Training in progress, step 400000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4182e3962d3a040ab734b61da56d604a525bd5f2d61cf2e3f5b36f5f0ee5bc
+oid sha256:c173163e338165d1fe37ba14405dbe53b272a5ca3e52267ff5c851a862f35da2
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf099ec439cbdff64f3d3b55ea1f32c5386c40432f4a5418054927a7f60a7a71
+oid sha256:e086dc2588b852e6182d32ad6ab8f484673dafebd51e08d7a801497b43f4fe30
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c992fbbd7cb3ac4ba0d93a3c933e4f1384224ccab41105813a52127e0943be99
-size 14439
+oid sha256:e8c3463e55c2827928dfa1b830953cf8eccfe7f6ab2a72af5d13db1a192ce98b
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56d30c04eda66f1451428a4a1783f0e0b3c6401e9dc47a22a9a23c6f9d71d1c
+oid sha256:9fbc08cc620efc6ad1b3090a70819940a5a6dca3de71f9ffed8d3aa8dee8bdcc
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252bfaee072432d2b9efeeb2414b13c69cfea81ef8749ee867aa8e12e0fa2d52
+oid sha256:5b8c2cc612f6c582ed6586d60fa04580b6f35775b91158d5b84ddd0f0a65ddd3
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e684c71dc83c29adb7891edadb6f809a0f52fc37575c6edaa71e9c79dd0a26
+oid sha256:60fbf66cb187e2da54f6604ee46efd1578eb148d61f9556ffc6254e09665c1a9
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d1c67928001883576d4a56b44f4eee5262f60a7be50b274805186459e2f4ae5
+oid sha256:591046c9a1cdb63ed76af20e30931eec37ddea64d1cedd0e21228761a5b0c89f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.955380457189976,
-  "global_step": 390000,
+  "epoch": 6.108082520194848,
+  "global_step": 400000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2892,11 +2892,85 @@
       "eval_samples_per_second": 976.954,
       "eval_steps_per_second": 15.631,
       "step": 390000
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 0.00011001384164990662,
+      "loss": 0.2775,
+      "step": 391000
+    },
+    {
+      "epoch": 5.99,
+      "learning_rate": 0.00010980455040955506,
+      "loss": 0.2769,
+      "step": 392000
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00010959493323141538,
+      "loss": 0.2773,
+      "step": 393000
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 0.00010938499240782739,
+      "loss": 0.277,
+      "step": 394000
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.00010917473023467032,
+      "loss": 0.277,
+      "step": 395000
+    },
+    {
+      "epoch": 6.03,
+      "eval_runtime": 1.0769,
+      "eval_samples_per_second": 928.59,
+      "eval_steps_per_second": 14.857,
+      "step": 395000
+    },
+    {
+      "epoch": 6.05,
+      "learning_rate": 0.00010896414901133761,
+      "loss": 0.2766,
+      "step": 396000
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 0.00010875325104071177,
+      "loss": 0.2768,
+      "step": 397000
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 0.00010854203862913927,
+      "loss": 0.2765,
+      "step": 398000
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 0.00010833051408640509,
+      "loss": 0.2763,
+      "step": 399000
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 0.00010811867972570786,
+      "loss": 0.2767,
+      "step": 400000
+    },
+    {
+      "epoch": 6.11,
+      "eval_runtime": 1.1081,
+      "eval_samples_per_second": 902.417,
+      "eval_steps_per_second": 14.439,
+      "step": 400000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.733906894842795e+22,
+  "total_flos": 2.8040064988049933e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf099ec439cbdff64f3d3b55ea1f32c5386c40432f4a5418054927a7f60a7a71
+oid sha256:e086dc2588b852e6182d32ad6ab8f484673dafebd51e08d7a801497b43f4fe30
 size 449471589