Training in progress, step 320000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0507b38aa7540f67f9e0a0633279dd51f9a831fc1db6cc8eacbb35397bd4b8
+oid sha256:e8164585c0cf8e0435f85a1a07a5b437860c2cdc001a4018d6d0b9d01b7eba98
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671528b9282de7ee8eda298ebd63ddf167905d49365aa89ef6684cdf3a665481
+oid sha256:962905691e3e61901278bd35bae6a9e6802f21882ed0e962dd2ab116fea9b46f
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
+oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
+oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
+oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
+oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
+oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
+oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
+oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
+oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8c10dab6d3ee824fc8fe4628d3bf3ceea806ce0d2fbe513f32af4d508ab89e
+oid sha256:5673377a057c7734bd1a0ee14d972f6f3bfc67bb8208ac49ae618347d18d616b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.222908269064983,
-  "global_step": 310000,
+  "epoch": 7.455905310002563,
+  "global_step": 320000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6206,11 +6206,211 @@
       "eval_samples_per_second": 1519.474,
       "eval_steps_per_second": 24.195,
       "step": 310000
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 0.00010973674410951567,
+      "loss": 0.2657,
+      "step": 310500
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 0.00010928144739511337,
+      "loss": 0.2656,
+      "step": 311000
+    },
+    {
+      "epoch": 7.25,
+      "eval_loss": 0.2480616420507431,
+      "eval_runtime": 1.4455,
+      "eval_samples_per_second": 1520.549,
+      "eval_steps_per_second": 24.213,
+      "step": 311000
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 0.00010882665065147757,
+      "loss": 0.2655,
+      "step": 311500
+    },
+    {
+      "epoch": 7.27,
+      "learning_rate": 0.00010837235885219267,
+      "loss": 0.2653,
+      "step": 312000
+    },
+    {
+      "epoch": 7.27,
+      "eval_loss": 0.2518889009952545,
+      "eval_runtime": 1.4252,
+      "eval_samples_per_second": 1542.203,
+      "eval_steps_per_second": 24.557,
+      "step": 312000
+    },
+    {
+      "epoch": 7.28,
+      "learning_rate": 0.00010791857696532089,
+      "loss": 0.2653,
+      "step": 312500
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 0.00010746530995334832,
+      "loss": 0.2652,
+      "step": 313000
+    },
+    {
+      "epoch": 7.29,
+      "eval_loss": 0.24834561347961426,
+      "eval_runtime": 1.454,
+      "eval_samples_per_second": 1511.735,
+      "eval_steps_per_second": 24.072,
+      "step": 313000
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 0.0001070125627731304,
+      "loss": 0.2653,
+      "step": 313500
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 0.0001065603403758377,
+      "loss": 0.2654,
+      "step": 314000
+    },
+    {
+      "epoch": 7.32,
+      "eval_loss": 0.24683910608291626,
+      "eval_runtime": 1.4569,
+      "eval_samples_per_second": 1508.633,
+      "eval_steps_per_second": 24.023,
+      "step": 314000
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 0.00010610864770690196,
+      "loss": 0.2652,
+      "step": 314500
+    },
+    {
+      "epoch": 7.34,
+      "learning_rate": 0.00010565748970596172,
+      "loss": 0.2653,
+      "step": 315000
+    },
+    {
+      "epoch": 7.34,
+      "eval_loss": 0.2493169754743576,
+      "eval_runtime": 1.4715,
+      "eval_samples_per_second": 1493.749,
+      "eval_steps_per_second": 23.786,
+      "step": 315000
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 0.00010520687130680884,
+      "loss": 0.2653,
+      "step": 315500
+    },
+    {
+      "epoch": 7.36,
+      "learning_rate": 0.00010475679743733364,
+      "loss": 0.265,
+      "step": 316000
+    },
+    {
+      "epoch": 7.36,
+      "eval_loss": 0.24726563692092896,
+      "eval_runtime": 1.4143,
+      "eval_samples_per_second": 1554.111,
+      "eval_steps_per_second": 24.747,
+      "step": 316000
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 0.00010430727301947202,
+      "loss": 0.2647,
+      "step": 316500
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 0.00010385830296915104,
+      "loss": 0.2646,
+      "step": 317000
+    },
+    {
+      "epoch": 7.39,
+      "eval_loss": 0.24790264666080475,
+      "eval_runtime": 1.4368,
+      "eval_samples_per_second": 1529.828,
+      "eval_steps_per_second": 24.36,
+      "step": 317000
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 0.00010340989219623508,
+      "loss": 0.2649,
+      "step": 317500
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 0.0001029620456044727,
+      "loss": 0.2647,
+      "step": 318000
+    },
+    {
+      "epoch": 7.41,
+      "eval_loss": 0.24833044409751892,
+      "eval_runtime": 1.4568,
+      "eval_samples_per_second": 1508.735,
+      "eval_steps_per_second": 24.024,
+      "step": 318000
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 0.00010251476809144226,
+      "loss": 0.2643,
+      "step": 318500
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 0.00010206806454849917,
+      "loss": 0.2645,
+      "step": 319000
+    },
+    {
+      "epoch": 7.43,
+      "eval_loss": 0.2483694851398468,
+      "eval_runtime": 1.465,
+      "eval_samples_per_second": 1500.321,
+      "eval_steps_per_second": 23.89,
+      "step": 319000
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 0.00010162193986072167,
+      "loss": 0.2644,
+      "step": 319500
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 0.00010117639890685795,
+      "loss": 0.2642,
+      "step": 320000
+    },
+    {
+      "epoch": 7.46,
+      "eval_loss": 0.2466782182455063,
+      "eval_runtime": 1.4627,
+      "eval_samples_per_second": 1502.721,
+      "eval_steps_per_second": 23.929,
+      "step": 320000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 9.904083823073153e+21,
+  "total_flos": 1.0223570961847653e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671528b9282de7ee8eda298ebd63ddf167905d49365aa89ef6684cdf3a665481
+oid sha256:962905691e3e61901278bd35bae6a9e6802f21882ed0e962dd2ab116fea9b46f
 size 102501541