Training in progress, step 220000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6726cc29ffbd179a11fbc16d86e9b622977d56af7affe8432ce17ac7f0c3324c
+oid sha256:8a40ae38fb36d58e51d1115a0ffe2456ed04e074ef34058cb0e87aed44c8749c
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25943354903cd35afbe5a9d2bfdd9b41bedaf40773891780d5be2bd5e21bdecd
+oid sha256:10097219a660b41bb145e7706c7d6f55222a5f2edc7e876d75c0a98689203eb2
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03fb7438c7a7d082a41521ad34b09e54c24c6f0ce434446a8cee447a9825e2b
+oid sha256:e24fad87df726ddb772c9cb0d65a2287f26959859abcdfd31a878c712083b0ad
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc9d9f513ad52cd61a225040b44572cf8ad6a7b8c109e5c0f358d82b01eeccf1
+oid sha256:c92de4a3d2058b3ce7b32a9cce1c0af01d1561a150ed18aab859e87d677cd3e5
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9d3b6fefa1771a4c0591688a8a75e14c07fabc888c3cb2da62c9a866f74518
-size 14503
+oid sha256:f65d3255696500543d0622932269f1d53ce3922d103b14f2f2c1083844f3a484
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81ca6dfbee96ec9e54db682b05df0c1c63341958079572fddfe5a0fdd3446e54
+oid sha256:7fa2d72d91bc1245eb1895f8dc7e0d0a135c4c74e82bc0564ae764117f596160
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300ca51e5088cb48f99d1cdf1919949938caf62a53f95795867484c1a5c8ec3a
+oid sha256:90281c7a304663a504e1f9c6a24dafa78aa1aa7b7e1d73398e43919f9e0a3e35
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.206743323102295,
-  "global_step": 210000,
+  "epoch": 3.3594453861071663,
+  "global_step": 220000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1560,11 +1560,85 @@
       "eval_samples_per_second": 977.233,
       "eval_steps_per_second": 15.636,
       "step": 210000
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.0001403107774233577,
+      "loss": 0.3098,
+      "step": 211000
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 0.00014019294163068597,
+      "loss": 0.3093,
+      "step": 212000
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.00014007444757764835,
+      "loss": 0.3093,
+      "step": 213000
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.0001399552965600768,
+      "loss": 0.3088,
+      "step": 214000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 0.0001398354898809877,
+      "loss": 0.3089,
+      "step": 215000
+    },
+    {
+      "epoch": 3.28,
+      "eval_runtime": 1.0098,
+      "eval_samples_per_second": 990.287,
+      "eval_steps_per_second": 15.845,
+      "step": 215000
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 0.0001397150288505678,
+      "loss": 0.3315,
+      "step": 216000
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 0.00013959391478615959,
+      "loss": 0.628,
+      "step": 217000
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.00013947214901224706,
+      "loss": 0.3112,
+      "step": 218000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 0.0001393497328604412,
+      "loss": 0.3094,
+      "step": 219000
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.00013922666766946545,
+      "loss": 0.3082,
+      "step": 220000
+    },
+    {
+      "epoch": 3.36,
+      "eval_runtime": 1.0751,
+      "eval_samples_per_second": 930.139,
+      "eval_steps_per_second": 14.882,
+      "step": 220000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.4721035104328438e+22,
+  "total_flos": 1.542203771463191e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25943354903cd35afbe5a9d2bfdd9b41bedaf40773891780d5be2bd5e21bdecd
+oid sha256:10097219a660b41bb145e7706c7d6f55222a5f2edc7e876d75c0a98689203eb2
 size 449471589