Training in progress, step 390000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f4969533102642963b0b2227bcca65da739e93c9ba93ada329fad00247349b
+oid sha256:e3ec63277b76b09811bbdd2d480a7f996b4a3ffed8bebe328de7594fd1352f61
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31402a0bcc9e6eb51374c53180861ce7a4f03142fd97638776d46c6dc480c809
+oid sha256:d2b105f9c88c11eebbcdaeb34a846701e3b5103c2b4d7fbe6a23d3a666e3272c
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942041c29d1b42261564b880acf9a06c922c5e2ec40da67c47a0bff66b113b4
+oid sha256:3030b698db0941f5555a8625c40cb49a93fb370be875ba63b732087f65663441
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942041c29d1b42261564b880acf9a06c922c5e2ec40da67c47a0bff66b113b4
+oid sha256:3030b698db0941f5555a8625c40cb49a93fb370be875ba63b732087f65663441
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942041c29d1b42261564b880acf9a06c922c5e2ec40da67c47a0bff66b113b4
+oid sha256:3030b698db0941f5555a8625c40cb49a93fb370be875ba63b732087f65663441
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942041c29d1b42261564b880acf9a06c922c5e2ec40da67c47a0bff66b113b4
+oid sha256:3030b698db0941f5555a8625c40cb49a93fb370be875ba63b732087f65663441
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942041c29d1b42261564b880acf9a06c922c5e2ec40da67c47a0bff66b113b4
+oid sha256:3030b698db0941f5555a8625c40cb49a93fb370be875ba63b732087f65663441
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942041c29d1b42261564b880acf9a06c922c5e2ec40da67c47a0bff66b113b4
+oid sha256:3030b698db0941f5555a8625c40cb49a93fb370be875ba63b732087f65663441
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942041c29d1b42261564b880acf9a06c922c5e2ec40da67c47a0bff66b113b4
+oid sha256:3030b698db0941f5555a8625c40cb49a93fb370be875ba63b732087f65663441
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942041c29d1b42261564b880acf9a06c922c5e2ec40da67c47a0bff66b113b4
+oid sha256:3030b698db0941f5555a8625c40cb49a93fb370be875ba63b732087f65663441
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2047b5f47fc3de929bb0738f7fbdd248300ab063f6fd4eddcabc29f5482852
+oid sha256:864647684ab3694f7aa2a258c1806e10c4abf99f67ed5e54443050e485ac9436
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.853887555628043,
-  "global_step": 380000,
+  "epoch": 9.086884596565623,
+  "global_step": 390000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7606,11 +7606,211 @@
       "eval_samples_per_second": 1520.737,
       "eval_steps_per_second": 24.216,
       "step": 380000
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 5.2979369233306834e-05,
+      "loss": 0.2576,
+      "step": 380500
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 5.26391878673975e-05,
+      "loss": 0.2573,
+      "step": 381000
+    },
+    {
+      "epoch": 8.88,
+      "eval_loss": 0.2407015562057495,
+      "eval_runtime": 1.4434,
+      "eval_samples_per_second": 1522.761,
+      "eval_steps_per_second": 24.248,
+      "step": 381000
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 5.230012590292987e-05,
+      "loss": 0.2575,
+      "step": 381500
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 5.1962187047831517e-05,
+      "loss": 0.2575,
+      "step": 382000
+    },
+    {
+      "epoch": 8.9,
+      "eval_loss": 0.2418326437473297,
+      "eval_runtime": 1.4362,
+      "eval_samples_per_second": 1530.452,
+      "eval_steps_per_second": 24.37,
+      "step": 382000
+    },
+    {
+      "epoch": 8.91,
+      "learning_rate": 5.162537499774743e-05,
+      "loss": 0.2574,
+      "step": 382500
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 5.128969343600032e-05,
+      "loss": 0.2573,
+      "step": 383000
+    },
+    {
+      "epoch": 8.92,
+      "eval_loss": 0.2397920787334442,
+      "eval_runtime": 1.4505,
+      "eval_samples_per_second": 1515.368,
+      "eval_steps_per_second": 24.13,
+      "step": 383000
+    },
+    {
+      "epoch": 8.94,
+      "learning_rate": 5.09551460335499e-05,
+      "loss": 0.2571,
+      "step": 383500
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 5.062173644895296e-05,
+      "loss": 0.2573,
+      "step": 384000
+    },
+    {
+      "epoch": 8.95,
+      "eval_loss": 0.23995496332645416,
+      "eval_runtime": 1.4711,
+      "eval_samples_per_second": 1494.15,
+      "eval_steps_per_second": 23.792,
+      "step": 384000
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 5.0289468328323434e-05,
+      "loss": 0.2569,
+      "step": 384500
+    },
+    {
+      "epoch": 8.97,
+      "learning_rate": 4.995834530529208e-05,
+      "loss": 0.2569,
+      "step": 385000
+    },
+    {
+      "epoch": 8.97,
+      "eval_loss": 0.23903849720954895,
+      "eval_runtime": 1.4433,
+      "eval_samples_per_second": 1522.946,
+      "eval_steps_per_second": 24.251,
+      "step": 385000
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 4.9628371000967394e-05,
+      "loss": 0.2573,
+      "step": 385500
+    },
+    {
+      "epoch": 8.99,
+      "learning_rate": 4.929954902389534e-05,
+      "loss": 0.2572,
+      "step": 386000
+    },
+    {
+      "epoch": 8.99,
+      "eval_loss": 0.23725509643554688,
+      "eval_runtime": 1.4864,
+      "eval_samples_per_second": 1478.786,
+      "eval_steps_per_second": 23.548,
+      "step": 386000
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 4.897188297002046e-05,
+      "loss": 0.2571,
+      "step": 386500
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 4.8645376422646226e-05,
+      "loss": 0.2566,
+      "step": 387000
+    },
+    {
+      "epoch": 9.02,
+      "eval_loss": 0.24057132005691528,
+      "eval_runtime": 1.4509,
+      "eval_samples_per_second": 1514.911,
+      "eval_steps_per_second": 24.123,
+      "step": 387000
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 4.832003295239591e-05,
+      "loss": 0.2568,
+      "step": 387500
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 4.7995856117173624e-05,
+      "loss": 0.2565,
+      "step": 388000
+    },
+    {
+      "epoch": 9.04,
+      "eval_loss": 0.23878733813762665,
+      "eval_runtime": 1.3617,
+      "eval_samples_per_second": 1614.217,
+      "eval_steps_per_second": 25.704,
+      "step": 388000
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 4.767284946212521e-05,
+      "loss": 0.2567,
+      "step": 388500
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 4.735101651959977e-05,
+      "loss": 0.2566,
+      "step": 389000
+    },
+    {
+      "epoch": 9.06,
+      "eval_loss": 0.23982606828212738,
+      "eval_runtime": 1.4089,
+      "eval_samples_per_second": 1560.06,
+      "eval_steps_per_second": 24.842,
+      "step": 389000
+    },
+    {
+      "epoch": 9.08,
+      "learning_rate": 4.7030360809110754e-05,
+      "loss": 0.2564,
+      "step": 389500
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 4.6710885837297726e-05,
+      "loss": 0.2564,
+      "step": 390000
+    },
+    {
+      "epoch": 9.09,
+      "eval_loss": 0.24110108613967896,
+      "eval_runtime": 1.4757,
+      "eval_samples_per_second": 1489.497,
+      "eval_steps_per_second": 23.718,
+      "step": 390000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.2140491297503746e+22,
+  "total_flos": 1.245997593928734e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31402a0bcc9e6eb51374c53180861ce7a4f03142fd97638776d46c6dc480c809
+oid sha256:d2b105f9c88c11eebbcdaeb34a846701e3b5103c2b4d7fbe6a23d3a666e3272c
 size 102501541