Training in progress, step 390000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d80b5fe4b73581493fbf7e8d5375ba0cc27fca0abae2f649940dc93608ed91
+oid sha256:ea287e9b4ef69b399ab26f5a72f16419f78692f80f4478f9dc9fde54c01b3139
 size 893441530

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaf5cca6f5ad9c15d0fba6e119e98e99e1b26c717ce470e245593e0001049d48
+oid sha256:0754eb41ff5a1456b603e8b2753adb511ac0a9ee839b9d73f658f3c72064f5ce
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda2635cf5eb97c959b3473ee8ed882086ce2dab72fcbeb241e25a40c966b7bf
+oid sha256:ea76d909d3c482cb352315f678531422d38691040b817f22cbe42d6a4283267d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b42df27cb36c10cd745fac26ea88f136bc616f898f1fd1486819c4852d2c54f3
+oid sha256:ceb7667759b15c886ebe5f226629aa0745d8db84769a12c7b2d7c8d4d08bd35a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.38,
-  "global_step": 380000,
+  "epoch": 0.39,
+  "global_step": 390000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2818,11 +2818,85 @@
       "eval_samples_per_second": 107.622,
       "eval_steps_per_second": 13.453,
       "step": 380000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.6380520358812106e-05,
+      "loss": 0.3466,
+      "step": 381000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.636765119754312e-05,
+      "loss": 0.345,
+      "step": 382000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.635476024495989e-05,
+      "loss": 0.3439,
+      "step": 383000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.6341847642035807e-05,
+      "loss": 0.3447,
+      "step": 384000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.632891352998103e-05,
+      "loss": 0.3453,
+      "step": 385000
+    },
+    {
+      "epoch": 0.39,
+      "eval_runtime": 3143.6271,
+      "eval_samples_per_second": 108.045,
+      "eval_steps_per_second": 13.506,
+      "step": 385000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.631595805024093e-05,
+      "loss": 0.3451,
+      "step": 386000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.6302981344494562e-05,
+      "loss": 0.3411,
+      "step": 387000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.62899835546531e-05,
+      "loss": 0.3435,
+      "step": 388000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.6276964822858297e-05,
+      "loss": 0.3437,
+      "step": 389000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.6263925291480904e-05,
+      "loss": 0.3446,
+      "step": 390000
+    },
+    {
+      "epoch": 0.39,
+      "eval_runtime": 3211.4597,
+      "eval_samples_per_second": 105.762,
+      "eval_steps_per_second": 13.22,
+      "step": 390000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 3.3647518658278195e+21,
+  "total_flos": 3.4532979675601306e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaf5cca6f5ad9c15d0fba6e119e98e99e1b26c717ce470e245593e0001049d48
+oid sha256:0754eb41ff5a1456b603e8b2753adb511ac0a9ee839b9d73f658f3c72064f5ce
 size 454197066