Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6e0063168d01e8d9ad637627df35c664793162761ded8ac5e14cee0a39fa4b
+oid sha256:a05b029ed1927bee45376b9ec825ac1e6ad7ff6cc8cad870573ced24bc0e8a7a
 size 893440890

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcf9f6920ad5ded398eb8f93116f71e8adc7c3a91f6cd5c0da8e0f651bc8faf
+oid sha256:9c27e63159040ffd991f11430bcaa8ba43680821f717186a7bc3c221a468601c
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832b02611c12b9ad0dcde16a2bc02988c4f2b0b885960cfa4b9125a284bdeb99
-size 14244
+oid sha256:76f1055b9fbc745e8095815e2f9b0f2460e6416163d65d839c2d6bec7dc4f817
+size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfba27d7b6929b849933e9ae7d0e075a396ddca1f7f2a518e796268cde14302
+oid sha256:c55f5050853d52e8377712864d5685c98b2bc91dad2debd9776569f4616235b0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05,
-  "global_step": 50000,
+  "epoch": 0.06,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -376,11 +376,85 @@
       "eval_samples_per_second": 101.039,
       "eval_steps_per_second": 12.63,
       "step": 50000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.874997607785047e-05,
+      "loss": 0.497,
+      "step": 51000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.874990431166348e-05,
+      "loss": 0.498,
+      "step": 52000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.8749784702223863e-05,
+      "loss": 0.4921,
+      "step": 53000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.8749617250839647e-05,
+      "loss": 0.4876,
+      "step": 54000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8749401959342052e-05,
+      "loss": 0.483,
+      "step": 55000
+    },
+    {
+      "epoch": 0.06,
+      "eval_runtime": 3145.913,
+      "eval_samples_per_second": 107.966,
+      "eval_steps_per_second": 13.496,
+      "step": 55000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.874913883008547e-05,
+      "loss": 0.4809,
+      "step": 56000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8748827865947437e-05,
+      "loss": 0.4788,
+      "step": 57000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8748469070328614e-05,
+      "loss": 0.4767,
+      "step": 58000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8748062447152732e-05,
+      "loss": 0.475,
+      "step": 59000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.874760800086655e-05,
+      "loss": 0.4696,
+      "step": 60000
+    },
+    {
+      "epoch": 0.06,
+      "eval_runtime": 3128.1932,
+      "eval_samples_per_second": 108.578,
+      "eval_steps_per_second": 13.572,
+      "step": 60000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 4.427305086615552e+20,
+  "total_flos": 5.3127661039386624e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcf9f6920ad5ded398eb8f93116f71e8adc7c3a91f6cd5c0da8e0f651bc8faf
+oid sha256:9c27e63159040ffd991f11430bcaa8ba43680821f717186a7bc3c221a468601c
 size 454197066