Training in progress, step 350000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70f0de01be5fcc7537de81ac336cef4498cd2899bb7ea7761980f3fb9003a0f
+oid sha256:7fe20f9a7048e778f6f933d7208f0d74ea50740d5e42b03ab00e70891186e444
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20cd52574261829d86d2a5ad2e1ec4588da3ef0a45a350a2067e301217ba680c
+oid sha256:9b416d6314d39e9369d9492ca6e3f40f06cfe57d4e4160d5311194f08695a8e6
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
+oid sha256:fb525c3a5a5b20b39f1725d61547b357ecdab21b75b423ee22380919a8bde5bb
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
+oid sha256:fb525c3a5a5b20b39f1725d61547b357ecdab21b75b423ee22380919a8bde5bb
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
+oid sha256:fb525c3a5a5b20b39f1725d61547b357ecdab21b75b423ee22380919a8bde5bb
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
+oid sha256:fb525c3a5a5b20b39f1725d61547b357ecdab21b75b423ee22380919a8bde5bb
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
+oid sha256:fb525c3a5a5b20b39f1725d61547b357ecdab21b75b423ee22380919a8bde5bb
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
+oid sha256:fb525c3a5a5b20b39f1725d61547b357ecdab21b75b423ee22380919a8bde5bb
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
+oid sha256:fb525c3a5a5b20b39f1725d61547b357ecdab21b75b423ee22380919a8bde5bb
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
+oid sha256:fb525c3a5a5b20b39f1725d61547b357ecdab21b75b423ee22380919a8bde5bb
 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": 8.665069575411591,
-  "global_step": 340000,
+  "epoch": 8.919924562923697,
+  "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": 774.959,
       "eval_steps_per_second": 12.399,
       "step": 340000
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 8.347109939861605e-05,
+      "loss": 0.2778,
+      "step": 340500
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 8.305438908125285e-05,
+      "loss": 0.2773,
+      "step": 341000
+    },
+    {
+      "epoch": 8.69,
+      "eval_loss": 0.8103182315826416,
+      "eval_runtime": 1.3256,
+      "eval_samples_per_second": 754.398,
+      "eval_steps_per_second": 12.07,
+      "step": 341000
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 8.263846554956402e-05,
+      "loss": 0.2776,
+      "step": 341500
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 8.222333335202254e-05,
+      "loss": 0.2779,
+      "step": 342000
+    },
+    {
+      "epoch": 8.72,
+      "eval_loss": 0.8094441294670105,
+      "eval_runtime": 1.28,
+      "eval_samples_per_second": 781.22,
+      "eval_steps_per_second": 12.5,
+      "step": 342000
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 8.18089970284477e-05,
+      "loss": 0.2783,
+      "step": 342500
+    },
+    {
+      "epoch": 8.74,
+      "learning_rate": 8.1395461109955e-05,
+      "loss": 0.2777,
+      "step": 343000
+    },
+    {
+      "epoch": 8.74,
+      "eval_loss": 0.802370548248291,
+      "eval_runtime": 1.2621,
+      "eval_samples_per_second": 792.35,
+      "eval_steps_per_second": 12.678,
+      "step": 343000
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 8.098273011890726e-05,
+      "loss": 0.2772,
+      "step": 343500
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 8.057080856886426e-05,
+      "loss": 0.277,
+      "step": 344000
+    },
+    {
+      "epoch": 8.77,
+      "eval_loss": 0.8032689094543457,
+      "eval_runtime": 1.2677,
+      "eval_samples_per_second": 788.842,
+      "eval_steps_per_second": 12.621,
+      "step": 344000
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 8.015970096453414e-05,
+      "loss": 0.2771,
+      "step": 344500
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 7.974941180172382e-05,
+      "loss": 0.2771,
+      "step": 345000
+    },
+    {
+      "epoch": 8.79,
+      "eval_loss": 0.8085340857505798,
+      "eval_runtime": 1.2759,
+      "eval_samples_per_second": 783.767,
+      "eval_steps_per_second": 12.54,
+      "step": 345000
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 7.933994556728976e-05,
+      "loss": 0.2768,
+      "step": 345500
+    },
+    {
+      "epoch": 8.82,
+      "learning_rate": 7.893130673908927e-05,
+      "loss": 0.2773,
+      "step": 346000
+    },
+    {
+      "epoch": 8.82,
+      "eval_loss": 0.8130091428756714,
+      "eval_runtime": 1.2476,
+      "eval_samples_per_second": 801.539,
+      "eval_steps_per_second": 12.825,
+      "step": 346000
+    },
+    {
+      "epoch": 8.83,
+      "learning_rate": 7.852349978593091e-05,
+      "loss": 0.2774,
+      "step": 346500
+    },
+    {
+      "epoch": 8.84,
+      "learning_rate": 7.811652916752633e-05,
+      "loss": 0.2775,
+      "step": 347000
+    },
+    {
+      "epoch": 8.84,
+      "eval_loss": 0.8052127957344055,
+      "eval_runtime": 1.2887,
+      "eval_samples_per_second": 775.993,
+      "eval_steps_per_second": 12.416,
+      "step": 347000
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 7.771039933444092e-05,
+      "loss": 0.2771,
+      "step": 347500
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 7.730511472804544e-05,
+      "loss": 0.2769,
+      "step": 348000
+    },
+    {
+      "epoch": 8.87,
+      "eval_loss": 0.804824948310852,
+      "eval_runtime": 1.2577,
+      "eval_samples_per_second": 795.106,
+      "eval_steps_per_second": 12.722,
+      "step": 348000
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 7.690067978046758e-05,
+      "loss": 0.2767,
+      "step": 348500
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 7.649709891454298e-05,
+      "loss": 0.2769,
+      "step": 349000
+    },
+    {
+      "epoch": 8.89,
+      "eval_loss": 0.8068578839302063,
+      "eval_runtime": 1.3222,
+      "eval_samples_per_second": 756.317,
+      "eval_steps_per_second": 12.101,
+      "step": 349000
+    },
+    {
+      "epoch": 8.91,
+      "learning_rate": 7.609437654376742e-05,
+      "loss": 0.277,
+      "step": 349500
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 7.569251707224812e-05,
+      "loss": 0.2774,
+      "step": 350000
+    },
+    {
+      "epoch": 8.92,
+      "eval_loss": 0.8125748038291931,
+      "eval_runtime": 1.2634,
+      "eval_samples_per_second": 791.502,
+      "eval_steps_per_second": 12.664,
+      "step": 350000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.086245488702864e+22,
+  "total_flos": 1.118194202580314e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20cd52574261829d86d2a5ad2e1ec4588da3ef0a45a350a2067e301217ba680c
+oid sha256:9b416d6314d39e9369d9492ca6e3f40f06cfe57d4e4160d5311194f08695a8e6
 size 102501541