Training in progress, step 290000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a09f2253c2da714db2381b4b6c94afe74f0c5bcca5dfab2a4d09f3bc77a1a830
+oid sha256:f3a8513b0368f6cb2e3381f928e0aa14b5dd1d4d6e81f16afa2b1f5c07381ace
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f568156f561dbbcf7503a348dffb485dffe24e58ccf5c28c9e6be3fa82361daf
+oid sha256:34882c0a1ec238c2b1ad9048809a8c4ec0fe4694d212fa9d7361294be70895cf
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a9fce20181e682cc72fca21c2c1d9ae33919a24109d9c3b0015bbe48914330
+oid sha256:53d2183906572577bb72529bb7cea14ccb3598c2ad81bd496d1690556b2c2fad
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3a816674b62f2ebc9df81821d70aa6368f98c31e4a2d5592af6a40fe48198f
+oid sha256:e47c84ee1a7263145bb05e6bd38ff747cca1ce76d180b5d014131790082d04ac
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913db27023ff5c862ac68d8593e062aa9da19c0798da56d43a2896de4cc6dca5
+oid sha256:5654423abeb0cd8c1ac599d51c54b19e61e2cbf655685c7b1d094b3f86c3ae14
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a839f0e74d399ee3f4539eaee8bff7b1db922601d5d69fcbfe490fd00b94d2
-size 14503
+oid sha256:75741429273458049dfadf451049de4bb7af88e4bb53df1b8babe07272a17a27
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9756e1f2ce28cffe3ad2413091d8de7b6aa9409f983eeb48589ea2a1911fb547
+oid sha256:43486ecf7953ead4f44fd0913517d08c2421c80bd01545c2aa6edfd9bc952a2c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.275657764136393,
-  "global_step": 280000,
+  "epoch": 4.428359827141264,
+  "global_step": 290000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2078,11 +2078,85 @@
       "eval_samples_per_second": 971.532,
       "eval_steps_per_second": 15.545,
       "step": 280000
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.00013054991184149905,
+      "loss": 0.2946,
+      "step": 281000
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 0.00013038950654188476,
+      "loss": 0.2942,
+      "step": 282000
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.00013022855019070005,
+      "loss": 0.2941,
+      "step": 283000
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 0.0001300670445481378,
+      "loss": 0.2937,
+      "step": 284000
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 0.0001299049913803978,
+      "loss": 0.2937,
+      "step": 285000
+    },
+    {
+      "epoch": 4.35,
+      "eval_runtime": 1.0469,
+      "eval_samples_per_second": 955.197,
+      "eval_steps_per_second": 15.283,
+      "step": 285000
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 0.00012974239245966754,
+      "loss": 0.2934,
+      "step": 286000
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 0.0001295792495641028,
+      "loss": 0.2962,
+      "step": 287000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.00012941556447780813,
+      "loss": 0.2931,
+      "step": 288000
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 0.0001292513389908174,
+      "loss": 0.2931,
+      "step": 289000
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 0.0001290865748990742,
+      "loss": 0.2932,
+      "step": 290000
+    },
+    {
+      "epoch": 4.43,
+      "eval_runtime": 1.0143,
+      "eval_samples_per_second": 985.898,
+      "eval_steps_per_second": 15.774,
+      "step": 290000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.962804680577125e+22,
+  "total_flos": 2.032904941607472e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f568156f561dbbcf7503a348dffb485dffe24e58ccf5c28c9e6be3fa82361daf
+oid sha256:34882c0a1ec238c2b1ad9048809a8c4ec0fe4694d212fa9d7361294be70895cf
 size 449471589