Training in progress, step 420000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07f03ea18fd5d4a8b1e4e3c742e1d56a40794f2a3b257ce44d2264feed3af286
+oid sha256:b6c710dd18f96e58101abb4543f93762b3065e883b1aa3865d95449d6dcff2ef
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c6809c972a6eabd269160656909344105b6d4e4ab486435a7eb7ab6f03cd31
+oid sha256:26a1dec101691ebd7c104c916b6fbf2b961123d72841379924840b574ab6cdb5
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be43869b2d26de64620114c0cd31802e0f535f8b4066fd45c9c93b0dc7fc8193
-size 14439
+oid sha256:482727048b96ef6295d46f8e1c756249fe05df8f4565790853af683f2f73d3d9
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3ef4114c1e842456ef64f4180a6eab84b1c65069eb4d0f673451378faba5e88
-size 14439
+oid sha256:ec58e861ecfc9f74cf3526c7f7e07d40e14496fd6bc4013607b9344e9c1e618d
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d2f54aa3ce711401cd4ee540e9c92a11b601491f08344941d6924f5e6c29f97
+oid sha256:b2aebd434102fdb5bc0174b7c6fb694db378bfa14b7f46447d196181b9cfcb39
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db27b64031de4e8fdf403dbbf855618a1ce97321f71e80ad2ee2fd8a0ecff85b
+oid sha256:f00f2e685c708cfd0cbbb80e095c6bf343a9624eb506d7fe315e91e79d2cc8c7
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111428f29ffec49187b68d16c54a6c29ee4fbb60ae7b0a594f8a3a5492faefcc
+oid sha256:e8dd01bc2de28ac7cee0c2566f096951eb4ee6698f2cb4f09a40119c0f514708
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ed3db5c699900337804672d3763c810ccb3d79001c4a96e25a3be74c283a16
-size 14503
+oid sha256:ed4ca2d2c2eb8082634a2e8e07ce3220676e6442b8fc3172e0e2229e0f0ad540
+size 14439

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba203c82676ee0f0f6d805eb229d404fcf81bb695cf23304c62df491ffe623d
-size 14503
+oid sha256:0a08068423bd0da8de286f2bfe952fac174abba9ea4b1b0d5c4dc9fed6c69200
+size 14439

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a98f099a2c4465105355e169c3be433597657bb0fd97136841e01a3bc9cfc2
+oid sha256:6a39f4a2af63c824a2393a7a188b35765b425e608da84400d9022e1ad2be2efc
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:498c95fdcab578849c69bf4a10f0532f5bf3ba8048fa37c1b416b3afd0ea5f33
+oid sha256:21fa0c13fc0e3348f6228394f5e318945295debe26ba21ec91b2c06a47593869
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.561659364563866,
-  "global_step": 410000,
+  "epoch": 12.868041300284935,
+  "global_step": 420000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8206,11 +8206,211 @@
       "eval_samples_per_second": 1952.734,
       "eval_steps_per_second": 31.244,
       "step": 410000
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 3.4670510086189736e-05,
+      "loss": 0.3172,
+      "step": 410500
+    },
+    {
+      "epoch": 12.59,
+      "learning_rate": 3.440361659286563e-05,
+      "loss": 0.3168,
+      "step": 411000
+    },
+    {
+      "epoch": 12.59,
+      "eval_loss": 0.7748520374298096,
+      "eval_runtime": 0.5115,
+      "eval_samples_per_second": 1955.169,
+      "eval_steps_per_second": 31.283,
+      "step": 411000
+    },
+    {
+      "epoch": 12.61,
+      "learning_rate": 3.413804192226918e-05,
+      "loss": 0.317,
+      "step": 411500
+    },
+    {
+      "epoch": 12.62,
+      "learning_rate": 3.387378897868246e-05,
+      "loss": 0.317,
+      "step": 412000
+    },
+    {
+      "epoch": 12.62,
+      "eval_loss": 0.7790003418922424,
+      "eval_runtime": 0.5251,
+      "eval_samples_per_second": 1904.548,
+      "eval_steps_per_second": 30.473,
+      "step": 412000
+    },
+    {
+      "epoch": 12.64,
+      "learning_rate": 3.361086065193336e-05,
+      "loss": 0.3169,
+      "step": 412500
+    },
+    {
+      "epoch": 12.65,
+      "learning_rate": 3.334925981736389e-05,
+      "loss": 0.3169,
+      "step": 413000
+    },
+    {
+      "epoch": 12.65,
+      "eval_loss": 0.7779929041862488,
+      "eval_runtime": 0.5032,
+      "eval_samples_per_second": 1987.349,
+      "eval_steps_per_second": 31.798,
+      "step": 413000
+    },
+    {
+      "epoch": 12.67,
+      "learning_rate": 3.3088989335798925e-05,
+      "loss": 0.3169,
+      "step": 413500
+    },
+    {
+      "epoch": 12.68,
+      "learning_rate": 3.283005205351467e-05,
+      "loss": 0.3165,
+      "step": 414000
+    },
+    {
+      "epoch": 12.68,
+      "eval_loss": 0.7767853736877441,
+      "eval_runtime": 0.5028,
+      "eval_samples_per_second": 1988.956,
+      "eval_steps_per_second": 31.823,
+      "step": 414000
+    },
+    {
+      "epoch": 12.7,
+      "learning_rate": 3.2572450802207845e-05,
+      "loss": 0.3169,
+      "step": 414500
+    },
+    {
+      "epoch": 12.71,
+      "learning_rate": 3.2316188398964344e-05,
+      "loss": 0.3165,
+      "step": 415000
+    },
+    {
+      "epoch": 12.71,
+      "eval_loss": 0.7794355750083923,
+      "eval_runtime": 0.5308,
+      "eval_samples_per_second": 1884.074,
+      "eval_steps_per_second": 30.145,
+      "step": 415000
+    },
+    {
+      "epoch": 12.73,
+      "learning_rate": 3.206126764622888e-05,
+      "loss": 0.3166,
+      "step": 415500
+    },
+    {
+      "epoch": 12.75,
+      "learning_rate": 3.180769133177392e-05,
+      "loss": 0.3165,
+      "step": 416000
+    },
+    {
+      "epoch": 12.75,
+      "eval_loss": 0.7837159633636475,
+      "eval_runtime": 0.5042,
+      "eval_samples_per_second": 1983.371,
+      "eval_steps_per_second": 31.734,
+      "step": 416000
+    },
+    {
+      "epoch": 12.76,
+      "learning_rate": 3.155546222866939e-05,
+      "loss": 0.3168,
+      "step": 416500
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 3.130458309525239e-05,
+      "loss": 0.3164,
+      "step": 417000
+    },
+    {
+      "epoch": 12.78,
+      "eval_loss": 0.7775956988334656,
+      "eval_runtime": 0.5205,
+      "eval_samples_per_second": 1921.225,
+      "eval_steps_per_second": 30.74,
+      "step": 417000
+    },
+    {
+      "epoch": 12.79,
+      "learning_rate": 3.1055056675096826e-05,
+      "loss": 0.3165,
+      "step": 417500
+    },
+    {
+      "epoch": 12.81,
+      "learning_rate": 3.0806885696983816e-05,
+      "loss": 0.3165,
+      "step": 418000
+    },
+    {
+      "epoch": 12.81,
+      "eval_loss": 0.7772942185401917,
+      "eval_runtime": 0.5181,
+      "eval_samples_per_second": 1929.962,
+      "eval_steps_per_second": 30.879,
+      "step": 418000
+    },
+    {
+      "epoch": 12.82,
+      "learning_rate": 3.056007287487128e-05,
+      "loss": 0.3164,
+      "step": 418500
+    },
+    {
+      "epoch": 12.84,
+      "learning_rate": 3.0314620907864744e-05,
+      "loss": 0.3164,
+      "step": 419000
+    },
+    {
+      "epoch": 12.84,
+      "eval_loss": 0.7730494141578674,
+      "eval_runtime": 0.5018,
+      "eval_samples_per_second": 1992.671,
+      "eval_steps_per_second": 31.883,
+      "step": 419000
+    },
+    {
+      "epoch": 12.85,
+      "learning_rate": 3.0070532480187637e-05,
+      "loss": 0.3164,
+      "step": 419500
+    },
+    {
+      "epoch": 12.87,
+      "learning_rate": 2.9827810261151784e-05,
+      "loss": 0.3161,
+      "step": 420000
+    },
+    {
+      "epoch": 12.87,
+      "eval_loss": 0.7735152840614319,
+      "eval_runtime": 0.5135,
+      "eval_samples_per_second": 1947.554,
+      "eval_steps_per_second": 31.161,
+      "step": 420000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.309887683433079e+22,
+  "total_flos": 1.341836397310529e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c6809c972a6eabd269160656909344105b6d4e4ab486435a7eb7ab6f03cd31
+oid sha256:26a1dec101691ebd7c104c916b6fbf2b961123d72841379924840b574ab6cdb5
 size 102501541