Training in progress, step 170000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c4479b7100b24acffdfd7fb1cff497645cac828edc9bce49ad39669a19e6f1
+oid sha256:6f9a70132918b6ab165a91d577d712613356dca52075d5c7c05f34314005b476
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45b8970c2fcdae44788b5d4ade86d7949295115594ab3b0d456c282cadcd002
+oid sha256:04e4608999d97a58a30e39361b70b419f5aef3e2535ed3ca55c26e98dfa526a2
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a1d97b2752462543b92ffd0f23922ddd8ffff9e6ba2aaf2b57366a0cea0714
+oid sha256:ef92b44093f62f1441b173acbe3fd1139e94c5c223ed6a54381a9d3cb2f5c022
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29849d211b595c5ac9c137dcd37e20da1964e185621f9086f1491a26e0f460bc
+oid sha256:161efcaf59347006251947d35ba8e577aead293e95ee199281ec31fb424a8671
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99c0c1e436962d7938fd416d17b1f2b444137c2e5f765032e46157e9b60a3ea
-size 14503
+oid sha256:a5b4db0eb85867b5e22ab5799a8329f0f5930ac32c5205c1b81fbef9bb0ad0ab
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c80b4bceef61474bcae1ecae0d1e95d0713b469a0fdc8873f2259acce5bd7e
+oid sha256:ed9a9a05da89d28b0f8404cc60f79e71945e2a52c47886846fb03eae29b9b7e7
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b0f5af299b689f18c326dad86c4c4c3f628480672d22f22ec90ae66ce6a4f1
+oid sha256:7e6e6dbb6845e268a54a5a558c86918603b34b6bae9a32a1510a924b34f03635
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.443233008077939,
-  "global_step": 160000,
+  "epoch": 2.59593507108281,
+  "global_step": 170000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1190,11 +1190,85 @@
       "eval_samples_per_second": 980.452,
       "eval_steps_per_second": 15.687,
       "step": 160000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.00014533679374921493,
+      "loss": 0.3259,
+      "step": 161000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.00014525336046375905,
+      "loss": 0.3254,
+      "step": 162000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 0.00014516921357800766,
+      "loss": 0.3251,
+      "step": 163000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00014508435401217759,
+      "loss": 0.3244,
+      "step": 164000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.00014499878269427948,
+      "loss": 0.3243,
+      "step": 165000
+    },
+    {
+      "epoch": 2.52,
+      "eval_runtime": 1.0655,
+      "eval_samples_per_second": 938.486,
+      "eval_steps_per_second": 15.016,
+      "step": 165000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.00014491250056010758,
+      "loss": 0.3236,
+      "step": 166000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.00014482550855322943,
+      "loss": 0.3233,
+      "step": 167000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.0001447378076249757,
+      "loss": 0.3231,
+      "step": 168000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 0.00014464939873442973,
+      "loss": 0.3228,
+      "step": 169000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00014456028284841693,
+      "loss": 0.3221,
+      "step": 170000
+    },
+    {
+      "epoch": 2.6,
+      "eval_runtime": 1.1756,
+      "eval_samples_per_second": 850.656,
+      "eval_steps_per_second": 13.611,
+      "step": 170000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.1216028623492568e+22,
+  "total_flos": 1.191703123379604e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45b8970c2fcdae44788b5d4ade86d7949295115594ab3b0d456c282cadcd002
+oid sha256:04e4608999d97a58a30e39361b70b419f5aef3e2535ed3ca55c26e98dfa526a2
 size 449471589