Training in progress, step 50000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144ab11f29aad5086eb7e021e4229dc776bde464bdeb68571c460231f7e3d4db
+oid sha256:4b6e0063168d01e8d9ad637627df35c664793162761ded8ac5e14cee0a39fa4b
 size 893440890

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ba4cc15f1aa64c4904af07ad626b329074ee800b722742cb772b5f3107448b
+oid sha256:3bcf9f6920ad5ded398eb8f93116f71e8adc7c3a91f6cd5c0da8e0f651bc8faf
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24823f9423b69ce75c9be00b967bc60f7fb6bd2d410d5fef23d8bda17dae11b
+oid sha256:832b02611c12b9ad0dcde16a2bc02988c4f2b0b885960cfa4b9125a284bdeb99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7511346d6e23d46db8df4597671861c1d4ab566dbbf2c42030f6ce7dfc2c854d
+oid sha256:2cfba27d7b6929b849933e9ae7d0e075a396ddca1f7f2a518e796268cde14302
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04,
-  "global_step": 40000,
+  "epoch": 0.05,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -302,11 +302,85 @@
       "eval_samples_per_second": 111.653,
       "eval_steps_per_second": 13.957,
       "step": 40000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.5374999999999998e-05,
+      "loss": 0.5352,
+      "step": 41000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.5749999999999997e-05,
+      "loss": 0.5329,
+      "step": 42000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.6125e-05,
+      "loss": 0.5304,
+      "step": 43000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.6499999999999998e-05,
+      "loss": 0.5232,
+      "step": 44000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.6875e-05,
+      "loss": 0.5164,
+      "step": 45000
+    },
+    {
+      "epoch": 0.04,
+      "eval_runtime": 3334.4968,
+      "eval_samples_per_second": 101.86,
+      "eval_steps_per_second": 12.733,
+      "step": 45000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.725e-05,
+      "loss": 0.5133,
+      "step": 46000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.7624999999999998e-05,
+      "loss": 0.5104,
+      "step": 47000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 0.507,
+      "step": 48000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.8375e-05,
+      "loss": 0.5034,
+      "step": 49000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.875e-05,
+      "loss": 0.5007,
+      "step": 50000
+    },
+    {
+      "epoch": 0.05,
+      "eval_runtime": 3361.5856,
+      "eval_samples_per_second": 101.039,
+      "eval_steps_per_second": 12.63,
+      "step": 50000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 3.5418440692924416e+20,
+  "total_flos": 4.427305086615552e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ba4cc15f1aa64c4904af07ad626b329074ee800b722742cb772b5f3107448b
+oid sha256:3bcf9f6920ad5ded398eb8f93116f71e8adc7c3a91f6cd5c0da8e0f651bc8faf
 size 454197066