Training in progress, step 340000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09a56e384d254aab855de1a90b785089bbc79d5ef77280cdbfcb35429d430ef
+oid sha256:04771db8bd1f33900edfa684667fd4cf02cabbcb49e84db3d0f1e9a8ca0ae8a9
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee0432d69ea3db4e0974a82daf7e165933af59ea7da9e58c52fdbc3c819eb79
+oid sha256:ee15a0abd466e3b28029d33761b33f84fe8353f7b59b9970581bfe0c3b7fa88c
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f34aa486628a314eb93527ad668c85f3fc184218448636c799c09cb7973109e
+oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f34aa486628a314eb93527ad668c85f3fc184218448636c799c09cb7973109e
+oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f34aa486628a314eb93527ad668c85f3fc184218448636c799c09cb7973109e
+oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f34aa486628a314eb93527ad668c85f3fc184218448636c799c09cb7973109e
+oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f34aa486628a314eb93527ad668c85f3fc184218448636c799c09cb7973109e
+oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f34aa486628a314eb93527ad668c85f3fc184218448636c799c09cb7973109e
+oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f34aa486628a314eb93527ad668c85f3fc184218448636c799c09cb7973109e
+oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f34aa486628a314eb93527ad668c85f3fc184218448636c799c09cb7973109e
+oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
 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": 7.360813704496788,
-  "global_step": 330000,
+  "epoch": 7.583868665239115,
+  "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": 1117.004,
       "eval_steps_per_second": 17.506,
       "step": 330000
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 9.196345158526793e-05,
+      "loss": 0.2655,
+      "step": 330500
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 9.153197361721149e-05,
+      "loss": 0.2653,
+      "step": 331000
+    },
+    {
+      "epoch": 7.38,
+      "eval_loss": 0.24651852250099182,
+      "eval_runtime": 1.9849,
+      "eval_samples_per_second": 1157.249,
+      "eval_steps_per_second": 18.137,
+      "step": 331000
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 9.110118972532302e-05,
+      "loss": 0.2652,
+      "step": 331500
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 9.067110462058634e-05,
+      "loss": 0.2656,
+      "step": 332000
+    },
+    {
+      "epoch": 7.41,
+      "eval_loss": 0.24983063340187073,
+      "eval_runtime": 1.9337,
+      "eval_samples_per_second": 1187.894,
+      "eval_steps_per_second": 18.617,
+      "step": 332000
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 9.024172300634305e-05,
+      "loss": 0.2655,
+      "step": 332500
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 8.981304957824182e-05,
+      "loss": 0.2655,
+      "step": 333000
+    },
+    {
+      "epoch": 7.43,
+      "eval_loss": 0.2502962350845337,
+      "eval_runtime": 2.0089,
+      "eval_samples_per_second": 1143.431,
+      "eval_steps_per_second": 17.921,
+      "step": 333000
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 8.938508902418643e-05,
+      "loss": 0.2651,
+      "step": 333500
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 8.89578460242851e-05,
+      "loss": 0.265,
+      "step": 334000
+    },
+    {
+      "epoch": 7.45,
+      "eval_loss": 0.2484452873468399,
+      "eval_runtime": 1.9509,
+      "eval_samples_per_second": 1177.421,
+      "eval_steps_per_second": 18.453,
+      "step": 334000
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 8.85313252507988e-05,
+      "loss": 0.265,
+      "step": 334500
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 8.810553136809027e-05,
+      "loss": 0.2651,
+      "step": 335000
+    },
+    {
+      "epoch": 7.47,
+      "eval_loss": 0.24745772778987885,
+      "eval_runtime": 2.0372,
+      "eval_samples_per_second": 1127.544,
+      "eval_steps_per_second": 17.672,
+      "step": 335000
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 8.76804690325733e-05,
+      "loss": 0.2649,
+      "step": 335500
+    },
+    {
+      "epoch": 7.49,
+      "learning_rate": 8.725614289266137e-05,
+      "loss": 0.2647,
+      "step": 336000
+    },
+    {
+      "epoch": 7.49,
+      "eval_loss": 0.24857033789157867,
+      "eval_runtime": 2.0353,
+      "eval_samples_per_second": 1128.559,
+      "eval_steps_per_second": 17.687,
+      "step": 336000
+    },
+    {
+      "epoch": 7.51,
+      "learning_rate": 8.683255758871734e-05,
+      "loss": 0.2649,
+      "step": 336500
+    },
+    {
+      "epoch": 7.52,
+      "learning_rate": 8.640971775300207e-05,
+      "loss": 0.2654,
+      "step": 337000
+    },
+    {
+      "epoch": 7.52,
+      "eval_loss": 0.24552865326404572,
+      "eval_runtime": 2.0136,
+      "eval_samples_per_second": 1140.751,
+      "eval_steps_per_second": 17.879,
+      "step": 337000
+    },
+    {
+      "epoch": 7.53,
+      "learning_rate": 8.598762800962431e-05,
+      "loss": 0.2767,
+      "step": 337500
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 8.55662929744899e-05,
+      "loss": 0.2655,
+      "step": 338000
+    },
+    {
+      "epoch": 7.54,
+      "eval_loss": 0.24788717925548553,
+      "eval_runtime": 2.0497,
+      "eval_samples_per_second": 1120.627,
+      "eval_steps_per_second": 17.563,
+      "step": 338000
+    },
+    {
+      "epoch": 7.55,
+      "learning_rate": 8.514571725525124e-05,
+      "loss": 0.2666,
+      "step": 338500
+    },
+    {
+      "epoch": 7.56,
+      "learning_rate": 8.47259054512571e-05,
+      "loss": 0.2678,
+      "step": 339000
+    },
+    {
+      "epoch": 7.56,
+      "eval_loss": 0.24549083411693573,
+      "eval_runtime": 2.0079,
+      "eval_samples_per_second": 1143.957,
+      "eval_steps_per_second": 17.929,
+      "step": 339000
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 8.430686215350198e-05,
+      "loss": 0.265,
+      "step": 339500
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 8.388859194457636e-05,
+      "loss": 0.265,
+      "step": 340000
+    },
+    {
+      "epoch": 7.58,
+      "eval_loss": 0.24893943965435028,
+      "eval_runtime": 2.0535,
+      "eval_samples_per_second": 1118.576,
+      "eval_steps_per_second": 17.531,
+      "step": 340000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.0542876399728593e+22,
+  "total_flos": 1.0862363538503093e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee0432d69ea3db4e0974a82daf7e165933af59ea7da9e58c52fdbc3c819eb79
+oid sha256:ee15a0abd466e3b28029d33761b33f84fe8353f7b59b9970581bfe0c3b7fa88c
 size 102501541