Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79698e8ce41155df8f2ac96cd99d16ef6b016cb4ff277c5445301a3db1fa101
+oid sha256:67589357f5095310d4686130056aa06ce9ae4e2fa5ce926bd48f51088af92af7
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16799df5e196079b65225695fe6105fc300cf5157671e1537af93401d1b8d74a
+oid sha256:6f8355919230d3848ec5ca15fcb85fb31871fa61b50484347e59854072226bac
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d372c7ec90718e7e982db780f8d7b62ea26c5068bb213efc91ce4e4dbff2188
+oid sha256:56696dbd8b022c9a375dc483a2ed57d389284babd22e89c40b8de9038eb3703d
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200bd99b77ad19fc80e27fc902aca5e36eebe6570a18efbc020b994d75bc6fba
+oid sha256:e0c18c513645e98f74c56b9e9e177b503e18704a58f67fc3838ebaa773205ef1
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f78dbe211932d0c37e15c11f906dcb55aae5aedb42250507005f499cf4150e
+oid sha256:a7657a362d765d540acd9b7e721a68b7cd2eb75cf243194edc5a268c52185c5f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7cd6974be7a03bcf0342d3707956fc7f1e60ef89c3b2bd3445ff8c5a29e4db
+oid sha256:17cd85c4bd32b953041cb6ed12687d174e095b2b2edce062be3f66f2a0041ec7
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4347385b2c0f1e2d9aeca7fb88e1c942d1dae99e52563bdfa6c48a7a4a2bf97f
+oid sha256:82157ec414d7845758afa3fc7a8ceafcaf8d618c9a8c5350ea190a69bffb0ab4
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9013391970925526,
-  "global_step": 190000,
+  "epoch": 3.054041260097424,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1412,11 +1412,85 @@
       "eval_samples_per_second": 988.212,
       "eval_steps_per_second": 15.811,
       "step": 190000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.00014252732722876176,
+      "loss": 0.3149,
+      "step": 191000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0001424229175812373,
+      "loss": 0.3149,
+      "step": 192000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 0.00014231782528668717,
+      "loss": 0.3146,
+      "step": 193000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.00014221205149438394,
+      "loss": 0.3145,
+      "step": 194000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0001421055973610528,
+      "loss": 0.3138,
+      "step": 195000
+    },
+    {
+      "epoch": 2.98,
+      "eval_runtime": 1.0908,
+      "eval_samples_per_second": 916.734,
+      "eval_steps_per_second": 14.668,
+      "step": 195000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.00014199846405085913,
+      "loss": 0.3137,
+      "step": 196000
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.00014189065273539564,
+      "loss": 0.3135,
+      "step": 197000
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.00014178216459366958,
+      "loss": 0.3137,
+      "step": 198000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.00014167300081208988,
+      "loss": 0.3131,
+      "step": 199000
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 0.00014156316258445421,
+      "loss": 0.3125,
+      "step": 200000
+    },
+    {
+      "epoch": 3.05,
+      "eval_runtime": 1.1346,
+      "eval_samples_per_second": 881.333,
+      "eval_steps_per_second": 14.101,
+      "step": 200000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.3319036454402982e+22,
+  "total_flos": 1.4020032494024966e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16799df5e196079b65225695fe6105fc300cf5157671e1537af93401d1b8d74a
+oid sha256:6f8355919230d3848ec5ca15fcb85fb31871fa61b50484347e59854072226bac
 size 449471589