Training in progress, step 380000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5937fbf5a223bdee412711090b2afe19ccd59cb5aa00ff257849fe3abbc0df
+oid sha256:a7d80b5fe4b73581493fbf7e8d5375ba0cc27fca0abae2f649940dc93608ed91
 size 893441530

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb18529144e5631f4110d550e5ae8dec1ab66ae10143ec11a390bb4bb1168003
+oid sha256:eaf5cca6f5ad9c15d0fba6e119e98e99e1b26c717ce470e245593e0001049d48
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57495da3e14701eaa78ba01626380cf06c08d77e93ad6e4f3e1fa2ad42d22c6c
+oid sha256:fda2635cf5eb97c959b3473ee8ed882086ce2dab72fcbeb241e25a40c966b7bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bbce26cd1d82261c68bda952c3a8a3f941ff6e36a11d4fea5bc7113b3bffa2
+oid sha256:b42df27cb36c10cd745fac26ea88f136bc616f898f1fd1486819c4852d2c54f3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37,
-  "global_step": 370000,
+  "epoch": 0.38,
+  "global_step": 380000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2744,11 +2744,85 @@
       "eval_samples_per_second": 107.338,
       "eval_steps_per_second": 13.417,
       "step": 370000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.650798260743744e-05,
+      "loss": 0.3488,
+      "step": 371000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6495339059660347e-05,
+      "loss": 0.3483,
+      "step": 372000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6482672324195004e-05,
+      "loss": 0.3477,
+      "step": 373000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6469982539562804e-05,
+      "loss": 0.3446,
+      "step": 374000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.6457269844537196e-05,
+      "loss": 0.3442,
+      "step": 375000
+    },
+    {
+      "epoch": 0.38,
+      "eval_runtime": 3159.753,
+      "eval_samples_per_second": 107.493,
+      "eval_steps_per_second": 13.437,
+      "step": 375000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.644453437814218e-05,
+      "loss": 0.3423,
+      "step": 376000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.643177627965077e-05,
+      "loss": 0.3422,
+      "step": 377000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.641899568858349e-05,
+      "loss": 0.3442,
+      "step": 378000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.640619274470684e-05,
+      "loss": 0.3418,
+      "step": 379000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.639336758803176e-05,
+      "loss": 0.3446,
+      "step": 380000
+    },
+    {
+      "epoch": 0.38,
+      "eval_runtime": 3155.9637,
+      "eval_samples_per_second": 107.622,
+      "eval_steps_per_second": 13.453,
+      "step": 380000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 3.2762057640955085e+21,
+  "total_flos": 3.3647518658278195e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb18529144e5631f4110d550e5ae8dec1ab66ae10143ec11a390bb4bb1168003
+oid sha256:eaf5cca6f5ad9c15d0fba6e119e98e99e1b26c717ce470e245593e0001049d48
 size 454197066