Training in progress, step 280000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c02aa896c2ee6ca7e7195a5ec6659df9dfbcf711b2a086585d06699889d2a77
+oid sha256:a09f2253c2da714db2381b4b6c94afe74f0c5bcca5dfab2a4d09f3bc77a1a830
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8d446dc34b2bbf6e36c989da495609d6f957caff490ddd65c84402cd84a1a7
+oid sha256:f568156f561dbbcf7503a348dffb485dffe24e58ccf5c28c9e6be3fa82361daf
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:726a297059cefb8d3acf77f8c6eb72aad5247d33b79ba9f00d002be1f6ad5127
+oid sha256:59a9fce20181e682cc72fca21c2c1d9ae33919a24109d9c3b0015bbe48914330
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9deb037f8188638d71fed3178b79cf150c9aa2692b1c0ab4a2586496ec3fa41c
+oid sha256:6f3a816674b62f2ebc9df81821d70aa6368f98c31e4a2d5592af6a40fe48198f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c69465d2a6dab3d96db9a2b18d912729d3e1e1b1af7c09352e2b892ef04628
+oid sha256:913db27023ff5c862ac68d8593e062aa9da19c0798da56d43a2896de4cc6dca5
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec7d7dce919d39a021b1844dce51ccb12ffead3d1363108b5bdbc846b3db389
+oid sha256:77a839f0e74d399ee3f4539eaee8bff7b1db922601d5d69fcbfe490fd00b94d2
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7030c55d7b4ceacafe5134891d17b9fbbdf3b9a0eab868717813c67134ec0794
+oid sha256:9756e1f2ce28cffe3ad2413091d8de7b6aa9409f983eeb48589ea2a1911fb547
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.122955701131522,
-  "global_step": 270000,
+  "epoch": 4.275657764136393,
+  "global_step": 280000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2004,11 +2004,85 @@
       "eval_samples_per_second": 902.192,
       "eval_steps_per_second": 14.435,
       "step": 270000
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 0.00013212327409215343,
+      "loss": 0.296,
+      "step": 271000
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 0.0001319684747836415,
+      "loss": 0.2958,
+      "step": 272000
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 0.0001318131071562154,
+      "loss": 0.2961,
+      "step": 273000
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 0.00013165717290895067,
+      "loss": 0.2957,
+      "step": 274000
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 0.0001315006737471192,
+      "loss": 0.2955,
+      "step": 275000
+    },
+    {
+      "epoch": 4.2,
+      "eval_runtime": 1.0552,
+      "eval_samples_per_second": 947.654,
+      "eval_steps_per_second": 15.162,
+      "step": 275000
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.0001313436113821708,
+      "loss": 0.2952,
+      "step": 276000
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 0.00013118598753171425,
+      "loss": 0.2951,
+      "step": 277000
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 0.0001310278039194988,
+      "loss": 0.2951,
+      "step": 278000
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 0.00013086906227539506,
+      "loss": 0.2952,
+      "step": 279000
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 0.00013070976433537623,
+      "loss": 0.2946,
+      "step": 280000
+    },
+    {
+      "epoch": 4.28,
+      "eval_runtime": 1.0293,
+      "eval_samples_per_second": 971.532,
+      "eval_steps_per_second": 15.545,
+      "step": 280000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.892704419546778e+22,
+  "total_flos": 1.962804680577125e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8d446dc34b2bbf6e36c989da495609d6f957caff490ddd65c84402cd84a1a7
+oid sha256:f568156f561dbbcf7503a348dffb485dffe24e58ccf5c28c9e6be3fa82361daf
 size 449471589