Training in progress, step 330000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8164585c0cf8e0435f85a1a07a5b437860c2cdc001a4018d6d0b9d01b7eba98
+oid sha256:2b12d2d3c7e9c65fa1cdfdb5c2f4716c387d264ad1a9842602482f2263f5d461
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962905691e3e61901278bd35bae6a9e6802f21882ed0e962dd2ab116fea9b46f
+oid sha256:fe8e1879944525f3e680f804773ec89ad33764384906428a52a2c3c6871bf701
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
+oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
+oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
+oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
+oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
+oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
+oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
+oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48df4ff304dd68d62a4e5fc4e07d3d51f94b7c8bf43256093a56ac0f03010b1f
+oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5673377a057c7734bd1a0ee14d972f6f3bfc67bb8208ac49ae618347d18d616b
+oid sha256:636cb28fce30ad56f68aface20193360fd815697da4c2ec39f5ca647b5e6b45b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.455905310002563,
-  "global_step": 320000,
+  "epoch": 7.688902350940143,
+  "global_step": 330000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6406,11 +6406,211 @@
       "eval_samples_per_second": 1502.721,
       "eval_steps_per_second": 23.929,
       "step": 320000
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 0.00010073144655927253,
+      "loss": 0.2641,
+      "step": 320500
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 0.0001002870876838929,
+      "loss": 0.2643,
+      "step": 321000
+    },
+    {
+      "epoch": 7.48,
+      "eval_loss": 0.24826975166797638,
+      "eval_runtime": 1.437,
+      "eval_samples_per_second": 1529.624,
+      "eval_steps_per_second": 24.357,
+      "step": 321000
+    },
+    {
+      "epoch": 7.49,
+      "learning_rate": 9.984332714015662e-05,
+      "loss": 0.264,
+      "step": 321500
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 9.94001697809578e-05,
+      "loss": 0.2643,
+      "step": 322000
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 0.2487555295228958,
+      "eval_runtime": 1.4486,
+      "eval_samples_per_second": 1517.36,
+      "eval_steps_per_second": 24.162,
+      "step": 322000
+    },
+    {
+      "epoch": 7.51,
+      "learning_rate": 9.895762045259445e-05,
+      "loss": 0.2639,
+      "step": 322500
+    },
+    {
+      "epoch": 7.53,
+      "learning_rate": 9.851568399471498e-05,
+      "loss": 0.2638,
+      "step": 323000
+    },
+    {
+      "epoch": 7.53,
+      "eval_loss": 0.2484089434146881,
+      "eval_runtime": 1.4155,
+      "eval_samples_per_second": 1552.76,
+      "eval_steps_per_second": 24.725,
+      "step": 323000
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 9.807436524026574e-05,
+      "loss": 0.2639,
+      "step": 323500
+    },
+    {
+      "epoch": 7.55,
+      "learning_rate": 9.763366901543801e-05,
+      "loss": 0.2636,
+      "step": 324000
+    },
+    {
+      "epoch": 7.55,
+      "eval_loss": 0.24783042073249817,
+      "eval_runtime": 1.4248,
+      "eval_samples_per_second": 1542.655,
+      "eval_steps_per_second": 24.565,
+      "step": 324000
+    },
+    {
+      "epoch": 7.56,
+      "learning_rate": 9.719360013961495e-05,
+      "loss": 0.2634,
+      "step": 324500
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 9.675416342531944e-05,
+      "loss": 0.2633,
+      "step": 325000
+    },
+    {
+      "epoch": 7.57,
+      "eval_loss": 0.24799397587776184,
+      "eval_runtime": 1.4677,
+      "eval_samples_per_second": 1497.557,
+      "eval_steps_per_second": 23.846,
+      "step": 325000
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 9.631536367816086e-05,
+      "loss": 0.2629,
+      "step": 325500
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 9.587720569678299e-05,
+      "loss": 0.2633,
+      "step": 326000
+    },
+    {
+      "epoch": 7.6,
+      "eval_loss": 0.24824275076389313,
+      "eval_runtime": 1.4202,
+      "eval_samples_per_second": 1547.658,
+      "eval_steps_per_second": 24.644,
+      "step": 326000
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 9.543969427281131e-05,
+      "loss": 0.2637,
+      "step": 326500
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 9.500283419080062e-05,
+      "loss": 0.2637,
+      "step": 327000
+    },
+    {
+      "epoch": 7.62,
+      "eval_loss": 0.24855847656726837,
+      "eval_runtime": 1.3917,
+      "eval_samples_per_second": 1579.351,
+      "eval_steps_per_second": 25.149,
+      "step": 327000
+    },
+    {
+      "epoch": 7.63,
+      "learning_rate": 9.45666302281829e-05,
+      "loss": 0.264,
+      "step": 327500
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 9.413108715521467e-05,
+      "loss": 0.2634,
+      "step": 328000
+    },
+    {
+      "epoch": 7.64,
+      "eval_loss": 0.24637793004512787,
+      "eval_runtime": 1.4458,
+      "eval_samples_per_second": 1520.249,
+      "eval_steps_per_second": 24.208,
+      "step": 328000
+    },
+    {
+      "epoch": 7.65,
+      "learning_rate": 9.369620973492525e-05,
+      "loss": 0.2638,
+      "step": 328500
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 9.326200272306445e-05,
+      "loss": 0.2631,
+      "step": 329000
+    },
+    {
+      "epoch": 7.67,
+      "eval_loss": 0.24531778693199158,
+      "eval_runtime": 1.4556,
+      "eval_samples_per_second": 1510.044,
+      "eval_steps_per_second": 24.045,
+      "step": 329000
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 9.282847086805059e-05,
+      "loss": 0.2636,
+      "step": 329500
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 9.239561891091853e-05,
+      "loss": 0.2631,
+      "step": 330000
+    },
+    {
+      "epoch": 7.69,
+      "eval_loss": 0.24822315573692322,
+      "eval_runtime": 1.4463,
+      "eval_samples_per_second": 1519.716,
+      "eval_steps_per_second": 24.199,
+      "step": 330000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.0223570961847653e+22,
+  "total_flos": 1.0543058100622153e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962905691e3e61901278bd35bae6a9e6802f21882ed0e962dd2ab116fea9b46f
+oid sha256:fe8e1879944525f3e680f804773ec89ad33764384906428a52a2c3c6871bf701
 size 102501541