Training in progress, step 440000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415b6b8c1b4d1a9fcb0ed4ef3046c0ad8d1ace085712e9a63b9c3ad1cdd80c3b
+oid sha256:d13dee40bf739e07daa5e776dbbdc46c2654fbf14746060e2ac946fb44dbe8e5
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7c87e28b6a6f33ab4f0a8c8ae59e95a04117be20f20068b2e46c87ef398e799
+oid sha256:61e3683717b89ff6ecb486f42da196e91a7d9315fab8b8963d03c3872a54d691
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b57b9eb19bd7ea54b7780f07359bc75fb7601e89f1aa7c6ff7720338af2926
+oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b57b9eb19bd7ea54b7780f07359bc75fb7601e89f1aa7c6ff7720338af2926
+oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b57b9eb19bd7ea54b7780f07359bc75fb7601e89f1aa7c6ff7720338af2926
+oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b57b9eb19bd7ea54b7780f07359bc75fb7601e89f1aa7c6ff7720338af2926
+oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b57b9eb19bd7ea54b7780f07359bc75fb7601e89f1aa7c6ff7720338af2926
+oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b57b9eb19bd7ea54b7780f07359bc75fb7601e89f1aa7c6ff7720338af2926
+oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b57b9eb19bd7ea54b7780f07359bc75fb7601e89f1aa7c6ff7720338af2926
+oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b57b9eb19bd7ea54b7780f07359bc75fb7601e89f1aa7c6ff7720338af2926
+oid sha256:ce0e6291f372fe9f86b6a4068760fc679c69ce294ee69065c8ff7ec587e652c0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f427c751ea4b109969727e0c5f2ef9ef6fd7587de8192ab50fc2201ab4ba3ed9
+oid sha256:1894f32b2441ea8820978bbb44f8f2d9ce0a579e669301efbd1655378591798a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.018872760315944,
-  "global_step": 430000,
+  "epoch": 10.251869801253523,
+  "global_step": 440000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8606,11 +8606,211 @@
       "eval_samples_per_second": 1535.576,
       "eval_steps_per_second": 24.452,
       "step": 430000
+    },
+    {
+      "epoch": 10.03,
+      "learning_rate": 2.5050805238106804e-05,
+      "loss": 0.253,
+      "step": 430500
+    },
+    {
+      "epoch": 10.04,
+      "learning_rate": 2.4838784403798542e-05,
+      "loss": 0.2529,
+      "step": 431000
+    },
+    {
+      "epoch": 10.04,
+      "eval_loss": 0.23809103667736053,
+      "eval_runtime": 1.4751,
+      "eval_samples_per_second": 1490.054,
+      "eval_steps_per_second": 23.727,
+      "step": 431000
+    },
+    {
+      "epoch": 10.05,
+      "learning_rate": 2.4628186991690346e-05,
+      "loss": 0.2528,
+      "step": 431500
+    },
+    {
+      "epoch": 10.07,
+      "learning_rate": 2.4419015304841797e-05,
+      "loss": 0.2532,
+      "step": 432000
+    },
+    {
+      "epoch": 10.07,
+      "eval_loss": 0.23703138530254364,
+      "eval_runtime": 1.4419,
+      "eval_samples_per_second": 1524.361,
+      "eval_steps_per_second": 24.273,
+      "step": 432000
+    },
+    {
+      "epoch": 10.08,
+      "learning_rate": 2.4211271630720957e-05,
+      "loss": 0.2532,
+      "step": 432500
+    },
+    {
+      "epoch": 10.09,
+      "learning_rate": 2.4004958241179347e-05,
+      "loss": 0.253,
+      "step": 433000
+    },
+    {
+      "epoch": 10.09,
+      "eval_loss": 0.2378602772951126,
+      "eval_runtime": 1.476,
+      "eval_samples_per_second": 1489.124,
+      "eval_steps_per_second": 23.712,
+      "step": 433000
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 2.3800077392427193e-05,
+      "loss": 0.2533,
+      "step": 433500
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 2.3596631325008536e-05,
+      "loss": 0.2531,
+      "step": 434000
+    },
+    {
+      "epoch": 10.11,
+      "eval_loss": 0.23943325877189636,
+      "eval_runtime": 1.4371,
+      "eval_samples_per_second": 1529.446,
+      "eval_steps_per_second": 24.354,
+      "step": 434000
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 2.3394622263777042e-05,
+      "loss": 0.2529,
+      "step": 434500
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 2.3194052417871433e-05,
+      "loss": 0.2528,
+      "step": 435000
+    },
+    {
+      "epoch": 10.14,
+      "eval_loss": 0.2356664538383484,
+      "eval_runtime": 1.4719,
+      "eval_samples_per_second": 1493.299,
+      "eval_steps_per_second": 23.779,
+      "step": 435000
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 2.2994923980691425e-05,
+      "loss": 0.253,
+      "step": 435500
+    },
+    {
+      "epoch": 10.16,
+      "learning_rate": 2.279723912987365e-05,
+      "loss": 0.253,
+      "step": 436000
+    },
+    {
+      "epoch": 10.16,
+      "eval_loss": 0.23836100101470947,
+      "eval_runtime": 1.4427,
+      "eval_samples_per_second": 1523.571,
+      "eval_steps_per_second": 24.261,
+      "step": 436000
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 2.2601000027268006e-05,
+      "loss": 0.2526,
+      "step": 436500
+    },
+    {
+      "epoch": 10.18,
+      "learning_rate": 2.2406208818913857e-05,
+      "loss": 0.2525,
+      "step": 437000
+    },
+    {
+      "epoch": 10.18,
+      "eval_loss": 0.23866206407546997,
+      "eval_runtime": 1.4308,
+      "eval_samples_per_second": 1536.237,
+      "eval_steps_per_second": 24.462,
+      "step": 437000
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 2.221286763501666e-05,
+      "loss": 0.2527,
+      "step": 437500
+    },
+    {
+      "epoch": 10.21,
+      "learning_rate": 2.2020978589924673e-05,
+      "loss": 0.2526,
+      "step": 438000
+    },
+    {
+      "epoch": 10.21,
+      "eval_loss": 0.23435133695602417,
+      "eval_runtime": 1.417,
+      "eval_samples_per_second": 1551.208,
+      "eval_steps_per_second": 24.701,
+      "step": 438000
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 2.1830543782105647e-05,
+      "loss": 0.2528,
+      "step": 438500
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 2.1641565294124206e-05,
+      "loss": 0.2527,
+      "step": 439000
+    },
+    {
+      "epoch": 10.23,
+      "eval_loss": 0.23615118861198425,
+      "eval_runtime": 1.4413,
+      "eval_samples_per_second": 1524.993,
+      "eval_steps_per_second": 24.283,
+      "step": 439000
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 2.1454045192618794e-05,
+      "loss": 0.2525,
+      "step": 439500
+    },
+    {
+      "epoch": 10.25,
+      "learning_rate": 2.1267985528279212e-05,
+      "loss": 0.2528,
+      "step": 440000
+    },
+    {
+      "epoch": 10.25,
+      "eval_loss": 0.23707140982151031,
+      "eval_runtime": 1.4358,
+      "eval_samples_per_second": 1530.896,
+      "eval_steps_per_second": 24.377,
+      "step": 440000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.3737921997394432e+22,
+  "total_flos": 1.4057409136168932e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7c87e28b6a6f33ab4f0a8c8ae59e95a04117be20f20068b2e46c87ef398e799
+oid sha256:61e3683717b89ff6ecb486f42da196e91a7d9315fab8b8963d03c3872a54d691
 size 102501541