Training in progress, step 350000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04771db8bd1f33900edfa684667fd4cf02cabbcb49e84db3d0f1e9a8ca0ae8a9
+oid sha256:8e2593684e29fbdab18ceae698c9db337e08a0411716ce5539ab2231b908aa6e
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee15a0abd466e3b28029d33761b33f84fe8353f7b59b9970581bfe0c3b7fa88c
+oid sha256:aaa6c11004791ef4e8c50d4145229be69aa0fee3306608bd403b2eb4d637219a
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
+oid sha256:2250a0c64e809cea437709ab2245b0ac11e166c80e52d01a00381d2aba90145d
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
+oid sha256:2250a0c64e809cea437709ab2245b0ac11e166c80e52d01a00381d2aba90145d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
+oid sha256:2250a0c64e809cea437709ab2245b0ac11e166c80e52d01a00381d2aba90145d
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
+oid sha256:2250a0c64e809cea437709ab2245b0ac11e166c80e52d01a00381d2aba90145d
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
+oid sha256:2250a0c64e809cea437709ab2245b0ac11e166c80e52d01a00381d2aba90145d
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
+oid sha256:2250a0c64e809cea437709ab2245b0ac11e166c80e52d01a00381d2aba90145d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
+oid sha256:2250a0c64e809cea437709ab2245b0ac11e166c80e52d01a00381d2aba90145d
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7057868b53c4e1dbbc7c1656971b5b184ea1a0e982e3960a18a5c5003eb8ed2
+oid sha256:2250a0c64e809cea437709ab2245b0ac11e166c80e52d01a00381d2aba90145d
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0f100ea6da4a9ff03fc2cc9b0cbbba13b42ccc41293a1d6143e5a081a97f70
+oid sha256:3aecc6465a886ff601ea303358a61f89a30e07c965e206675258095a3d963058
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.583868665239115,
-  "global_step": 340000,
+  "epoch": 7.806923625981442,
+  "global_step": 350000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6806,11 +6806,211 @@
       "eval_samples_per_second": 1118.576,
       "eval_steps_per_second": 17.531,
       "step": 340000
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 8.347109939861605e-05,
+      "loss": 0.2675,
+      "step": 340500
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 8.305438908125285e-05,
+      "loss": 0.2649,
+      "step": 341000
+    },
+    {
+      "epoch": 7.61,
+      "eval_loss": 0.2475811243057251,
+      "eval_runtime": 2.0091,
+      "eval_samples_per_second": 1143.275,
+      "eval_steps_per_second": 17.918,
+      "step": 341000
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 8.263846554956402e-05,
+      "loss": 0.2659,
+      "step": 341500
+    },
+    {
+      "epoch": 7.63,
+      "learning_rate": 8.222333335202254e-05,
+      "loss": 0.2649,
+      "step": 342000
+    },
+    {
+      "epoch": 7.63,
+      "eval_loss": 0.2466391623020172,
+      "eval_runtime": 2.0704,
+      "eval_samples_per_second": 1109.463,
+      "eval_steps_per_second": 17.388,
+      "step": 342000
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 8.18089970284477e-05,
+      "loss": 0.2646,
+      "step": 342500
+    },
+    {
+      "epoch": 7.65,
+      "learning_rate": 8.1395461109955e-05,
+      "loss": 0.2645,
+      "step": 343000
+    },
+    {
+      "epoch": 7.65,
+      "eval_loss": 0.24718651175498962,
+      "eval_runtime": 2.0893,
+      "eval_samples_per_second": 1099.419,
+      "eval_steps_per_second": 17.231,
+      "step": 343000
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 8.098273011890726e-05,
+      "loss": 0.2654,
+      "step": 343500
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 8.057080856886426e-05,
+      "loss": 0.2676,
+      "step": 344000
+    },
+    {
+      "epoch": 7.67,
+      "eval_loss": 0.2473945915699005,
+      "eval_runtime": 1.9984,
+      "eval_samples_per_second": 1149.403,
+      "eval_steps_per_second": 18.014,
+      "step": 344000
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 8.015970096453414e-05,
+      "loss": 0.2655,
+      "step": 344500
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 7.974941180172382e-05,
+      "loss": 0.265,
+      "step": 345000
+    },
+    {
+      "epoch": 7.7,
+      "eval_loss": 0.24670176208019257,
+      "eval_runtime": 2.0516,
+      "eval_samples_per_second": 1119.641,
+      "eval_steps_per_second": 17.548,
+      "step": 345000
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 7.933994556728976e-05,
+      "loss": 0.2648,
+      "step": 345500
+    },
+    {
+      "epoch": 7.72,
+      "learning_rate": 7.893130673908927e-05,
+      "loss": 0.2666,
+      "step": 346000
+    },
+    {
+      "epoch": 7.72,
+      "eval_loss": 0.24692493677139282,
+      "eval_runtime": 2.0097,
+      "eval_samples_per_second": 1142.931,
+      "eval_steps_per_second": 17.913,
+      "step": 346000
+    },
+    {
+      "epoch": 7.73,
+      "learning_rate": 7.852349978593091e-05,
+      "loss": 0.2645,
+      "step": 346500
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 7.811652916752633e-05,
+      "loss": 0.2645,
+      "step": 347000
+    },
+    {
+      "epoch": 7.74,
+      "eval_loss": 0.24660193920135498,
+      "eval_runtime": 2.0554,
+      "eval_samples_per_second": 1117.529,
+      "eval_steps_per_second": 17.515,
+      "step": 347000
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 7.771039933444092e-05,
+      "loss": 0.2644,
+      "step": 347500
+    },
+    {
+      "epoch": 7.76,
+      "learning_rate": 7.730511472804544e-05,
+      "loss": 0.2636,
+      "step": 348000
+    },
+    {
+      "epoch": 7.76,
+      "eval_loss": 0.248375803232193,
+      "eval_runtime": 1.9897,
+      "eval_samples_per_second": 1154.427,
+      "eval_steps_per_second": 18.093,
+      "step": 348000
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 7.690067978046758e-05,
+      "loss": 0.2637,
+      "step": 348500
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 7.649709891454298e-05,
+      "loss": 0.2632,
+      "step": 349000
+    },
+    {
+      "epoch": 7.78,
+      "eval_loss": 0.24848568439483643,
+      "eval_runtime": 2.0056,
+      "eval_samples_per_second": 1145.314,
+      "eval_steps_per_second": 17.95,
+      "step": 349000
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 7.609437654376742e-05,
+      "loss": 0.2636,
+      "step": 349500
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 7.569251707224812e-05,
+      "loss": 0.2635,
+      "step": 350000
+    },
+    {
+      "epoch": 7.81,
+      "eval_loss": 0.24438388645648956,
+      "eval_runtime": 2.0031,
+      "eval_samples_per_second": 1146.703,
+      "eval_steps_per_second": 17.972,
+      "step": 350000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.0862363538503093e+22,
+  "total_flos": 1.1181850677277593e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee15a0abd466e3b28029d33761b33f84fe8353f7b59b9970581bfe0c3b7fa88c
+oid sha256:aaa6c11004791ef4e8c50d4145229be69aa0fee3306608bd403b2eb4d637219a
 size 102501541