Training in progress, step 80000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c11a259e2fcb4db9bb25889155e0b96cd678f633b923947bdf13de2be4bf3ae6
+oid sha256:2ed32c01ba5914256ee8f4a1db952372628199494048f85def9b6bea2d03f63e
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca06a94bd9a048e9a1048edd363d5f15c12bf594452e56a2cb99b829fdbf580
+oid sha256:1aa4e826f8cd2d5cd8fce3cffdce3fc09b41b0fb0a4b74491ee02350a70950a4
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dbf8e062e9d4eda243137e0b414d7704f82717578f44d0ec7e823055c550c1
+oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dbf8e062e9d4eda243137e0b414d7704f82717578f44d0ec7e823055c550c1
+oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dbf8e062e9d4eda243137e0b414d7704f82717578f44d0ec7e823055c550c1
+oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dbf8e062e9d4eda243137e0b414d7704f82717578f44d0ec7e823055c550c1
+oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dbf8e062e9d4eda243137e0b414d7704f82717578f44d0ec7e823055c550c1
+oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dbf8e062e9d4eda243137e0b414d7704f82717578f44d0ec7e823055c550c1
+oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dbf8e062e9d4eda243137e0b414d7704f82717578f44d0ec7e823055c550c1
+oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dbf8e062e9d4eda243137e0b414d7704f82717578f44d0ec7e823055c550c1
+oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d89de13f8c844c8306762a31aff6dac5ffaadd95c6501762d83dc7939ed9eace
+oid sha256:0a3f000e1c939912bb1fea4c3fda9ca6e80fe563342ccf4a59cb3d0b46d78187
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.28921568627451,
-  "global_step": 70000,
+  "epoch": 4.901960784313726,
+  "global_step": 80000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1406,11 +1406,211 @@
       "eval_samples_per_second": 756.603,
       "eval_steps_per_second": 12.106,
       "step": 70000
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.0005173557775693715,
+      "loss": 0.5058,
+      "step": 70500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 0.0005159968305957235,
+      "loss": 0.5066,
+      "step": 71000
+    },
+    {
+      "epoch": 4.35,
+      "eval_loss": 0.9288005232810974,
+      "eval_runtime": 1.2769,
+      "eval_samples_per_second": 783.148,
+      "eval_steps_per_second": 12.53,
+      "step": 71000
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 0.0005146286539371703,
+      "loss": 0.5084,
+      "step": 71500
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 0.0005132513074421913,
+      "loss": 0.5051,
+      "step": 72000
+    },
+    {
+      "epoch": 4.41,
+      "eval_loss": 0.8597245812416077,
+      "eval_runtime": 1.3157,
+      "eval_samples_per_second": 760.048,
+      "eval_steps_per_second": 12.161,
+      "step": 72000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 0.0005118648513603841,
+      "loss": 0.5051,
+      "step": 72500
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 0.0005104693463398293,
+      "loss": 0.5045,
+      "step": 73000
+    },
+    {
+      "epoch": 4.47,
+      "eval_loss": 0.8554754257202148,
+      "eval_runtime": 1.3269,
+      "eval_samples_per_second": 753.64,
+      "eval_steps_per_second": 12.058,
+      "step": 73000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.0005090648534244371,
+      "loss": 0.5045,
+      "step": 73500
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 0.0005076514340512776,
+      "loss": 0.5043,
+      "step": 74000
+    },
+    {
+      "epoch": 4.53,
+      "eval_loss": 0.8547331094741821,
+      "eval_runtime": 1.2736,
+      "eval_samples_per_second": 785.148,
+      "eval_steps_per_second": 12.562,
+      "step": 74000
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 0.0005062291500478931,
+      "loss": 0.5039,
+      "step": 74500
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 0.0005047980636295937,
+      "loss": 0.5039,
+      "step": 75000
+    },
+    {
+      "epoch": 4.6,
+      "eval_loss": 0.8560617566108704,
+      "eval_runtime": 1.2429,
+      "eval_samples_per_second": 804.574,
+      "eval_steps_per_second": 12.873,
+      "step": 75000
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 0.0005033582373967348,
+      "loss": 0.5036,
+      "step": 75500
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 0.0005019097343319809,
+      "loss": 0.504,
+      "step": 76000
+    },
+    {
+      "epoch": 4.66,
+      "eval_loss": 0.854142427444458,
+      "eval_runtime": 1.3399,
+      "eval_samples_per_second": 746.336,
+      "eval_steps_per_second": 11.941,
+      "step": 76000
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 0.0005004526177975481,
+      "loss": 0.503,
+      "step": 76500
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 0.0004989869515324342,
+      "loss": 0.5026,
+      "step": 77000
+    },
+    {
+      "epoch": 4.72,
+      "eval_loss": 0.8489631414413452,
+      "eval_runtime": 1.2942,
+      "eval_samples_per_second": 772.659,
+      "eval_steps_per_second": 12.363,
+      "step": 77000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 0.0004975127996496297,
+      "loss": 0.5024,
+      "step": 77500
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 0.0004960302266333135,
+      "loss": 0.5024,
+      "step": 78000
+    },
+    {
+      "epoch": 4.78,
+      "eval_loss": 0.8499003648757935,
+      "eval_runtime": 1.3145,
+      "eval_samples_per_second": 760.727,
+      "eval_steps_per_second": 12.172,
+      "step": 78000
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 0.0004945392973360323,
+      "loss": 0.502,
+      "step": 78500
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 0.0004930400769758634,
+      "loss": 0.5019,
+      "step": 79000
+    },
+    {
+      "epoch": 4.84,
+      "eval_loss": 0.8521845936775208,
+      "eval_runtime": 1.3201,
+      "eval_samples_per_second": 757.527,
+      "eval_steps_per_second": 12.12,
+      "step": 79000
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 0.0004915326311335622,
+      "loss": 0.5017,
+      "step": 79500
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.0004900170257496933,
+      "loss": 0.5014,
+      "step": 80000
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 0.8508275747299194,
+      "eval_runtime": 1.3001,
+      "eval_samples_per_second": 769.194,
+      "eval_steps_per_second": 12.307,
+      "step": 80000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 1.1211359780461682e+21,
+  "total_flos": 1.2813039809119723e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca06a94bd9a048e9a1048edd363d5f15c12bf594452e56a2cb99b829fdbf580
+oid sha256:1aa4e826f8cd2d5cd8fce3cffdce3fc09b41b0fb0a4b74491ee02350a70950a4
 size 25761253