Training in progress, step 100000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150d8b3c57728037c4a472baaa9d8c4cdc3e29d155183e7b2a12684f9319c8cc
+oid sha256:c5a8740e850a7025efc4240518d5b20a0266625ee7a4df5824989ffd90a771e4
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7a8dbd06b2428a64e1f1bb1794f8399c9be17660f04561ced3ff300c0d49c2
+oid sha256:9743dfff2c56ecc42fa49782ae324bef5653923fd6c7bcd04473781c4c5cb59f
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
+oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
+oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
+oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
+oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
+oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
+oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
+oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bcfdcb6dd8b515af0d3d840d09eef233ce6cd3e8e3e4c426ccd84e88d11e4
+oid sha256:92ffde1f04d1013b5eec7ae73480f479d0d281fd050bfb67dcf4ffaf69a11bc9
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5810d5d1337eca8d561357c6c9e9920258e5fc2b2f0f70ea4b52e4984949eec8
+oid sha256:7786e0d240c1817a80f936fe537093f6b0f81238abcccea2c0e618f1ac9e9438
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.096973368438221,
-  "global_step": 90000,
+  "epoch": 2.329970409375801,
+  "global_step": 100000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1806,11 +1806,211 @@
       "eval_samples_per_second": 1570.392,
       "eval_steps_per_second": 25.006,
       "step": 90000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00028660537773622294,
+      "loss": 0.3073,
+      "step": 90500
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00028640336867499143,
+      "loss": 0.3063,
+      "step": 91000
+    },
+    {
+      "epoch": 2.12,
+      "eval_loss": 0.28914499282836914,
+      "eval_runtime": 1.4031,
+      "eval_samples_per_second": 1566.538,
+      "eval_steps_per_second": 24.945,
+      "step": 91000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002861999226075728,
+      "loss": 0.306,
+      "step": 91500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.0002859950417588206,
+      "loss": 0.3057,
+      "step": 92000
+    },
+    {
+      "epoch": 2.14,
+      "eval_loss": 0.28657251596450806,
+      "eval_runtime": 1.3993,
+      "eval_samples_per_second": 1570.823,
+      "eval_steps_per_second": 25.013,
+      "step": 92000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00028578872836927904,
+      "loss": 0.3057,
+      "step": 92500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.0002855809846951582,
+      "loss": 0.3066,
+      "step": 93000
+    },
+    {
+      "epoch": 2.17,
+      "eval_loss": 0.2893889248371124,
+      "eval_runtime": 1.4241,
+      "eval_samples_per_second": 1543.421,
+      "eval_steps_per_second": 24.577,
+      "step": 93000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.00028537181300830963,
+      "loss": 0.305,
+      "step": 93500
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0002851612155962014,
+      "loss": 0.3048,
+      "step": 94000
+    },
+    {
+      "epoch": 2.19,
+      "eval_loss": 0.2858821451663971,
+      "eval_runtime": 1.4056,
+      "eval_samples_per_second": 1563.797,
+      "eval_steps_per_second": 24.901,
+      "step": 94000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.0002849491947618932,
+      "loss": 0.3048,
+      "step": 94500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.0002847357528240107,
+      "loss": 0.3051,
+      "step": 95000
+    },
+    {
+      "epoch": 2.21,
+      "eval_loss": 0.28810954093933105,
+      "eval_runtime": 1.4039,
+      "eval_samples_per_second": 1565.629,
+      "eval_steps_per_second": 24.93,
+      "step": 95000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.0002845208921167208,
+      "loss": 0.3047,
+      "step": 95500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.00028430461498970584,
+      "loss": 0.3041,
+      "step": 96000
+    },
+    {
+      "epoch": 2.24,
+      "eval_loss": 0.28588977456092834,
+      "eval_runtime": 1.4454,
+      "eval_samples_per_second": 1520.728,
+      "eval_steps_per_second": 24.215,
+      "step": 96000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00028408692380813775,
+      "loss": 0.3042,
+      "step": 96500
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.00028386782095265247,
+      "loss": 0.3039,
+      "step": 97000
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 0.2837139666080475,
+      "eval_runtime": 1.414,
+      "eval_samples_per_second": 1554.434,
+      "eval_steps_per_second": 24.752,
+      "step": 97000
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002836473088193237,
+      "loss": 0.3036,
+      "step": 97500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00028342538981963677,
+      "loss": 0.3032,
+      "step": 98000
+    },
+    {
+      "epoch": 2.28,
+      "eval_loss": 0.28603771328926086,
+      "eval_runtime": 1.4079,
+      "eval_samples_per_second": 1561.179,
+      "eval_steps_per_second": 24.86,
+      "step": 98000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.0002832020663804624,
+      "loss": 0.3035,
+      "step": 98500
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00028297734094402986,
+      "loss": 0.3039,
+      "step": 99000
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 0.2857549488544464,
+      "eval_runtime": 1.4042,
+      "eval_samples_per_second": 1565.268,
+      "eval_steps_per_second": 24.925,
+      "step": 99000
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.0002827512159679005,
+      "loss": 0.3027,
+      "step": 99500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.00028252369392494086,
+      "loss": 0.3025,
+      "step": 100000
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 0.28487083315849304,
+      "eval_runtime": 1.4056,
+      "eval_samples_per_second": 1563.737,
+      "eval_steps_per_second": 24.9,
+      "step": 100000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 2.8753792549886865e+21,
+  "total_flos": 3.1948663937631865e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7a8dbd06b2428a64e1f1bb1794f8399c9be17660f04561ced3ff300c0d49c2
+oid sha256:9743dfff2c56ecc42fa49782ae324bef5653923fd6c7bcd04473781c4c5cb59f
 size 102501541