Training in progress, step 130000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea5ee7b5944fb69273cf2a7c5b4b6f7424b6dd4c513e7e42a1e34cf3979c95f
+oid sha256:a9c7a3961722d5e2e1d58ab1ec5745ef09a520dff61782c5846ec96a38f0f0c0
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488b20e22713e0037f71bd0daab1f22fe37b44d8f6535aeaca21bc1644596967
+oid sha256:d28d9f72755d5cec4196d53c4e7dbdd8ce8cdc55da23e20816db43ca099c784e
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802660e5bcfd656c7440733295a327b26e005038db43047150f87b4a5e83a211
+oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802660e5bcfd656c7440733295a327b26e005038db43047150f87b4a5e83a211
+oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802660e5bcfd656c7440733295a327b26e005038db43047150f87b4a5e83a211
+oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802660e5bcfd656c7440733295a327b26e005038db43047150f87b4a5e83a211
+oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802660e5bcfd656c7440733295a327b26e005038db43047150f87b4a5e83a211
+oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802660e5bcfd656c7440733295a327b26e005038db43047150f87b4a5e83a211
+oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802660e5bcfd656c7440733295a327b26e005038db43047150f87b4a5e83a211
+oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802660e5bcfd656c7440733295a327b26e005038db43047150f87b4a5e83a211
+oid sha256:846a10f670117f028a052aac8d19fc7914db47f5da8116b1d33ab4900e26ee93
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ddf5c33f60196860027b40e8443017b8ed479cc5dfb73f8a076fe07f546fd4
+oid sha256:f1c3de3c2d66025eca4b56b8d5efacb781ba1e9b4daae40acd9c92c0f7cbe98c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6766595289079227,
-  "global_step": 120000,
+  "epoch": 2.8997144896502496,
+  "global_step": 130000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2406,11 +2406,211 @@
       "eval_samples_per_second": 1112.04,
       "eval_steps_per_second": 17.429,
       "step": 120000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.0002720249765698123,
+      "loss": 0.2999,
+      "step": 120500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0002717412091888626,
+      "loss": 0.3004,
+      "step": 121000
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 0.28047671914100647,
+      "eval_runtime": 1.9731,
+      "eval_samples_per_second": 1164.181,
+      "eval_steps_per_second": 18.246,
+      "step": 121000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 0.00027145616514475274,
+      "loss": 0.2996,
+      "step": 121500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 0.0002711698475546788,
+      "loss": 0.299,
+      "step": 122000
+    },
+    {
+      "epoch": 2.72,
+      "eval_loss": 0.2800908386707306,
+      "eval_runtime": 2.05,
+      "eval_samples_per_second": 1120.501,
+      "eval_steps_per_second": 17.561,
+      "step": 122000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 0.00027088225954976407,
+      "loss": 0.2995,
+      "step": 122500
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.0002705934042750249,
+      "loss": 0.2991,
+      "step": 123000
+    },
+    {
+      "epoch": 2.74,
+      "eval_loss": 0.27821099758148193,
+      "eval_runtime": 2.0199,
+      "eval_samples_per_second": 1137.17,
+      "eval_steps_per_second": 17.822,
+      "step": 123000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.00027030328488933625,
+      "loss": 0.2989,
+      "step": 123500
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.00027001190456539726,
+      "loss": 0.2987,
+      "step": 124000
+    },
+    {
+      "epoch": 2.77,
+      "eval_loss": 0.2801131308078766,
+      "eval_runtime": 1.9909,
+      "eval_samples_per_second": 1153.743,
+      "eval_steps_per_second": 18.082,
+      "step": 124000
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 0.0002697192664896965,
+      "loss": 0.2987,
+      "step": 124500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 0.00026942537386247706,
+      "loss": 0.2987,
+      "step": 125000
+    },
+    {
+      "epoch": 2.79,
+      "eval_loss": 0.2810814380645752,
+      "eval_runtime": 1.998,
+      "eval_samples_per_second": 1149.64,
+      "eval_steps_per_second": 18.018,
+      "step": 125000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002691302298977016,
+      "loss": 0.2985,
+      "step": 125500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.0002688338378230173,
+      "loss": 0.298,
+      "step": 126000
+    },
+    {
+      "epoch": 2.81,
+      "eval_loss": 0.27943727374076843,
+      "eval_runtime": 2.0072,
+      "eval_samples_per_second": 1144.392,
+      "eval_steps_per_second": 17.936,
+      "step": 126000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.00026853620087972035,
+      "loss": 0.2983,
+      "step": 126500
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.00026823732232272065,
+      "loss": 0.2981,
+      "step": 127000
+    },
+    {
+      "epoch": 2.83,
+      "eval_loss": 0.27999699115753174,
+      "eval_runtime": 2.0113,
+      "eval_samples_per_second": 1142.034,
+      "eval_steps_per_second": 17.899,
+      "step": 127000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002679372054205063,
+      "loss": 0.2985,
+      "step": 127500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.0002676358534551076,
+      "loss": 0.2976,
+      "step": 128000
+    },
+    {
+      "epoch": 2.86,
+      "eval_loss": 0.2797393500804901,
+      "eval_runtime": 2.072,
+      "eval_samples_per_second": 1108.589,
+      "eval_steps_per_second": 17.374,
+      "step": 128000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 0.00026733326972206133,
+      "loss": 0.2981,
+      "step": 128500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 0.0002670294575303748,
+      "loss": 0.2977,
+      "step": 129000
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 0.2784021496772766,
+      "eval_runtime": 2.0212,
+      "eval_samples_per_second": 1136.428,
+      "eval_steps_per_second": 17.811,
+      "step": 129000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.0002667244202024894,
+      "loss": 0.2975,
+      "step": 129500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.00026641816107424453,
+      "loss": 0.297,
+      "step": 130000
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 0.2790050208568573,
+      "eval_runtime": 1.9904,
+      "eval_samples_per_second": 1154.041,
+      "eval_steps_per_second": 18.087,
+      "step": 130000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 3.8337887567711694e+21,
+  "total_flos": 4.1532758955456694e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488b20e22713e0037f71bd0daab1f22fe37b44d8f6535aeaca21bc1644596967
+oid sha256:d28d9f72755d5cec4196d53c4e7dbdd8ce8cdc55da23e20816db43ca099c784e
 size 102501541