Training in progress, step 310000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf06004ede41634f31f51db43c8e8bd655d6cf31bd715fe6a400fa272f9d936
+oid sha256:3e0507b38aa7540f67f9e0a0633279dd51f9a831fc1db6cc8eacbb35397bd4b8
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f18c7c2c86ca13727949f1e8fc13e7631481b4544ee49ec424ae0d909fab662
+oid sha256:671528b9282de7ee8eda298ebd63ddf167905d49365aa89ef6684cdf3a665481
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cc022b9e73fe2f5189297efc512c3e18716586fa066a4b492e92e4f957bb73
+oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cc022b9e73fe2f5189297efc512c3e18716586fa066a4b492e92e4f957bb73
+oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cc022b9e73fe2f5189297efc512c3e18716586fa066a4b492e92e4f957bb73
+oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cc022b9e73fe2f5189297efc512c3e18716586fa066a4b492e92e4f957bb73
+oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cc022b9e73fe2f5189297efc512c3e18716586fa066a4b492e92e4f957bb73
+oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cc022b9e73fe2f5189297efc512c3e18716586fa066a4b492e92e4f957bb73
+oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cc022b9e73fe2f5189297efc512c3e18716586fa066a4b492e92e4f957bb73
+oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cc022b9e73fe2f5189297efc512c3e18716586fa066a4b492e92e4f957bb73
+oid sha256:871f42af1f573f4efd66827fac31645af2cb2540adb5d0d237397c32c55cce8b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7914b9f1e3709b1198ec189eb9bb9105cd6b88dedbcbbdd4128934a703cf33e3
+oid sha256:9b8c10dab6d3ee824fc8fe4628d3bf3ceea806ce0d2fbe513f32af4d508ab89e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.9899112281274025,
-  "global_step": 300000,
+  "epoch": 7.222908269064983,
+  "global_step": 310000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6006,11 +6006,211 @@
       "eval_samples_per_second": 1567.888,
       "eval_steps_per_second": 24.966,
       "step": 300000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00011893996636109606,
+      "loss": 0.6483,
+      "step": 300500
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.00011847572270435852,
+      "loss": 0.6477,
+      "step": 301000
+    },
+    {
+      "epoch": 7.01,
+      "eval_loss": 0.6460827589035034,
+      "eval_runtime": 1.4908,
+      "eval_samples_per_second": 1474.348,
+      "eval_steps_per_second": 23.477,
+      "step": 301000
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 0.00011801187847126579,
+      "loss": 0.6478,
+      "step": 301500
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 0.00011754843873434411,
+      "loss": 0.6471,
+      "step": 302000
+    },
+    {
+      "epoch": 7.04,
+      "eval_loss": 0.6455149054527283,
+      "eval_runtime": 1.4371,
+      "eval_samples_per_second": 1529.505,
+      "eval_steps_per_second": 24.355,
+      "step": 302000
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 0.00011708540856169612,
+      "loss": 0.6443,
+      "step": 302500
+    },
+    {
+      "epoch": 7.06,
+      "learning_rate": 0.00011662279301694567,
+      "loss": 0.4659,
+      "step": 303000
+    },
+    {
+      "epoch": 7.06,
+      "eval_loss": 0.25994545221328735,
+      "eval_runtime": 1.3921,
+      "eval_samples_per_second": 1578.885,
+      "eval_steps_per_second": 25.141,
+      "step": 303000
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 0.0001161605971591822,
+      "loss": 0.2739,
+      "step": 303500
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 0.00011569882604290559,
+      "loss": 0.2707,
+      "step": 304000
+    },
+    {
+      "epoch": 7.08,
+      "eval_loss": 0.25346240401268005,
+      "eval_runtime": 1.4298,
+      "eval_samples_per_second": 1537.235,
+      "eval_steps_per_second": 24.478,
+      "step": 304000
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 0.00011523748471797075,
+      "loss": 0.2691,
+      "step": 304500
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 0.00011477657822953255,
+      "loss": 0.2681,
+      "step": 305000
+    },
+    {
+      "epoch": 7.11,
+      "eval_loss": 0.2524736821651459,
+      "eval_runtime": 1.4268,
+      "eval_samples_per_second": 1540.462,
+      "eval_steps_per_second": 24.53,
+      "step": 305000
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 0.00011431611161799043,
+      "loss": 0.268,
+      "step": 305500
+    },
+    {
+      "epoch": 7.13,
+      "learning_rate": 0.0001138560899189335,
+      "loss": 0.2678,
+      "step": 306000
+    },
+    {
+      "epoch": 7.13,
+      "eval_loss": 0.25040730834007263,
+      "eval_runtime": 1.4446,
+      "eval_samples_per_second": 1521.535,
+      "eval_steps_per_second": 24.228,
+      "step": 306000
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.00011339651816308543,
+      "loss": 0.267,
+      "step": 306500
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 0.00011293740137624925,
+      "loss": 0.267,
+      "step": 307000
+    },
+    {
+      "epoch": 7.15,
+      "eval_loss": 0.24852143228054047,
+      "eval_runtime": 1.3837,
+      "eval_samples_per_second": 1588.479,
+      "eval_steps_per_second": 25.294,
+      "step": 307000
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 0.00011247874457925261,
+      "loss": 0.2668,
+      "step": 307500
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 0.0001120205527878927,
+      "loss": 0.2663,
+      "step": 308000
+    },
+    {
+      "epoch": 7.18,
+      "eval_loss": 0.2509649991989136,
+      "eval_runtime": 1.4317,
+      "eval_samples_per_second": 1535.233,
+      "eval_steps_per_second": 24.446,
+      "step": 308000
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 0.00011156283101288165,
+      "loss": 0.266,
+      "step": 308500
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 0.00011110558425979132,
+      "loss": 0.266,
+      "step": 309000
+    },
+    {
+      "epoch": 7.2,
+      "eval_loss": 0.24989214539527893,
+      "eval_runtime": 1.446,
+      "eval_samples_per_second": 1520.105,
+      "eval_steps_per_second": 24.205,
+      "step": 309000
+    },
+    {
+      "epoch": 7.21,
+      "learning_rate": 0.00011064881752899906,
+      "loss": 0.2661,
+      "step": 309500
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 0.00011019253581563262,
+      "loss": 0.2658,
+      "step": 310000
+    },
+    {
+      "epoch": 7.22,
+      "eval_loss": 0.2480825036764145,
+      "eval_runtime": 1.4466,
+      "eval_samples_per_second": 1519.474,
+      "eval_steps_per_second": 24.195,
+      "step": 310000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 9.58459918128956e+21,
+  "total_flos": 9.904083823073153e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f18c7c2c86ca13727949f1e8fc13e7631481b4544ee49ec424ae0d909fab662
+oid sha256:671528b9282de7ee8eda298ebd63ddf167905d49365aa89ef6684cdf3a665481
 size 102501541