Training in progress, step 230000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a40ae38fb36d58e51d1115a0ffe2456ed04e074ef34058cb0e87aed44c8749c
+oid sha256:fc34397f53638aed3e1f7a8fec48fd945fe9d9a65862e2d30b0c18c847384362
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10097219a660b41bb145e7706c7d6f55222a5f2edc7e876d75c0a98689203eb2
+oid sha256:4a6f4b993c3e5de4e91e3f11164ead7579089c5cd884e3548feacf51898e103a
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24fad87df726ddb772c9cb0d65a2287f26959859abcdfd31a878c712083b0ad
+oid sha256:44d51ee7e5bc13fe73a3bcf57ad347fa22b3599a7d682e2e8a541926fd4330c8
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92de4a3d2058b3ce7b32a9cce1c0af01d1561a150ed18aab859e87d677cd3e5
+oid sha256:d56ac9935105b68f299f8fa21719a2673f088d35488fddd5fa62d8866469f5f5
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65d3255696500543d0622932269f1d53ce3922d103b14f2f2c1083844f3a484
-size 14439
+oid sha256:2738bd73d910d7af8da2f55f99c628d098f5213ea57df8ec541f1d8d067bf6de
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa2d72d91bc1245eb1895f8dc7e0d0a135c4c74e82bc0564ae764117f596160
+oid sha256:e2c56ac3ff977fd6146b9151ff886620564565fb7b6256b4c917e31e654c4ed6
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90281c7a304663a504e1f9c6a24dafa78aa1aa7b7e1d73398e43919f9e0a3e35
+oid sha256:77be04c57a43b741a7c74fdd71f54e13c7f455ba94a43817c822b41fc4e2570c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.3594453861071663,
-  "global_step": 220000,
+  "epoch": 3.5121474491120375,
+  "global_step": 230000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1634,11 +1634,85 @@
       "eval_samples_per_second": 930.139,
       "eval_steps_per_second": 14.882,
       "step": 220000
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 0.00013910295478514106,
+      "loss": 0.3079,
+      "step": 221000
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.0001389785955603722,
+      "loss": 0.3077,
+      "step": 222000
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 0.00013885359135513154,
+      "loss": 0.3073,
+      "step": 223000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 0.000138727943536445,
+      "loss": 0.3064,
+      "step": 224000
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.00013860165347837698,
+      "loss": 0.3066,
+      "step": 225000
+    },
+    {
+      "epoch": 3.44,
+      "eval_runtime": 1.0901,
+      "eval_samples_per_second": 917.309,
+      "eval_steps_per_second": 14.677,
+      "step": 225000
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 0.00013847472256201535,
+      "loss": 0.306,
+      "step": 226000
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 0.00013834715217545625,
+      "loss": 0.3058,
+      "step": 227000
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 0.000138218943713789,
+      "loss": 0.3056,
+      "step": 228000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.0001380900985790808,
+      "loss": 0.3054,
+      "step": 229000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 0.00013796061818036138,
+      "loss": 0.3051,
+      "step": 230000
+    },
+    {
+      "epoch": 3.51,
+      "eval_runtime": 1.0217,
+      "eval_samples_per_second": 978.715,
+      "eval_steps_per_second": 15.659,
+      "step": 230000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.542203771463191e+22,
+  "total_flos": 1.612304032493538e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10097219a660b41bb145e7706c7d6f55222a5f2edc7e876d75c0a98689203eb2
+oid sha256:4a6f4b993c3e5de4e91e3f11164ead7579089c5cd884e3548feacf51898e103a
 size 449471589