500
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.00026135462357735375,
+      "loss": 0.2931,
+      "step": 138000
+    },
+    {
+      "epoch": 3.22,
+      "eval_loss": 0.2752697467803955,
+      "eval_runtime": 1.4495,
+      "eval_samples_per_second": 1516.388,
+      "eval_steps_per_second": 24.146,
+      "step": 138000
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 0.0002610281170299795,
+      "loss": 0.292,
+      "step": 138500
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 0.00026070045097610465,
+      "loss": 0.2917,
+      "step": 139000
+    },
+    {
+      "epoch": 3.24,
+      "eval_loss": 0.2744641602039337,
+      "eval_runtime": 1.4101,
+      "eval_samples_per_second": 1558.726,
+      "eval_steps_per_second": 24.82,
+      "step": 139000
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.0002603716289990326,
+      "loss": 0.2923,
+      "step": 139500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 0.00026004165469470787,
+      "loss": 0.2918,
+      "step": 140000
+    },
+    {
+      "epoch": 3.26,
+      "eval_loss": 0.2773716449737549,
+      "eval_runtime": 1.4122,
+      "eval_samples_per_second": 1556.477,
+      "eval_steps_per_second": 24.785,
+      "step": 140000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 4.15332531309578e+21,
+  "total_flos": 4.4728124518702797e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e03d62fb4f6a3907627a7fbc89817395c675b306818e9086c488f63d3ab7cd
+oid sha256:9af6be3972f3b3e2c13dce429397ece13973069648d233609e51fd1be73a404a
 size 102501541