Training in progress, step 340000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b12d2d3c7e9c65fa1cdfdb5c2f4716c387d264ad1a9842602482f2263f5d461
+oid sha256:9697a4208e91543945338a4f4e4b0865355f4f56763ee61fbd92200c086baa3e
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe8e1879944525f3e680f804773ec89ad33764384906428a52a2c3c6871bf701
+oid sha256:724b6d72f0d9d61428cae11f63e8d73911644650c2b3a36828f03dde6fa5b8fd
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
+oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
+oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
+oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
+oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
+oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
+oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
+oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0bcb5dadf85017bb8728dac44f541535faed64c5ae748a5ae3b2a144ca0708
+oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636cb28fce30ad56f68aface20193360fd815697da4c2ec39f5ca647b5e6b45b
+oid sha256:4a0f100ea6da4a9ff03fc2cc9b0cbbba13b42ccc41293a1d6143e5a081a97f70
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.688902350940143,
-  "global_step": 330000,
+  "epoch": 7.921899391877723,
+  "global_step": 340000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6606,11 +6606,211 @@
       "eval_samples_per_second": 1519.716,
       "eval_steps_per_second": 24.199,
       "step": 330000
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 9.196345158526793e-05,
+      "loss": 0.2632,
+      "step": 330500
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 9.153197361721149e-05,
+      "loss": 0.263,
+      "step": 331000
+    },
+    {
+      "epoch": 7.71,
+      "eval_loss": 0.24357490241527557,
+      "eval_runtime": 1.4413,
+      "eval_samples_per_second": 1524.993,
+      "eval_steps_per_second": 24.283,
+      "step": 331000
+    },
+    {
+      "epoch": 7.72,
+      "learning_rate": 9.110118972532302e-05,
+      "loss": 0.2627,
+      "step": 331500
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 9.067110462058634e-05,
+      "loss": 0.2631,
+      "step": 332000
+    },
+    {
+      "epoch": 7.74,
+      "eval_loss": 0.2456502616405487,
+      "eval_runtime": 1.4523,
+      "eval_samples_per_second": 1513.463,
+      "eval_steps_per_second": 24.1,
+      "step": 332000
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 9.024172300634305e-05,
+      "loss": 0.2629,
+      "step": 332500
+    },
+    {
+      "epoch": 7.76,
+      "learning_rate": 8.981304957824182e-05,
+      "loss": 0.2629,
+      "step": 333000
+    },
+    {
+      "epoch": 7.76,
+      "eval_loss": 0.2470385730266571,
+      "eval_runtime": 1.4527,
+      "eval_samples_per_second": 1513.011,
+      "eval_steps_per_second": 24.093,
+      "step": 333000
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 8.938508902418643e-05,
+      "loss": 0.2623,
+      "step": 333500
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 8.89578460242851e-05,
+      "loss": 0.2626,
+      "step": 334000
+    },
+    {
+      "epoch": 7.78,
+      "eval_loss": 0.24880406260490417,
+      "eval_runtime": 1.4245,
+      "eval_samples_per_second": 1543.039,
+      "eval_steps_per_second": 24.571,
+      "step": 334000
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 8.85313252507988e-05,
+      "loss": 0.2621,
+      "step": 334500
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 8.810553136809027e-05,
+      "loss": 0.2626,
+      "step": 335000
+    },
+    {
+      "epoch": 7.81,
+      "eval_loss": 0.2465057224035263,
+      "eval_runtime": 1.453,
+      "eval_samples_per_second": 1512.782,
+      "eval_steps_per_second": 24.089,
+      "step": 335000
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 8.76804690325733e-05,
+      "loss": 0.2622,
+      "step": 335500
+    },
+    {
+      "epoch": 7.83,
+      "learning_rate": 8.725614289266137e-05,
+      "loss": 0.2623,
+      "step": 336000
+    },
+    {
+      "epoch": 7.83,
+      "eval_loss": 0.24810338020324707,
+      "eval_runtime": 1.4394,
+      "eval_samples_per_second": 1526.974,
+      "eval_steps_per_second": 24.315,
+      "step": 336000
+    },
+    {
+      "epoch": 7.84,
+      "learning_rate": 8.683255758871734e-05,
+      "loss": 0.2627,
+      "step": 336500
+    },
+    {
+      "epoch": 7.85,
+      "learning_rate": 8.640971775300207e-05,
+      "loss": 0.2624,
+      "step": 337000
+    },
+    {
+      "epoch": 7.85,
+      "eval_loss": 0.24493196606636047,
+      "eval_runtime": 1.4281,
+      "eval_samples_per_second": 1539.133,
+      "eval_steps_per_second": 24.508,
+      "step": 337000
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 8.598762800962431e-05,
+      "loss": 0.2625,
+      "step": 337500
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 8.55662929744899e-05,
+      "loss": 0.2623,
+      "step": 338000
+    },
+    {
+      "epoch": 7.88,
+      "eval_loss": 0.2459965944290161,
+      "eval_runtime": 1.463,
+      "eval_samples_per_second": 1502.342,
+      "eval_steps_per_second": 23.923,
+      "step": 338000
+    },
+    {
+      "epoch": 7.89,
+      "learning_rate": 8.514571725525124e-05,
+      "loss": 0.2626,
+      "step": 338500
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 8.47259054512571e-05,
+      "loss": 0.2626,
+      "step": 339000
+    },
+    {
+      "epoch": 7.9,
+      "eval_loss": 0.24472270905971527,
+      "eval_runtime": 1.4079,
+      "eval_samples_per_second": 1561.143,
+      "eval_steps_per_second": 24.859,
+      "step": 339000
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 8.430686215350198e-05,
+      "loss": 0.2624,
+      "step": 339500
+    },
+    {
+      "epoch": 7.92,
+      "learning_rate": 8.388859194457636e-05,
+      "loss": 0.262,
+      "step": 340000
+    },
+    {
+      "epoch": 7.92,
+      "eval_loss": 0.24556826055049896,
+      "eval_runtime": 1.3884,
+      "eval_samples_per_second": 1583.125,
+      "eval_steps_per_second": 25.209,
+      "step": 340000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.0543058100622153e+22,
+  "total_flos": 1.0862545239396653e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe8e1879944525f3e680f804773ec89ad33764384906428a52a2c3c6871bf701
+oid sha256:724b6d72f0d9d61428cae11f63e8d73911644650c2b3a36828f03dde6fa5b8fd
 size 102501541