Training in progress, step 430000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c710dd18f96e58101abb4543f93762b3065e883b1aa3865d95449d6dcff2ef
+oid sha256:2037a39653e9a86b52eb755df70a2048c15c66b97fc5c5b2e730133643a54847
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a1dec101691ebd7c104c916b6fbf2b961123d72841379924840b574ab6cdb5
+oid sha256:f68b8d9c04c07b07e7749f58776534bd53918c6e2c126a3b13ccf6e4c8fe0c11
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482727048b96ef6295d46f8e1c756249fe05df8f4565790853af683f2f73d3d9
+oid sha256:9b2daf51037932e93e0733ea24caef617dc93e09ea15b9fd221dcc7444c15f0e
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec58e861ecfc9f74cf3526c7f7e07d40e14496fd6bc4013607b9344e9c1e618d
+oid sha256:d3a3ebd3780a0e2b9539a7e9e3280f39aab22ea827f57421c4c22612d438cdfb
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2aebd434102fdb5bc0174b7c6fb694db378bfa14b7f46447d196181b9cfcb39
+oid sha256:86247109bf049f289c15c3221972c6c603aeaaab8c73e9572f0b173c34fca77b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00f2e685c708cfd0cbbb80e095c6bf343a9624eb506d7fe315e91e79d2cc8c7
+oid sha256:5cefc44f7d07864c913b59c01e54c2d25ff69e14a2f34a7e0e54f8b7ef0768fa
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8dd01bc2de28ac7cee0c2566f096951eb4ee6698f2cb4f09a40119c0f514708
-size 14503
+oid sha256:e44801ad618d45c1ec0026a0fb986a5b4b4808493b86436a804a9e6412bb1dd2
+size 14439

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4ca2d2c2eb8082634a2e8e07ce3220676e6442b8fc3172e0e2229e0f0ad540
-size 14439
+oid sha256:fb1f285c2e8ce7b907118ccf23b5cb322a34d0e9eb54ad8436c82bf6abb8cfb2
+size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a08068423bd0da8de286f2bfe952fac174abba9ea4b1b0d5c4dc9fed6c69200
-size 14439
+oid sha256:b32a0be0231f2f19d42d8561635e493d94c812c82d1070981857c9fbb59cf960
+size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a39f4a2af63c824a2393a7a188b35765b425e608da84400d9022e1ad2be2efc
-size 14503
+oid sha256:847320643082b3f276294a5fa2113e3868a05e1a1e4d298c40cb20665e82af38
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21fa0c13fc0e3348f6228394f5e318945295debe26ba21ec91b2c06a47593869
+oid sha256:f427c751ea4b109969727e0c5f2ef9ef6fd7587de8192ab50fc2201ab4ba3ed9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.868041300284935,
-  "global_step": 420000,
+  "epoch": 13.174423236006005,
+  "global_step": 430000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8406,11 +8406,211 @@
       "eval_samples_per_second": 1947.554,
       "eval_steps_per_second": 31.161,
       "step": 420000
+    },
+    {
+      "epoch": 12.88,
+      "learning_rate": 2.9586456905128618e-05,
+      "loss": 0.3162,
+      "step": 420500
+    },
+    {
+      "epoch": 12.9,
+      "learning_rate": 2.9346475051519687e-05,
+      "loss": 0.3163,
+      "step": 421000
+    },
+    {
+      "epoch": 12.9,
+      "eval_loss": 0.7781884670257568,
+      "eval_runtime": 0.5072,
+      "eval_samples_per_second": 1971.754,
+      "eval_steps_per_second": 31.548,
+      "step": 421000
+    },
+    {
+      "epoch": 12.91,
+      "learning_rate": 2.910786732472815e-05,
+      "loss": 0.3162,
+      "step": 421500
+    },
+    {
+      "epoch": 12.93,
+      "learning_rate": 2.887063633412981e-05,
+      "loss": 0.3161,
+      "step": 422000
+    },
+    {
+      "epoch": 12.93,
+      "eval_loss": 0.7753953337669373,
+      "eval_runtime": 0.5016,
+      "eval_samples_per_second": 1993.582,
+      "eval_steps_per_second": 31.897,
+      "step": 422000
+    },
+    {
+      "epoch": 12.94,
+      "learning_rate": 2.863478467404478e-05,
+      "loss": 0.3159,
+      "step": 422500
+    },
+    {
+      "epoch": 12.96,
+      "learning_rate": 2.8400314923709112e-05,
+      "loss": 0.3158,
+      "step": 423000
+    },
+    {
+      "epoch": 12.96,
+      "eval_loss": 0.7729361653327942,
+      "eval_runtime": 0.5075,
+      "eval_samples_per_second": 1970.45,
+      "eval_steps_per_second": 31.527,
+      "step": 423000
+    },
+    {
+      "epoch": 12.98,
+      "learning_rate": 2.816722964724636e-05,
+      "loss": 0.3159,
+      "step": 423500
+    },
+    {
+      "epoch": 12.99,
+      "learning_rate": 2.793553139363981e-05,
+      "loss": 0.3157,
+      "step": 424000
+    },
+    {
+      "epoch": 12.99,
+      "eval_loss": 0.7751319408416748,
+      "eval_runtime": 0.5075,
+      "eval_samples_per_second": 1970.502,
+      "eval_steps_per_second": 31.528,
+      "step": 424000
+    },
+    {
+      "epoch": 13.01,
+      "learning_rate": 2.7705222696704366e-05,
+      "loss": 0.3159,
+      "step": 424500
+    },
+    {
+      "epoch": 13.02,
+      "learning_rate": 2.7476306075059096e-05,
+      "loss": 0.3157,
+      "step": 425000
+    },
+    {
+      "epoch": 13.02,
+      "eval_loss": 0.7777685523033142,
+      "eval_runtime": 0.5223,
+      "eval_samples_per_second": 1914.553,
+      "eval_steps_per_second": 30.633,
+      "step": 425000
+    },
+    {
+      "epoch": 13.04,
+      "learning_rate": 2.7248784032099478e-05,
+      "loss": 0.3157,
+      "step": 425500
+    },
+    {
+      "epoch": 13.05,
+      "learning_rate": 2.7022659055970144e-05,
+      "loss": 0.3156,
+      "step": 426000
+    },
+    {
+      "epoch": 13.05,
+      "eval_loss": 0.7756606340408325,
+      "eval_runtime": 0.511,
+      "eval_samples_per_second": 1957.114,
+      "eval_steps_per_second": 31.314,
+      "step": 426000
+    },
+    {
+      "epoch": 13.07,
+      "learning_rate": 2.6797933619537604e-05,
+      "loss": 0.3155,
+      "step": 426500
+    },
+    {
+      "epoch": 13.08,
+      "learning_rate": 2.6574610180363166e-05,
+      "loss": 0.3155,
+      "step": 427000
+    },
+    {
+      "epoch": 13.08,
+      "eval_loss": 0.7737278938293457,
+      "eval_runtime": 0.5036,
+      "eval_samples_per_second": 1985.649,
+      "eval_steps_per_second": 31.77,
+      "step": 427000
+    },
+    {
+      "epoch": 13.1,
+      "learning_rate": 2.6352691180676286e-05,
+      "loss": 0.3157,
+      "step": 427500
+    },
+    {
+      "epoch": 13.11,
+      "learning_rate": 2.6132179047347505e-05,
+      "loss": 0.3156,
+      "step": 428000
+    },
+    {
+      "epoch": 13.11,
+      "eval_loss": 0.7748771905899048,
+      "eval_runtime": 0.5178,
+      "eval_samples_per_second": 1931.107,
+      "eval_steps_per_second": 30.898,
+      "step": 428000
+    },
+    {
+      "epoch": 13.13,
+      "learning_rate": 2.5913076191862238e-05,
+      "loss": 0.3156,
+      "step": 428500
+    },
+    {
+      "epoch": 13.14,
+      "learning_rate": 2.5695385010294165e-05,
+      "loss": 0.3156,
+      "step": 429000
+    },
+    {
+      "epoch": 13.14,
+      "eval_loss": 0.7763614058494568,
+      "eval_runtime": 0.5128,
+      "eval_samples_per_second": 1949.92,
+      "eval_steps_per_second": 31.199,
+      "step": 429000
+    },
+    {
+      "epoch": 13.16,
+      "learning_rate": 2.5479107883279144e-05,
+      "loss": 0.3155,
+      "step": 429500
+    },
+    {
+      "epoch": 13.17,
+      "learning_rate": 2.5264247175989292e-05,
+      "loss": 0.3151,
+      "step": 430000
+    },
+    {
+      "epoch": 13.17,
+      "eval_loss": 0.7742259502410889,
+      "eval_runtime": 0.5135,
+      "eval_samples_per_second": 1947.536,
+      "eval_steps_per_second": 31.161,
+      "step": 430000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.341836397310529e+22,
+  "total_flos": 1.3737843123927814e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a1dec101691ebd7c104c916b6fbf2b961123d72841379924840b574ab6cdb5
+oid sha256:f68b8d9c04c07b07e7749f58776534bd53918c6e2c126a3b13ccf6e4c8fe0c11
 size 102501541