Training in progress, step 590000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111490892a3e244f3ca9b9b0f1e04552db811c5c11d50e5dae81456c571735a9
+oid sha256:6ba1a60953f474b23784dd49858737503638550c3096a7f534e92e574e05a543
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c26410b4d902c6d077c2953f9eace1e47991bc5dcd2f62ceb38a14b3e3ee84
+oid sha256:5a8bbf9aa941f450bae2344c4f3ace716b8d409472808a8af9bbe468eecca5b1
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c101353913b86ff575c9018e352c46e19aa450e36d2ee34d697b2d5ed877d1d
+oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c101353913b86ff575c9018e352c46e19aa450e36d2ee34d697b2d5ed877d1d
+oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c101353913b86ff575c9018e352c46e19aa450e36d2ee34d697b2d5ed877d1d
+oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c101353913b86ff575c9018e352c46e19aa450e36d2ee34d697b2d5ed877d1d
+oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c101353913b86ff575c9018e352c46e19aa450e36d2ee34d697b2d5ed877d1d
+oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c101353913b86ff575c9018e352c46e19aa450e36d2ee34d697b2d5ed877d1d
+oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c101353913b86ff575c9018e352c46e19aa450e36d2ee34d697b2d5ed877d1d
+oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c101353913b86ff575c9018e352c46e19aa450e36d2ee34d697b2d5ed877d1d
+oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe2528712b13528834db613d1453dd7fb04ea3b7a1940fa3521b7d0be4a96c0a
+oid sha256:bf17ad9f6f8f5230f179dea9ee53bd043cf1c420455dc89092d4dbf5e8505225
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.111528724222923,
-  "global_step": 580000,
+  "epoch": 6.223057448445847,
+  "global_step": 590000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11606,11 +11606,211 @@
       "eval_samples_per_second": 937.277,
       "eval_steps_per_second": 14.69,
       "step": 580000
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 6.722454623985994e-05,
+      "loss": 0.2036,
+      "step": 580500
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 6.71107648105703e-05,
+      "loss": 0.2038,
+      "step": 581000
+    },
+    {
+      "epoch": 6.12,
+      "eval_loss": 0.1942874640226364,
+      "eval_runtime": 2.6604,
+      "eval_samples_per_second": 863.404,
+      "eval_steps_per_second": 13.532,
+      "step": 581000
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 6.69970186199575e-05,
+      "loss": 0.204,
+      "step": 581500
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 6.688330797899925e-05,
+      "loss": 0.2036,
+      "step": 582000
+    },
+    {
+      "epoch": 6.13,
+      "eval_loss": 0.1936686784029007,
+      "eval_runtime": 2.5783,
+      "eval_samples_per_second": 890.887,
+      "eval_steps_per_second": 13.963,
+      "step": 582000
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 6.676963319857618e-05,
+      "loss": 0.2038,
+      "step": 582500
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 6.665599458947072e-05,
+      "loss": 0.2035,
+      "step": 583000
+    },
+    {
+      "epoch": 6.14,
+      "eval_loss": 0.1947861611843109,
+      "eval_runtime": 2.5506,
+      "eval_samples_per_second": 900.557,
+      "eval_steps_per_second": 14.114,
+      "step": 583000
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 6.654239246236651e-05,
+      "loss": 0.2037,
+      "step": 583500
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 6.642882712784742e-05,
+      "loss": 0.2033,
+      "step": 584000
+    },
+    {
+      "epoch": 6.16,
+      "eval_loss": 0.1927429735660553,
+      "eval_runtime": 2.5138,
+      "eval_samples_per_second": 913.772,
+      "eval_steps_per_second": 14.321,
+      "step": 584000
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 6.631529889639679e-05,
+      "loss": 0.2032,
+      "step": 584500
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 6.620180807839639e-05,
+      "loss": 0.2033,
+      "step": 585000
+    },
+    {
+      "epoch": 6.17,
+      "eval_loss": 0.19153708219528198,
+      "eval_runtime": 2.5442,
+      "eval_samples_per_second": 902.822,
+      "eval_steps_per_second": 14.15,
+      "step": 585000
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 6.608835498412583e-05,
+      "loss": 0.2034,
+      "step": 585500
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 6.597493992376152e-05,
+      "loss": 0.2031,
+      "step": 586000
+    },
+    {
+      "epoch": 6.18,
+      "eval_loss": 0.1941889226436615,
+      "eval_runtime": 2.5658,
+      "eval_samples_per_second": 895.227,
+      "eval_steps_per_second": 14.031,
+      "step": 586000
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 6.586156320737592e-05,
+      "loss": 0.2032,
+      "step": 586500
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 6.574822514493664e-05,
+      "loss": 0.2029,
+      "step": 587000
+    },
+    {
+      "epoch": 6.19,
+      "eval_loss": 0.19126850366592407,
+      "eval_runtime": 2.5788,
+      "eval_samples_per_second": 890.72,
+      "eval_steps_per_second": 13.96,
+      "step": 587000
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 6.56349260463056e-05,
+      "loss": 0.2026,
+      "step": 587500
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 6.552166622123824e-05,
+      "loss": 0.2031,
+      "step": 588000
+    },
+    {
+      "epoch": 6.2,
+      "eval_loss": 0.19138653576374054,
+      "eval_runtime": 2.5292,
+      "eval_samples_per_second": 908.193,
+      "eval_steps_per_second": 14.234,
+      "step": 588000
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 6.540844597938256e-05,
+      "loss": 0.203,
+      "step": 588500
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 6.52952656302784e-05,
+      "loss": 0.203,
+      "step": 589000
+    },
+    {
+      "epoch": 6.21,
+      "eval_loss": 0.1942255049943924,
+      "eval_runtime": 2.5063,
+      "eval_samples_per_second": 916.493,
+      "eval_steps_per_second": 14.364,
+      "step": 589000
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 6.518212548335651e-05,
+      "loss": 0.2027,
+      "step": 589500
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 6.506902584793773e-05,
+      "loss": 0.2032,
+      "step": 590000
+    },
+    {
+      "epoch": 6.22,
+      "eval_loss": 0.1933428943157196,
+      "eval_runtime": 2.5059,
+      "eval_samples_per_second": 916.62,
+      "eval_steps_per_second": 14.366,
+      "step": 590000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.065782281075041e+22,
+  "total_flos": 4.135882542105388e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c26410b4d902c6d077c2953f9eace1e47991bc5dcd2f62ceb38a14b3e3ee84
+oid sha256:5a8bbf9aa941f450bae2344c4f3ace716b8d409472808a8af9bbe468eecca5b1
 size 449471589