Training in progress, step 270000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80fb9af3e1214502ea925d3599d3b6efda5d8711659b2c90eec052ea369703f7
+oid sha256:6c02aa896c2ee6ca7e7195a5ec6659df9dfbcf711b2a086585d06699889d2a77
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab3051ab890d6ef671960c94245505fe32b7894ead10b5d7877e9fabce99ffc
+oid sha256:2a8d446dc34b2bbf6e36c989da495609d6f957caff490ddd65c84402cd84a1a7
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72757db14fb233c9a7d81cef99ff1e84d48a76f7d40a8342399239cffc8c3e9f
+oid sha256:726a297059cefb8d3acf77f8c6eb72aad5247d33b79ba9f00d002be1f6ad5127
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8fbef78331483305594b3f85c6f32ce7bab8b9f165e2fb904f362fb3239105f
-size 14567
+oid sha256:9deb037f8188638d71fed3178b79cf150c9aa2692b1c0ab4a2586496ec3fa41c
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31003ab7fcda6d6f6ff162f700b04d49c90c118129057bd1f4ee624c393e588
+oid sha256:92c69465d2a6dab3d96db9a2b18d912729d3e1e1b1af7c09352e2b892ef04628
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da43c666b0af3cbe77f19371961622ab99b1114e6beec7303d695cd496caee4
+oid sha256:eec7d7dce919d39a021b1844dce51ccb12ffead3d1363108b5bdbc846b3db389
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04396ff3c1feb0819b380c26b60d419205385a8e624d7c59a71eaea179611c46
+oid sha256:7030c55d7b4ceacafe5134891d17b9fbbdf3b9a0eab868717813c67134ec0794
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.970253638126651,
-  "global_step": 260000,
+  "epoch": 4.122955701131522,
+  "global_step": 270000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1930,11 +1930,85 @@
       "eval_samples_per_second": 955.963,
       "eval_steps_per_second": 15.295,
       "step": 260000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 0.00013363964030785422,
+      "loss": 0.2983,
+      "step": 261000
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00013349061626121578,
+      "loss": 0.2982,
+      "step": 262000
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 0.00013334100724976783,
+      "loss": 0.2977,
+      "step": 263000
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 0.0001331908149096106,
+      "loss": 0.2976,
+      "step": 264000
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 0.00013304004088322342,
+      "loss": 0.2978,
+      "step": 265000
+    },
+    {
+      "epoch": 4.05,
+      "eval_runtime": 1.0225,
+      "eval_samples_per_second": 978.001,
+      "eval_steps_per_second": 15.648,
+      "step": 265000
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 0.00013288868681944692,
+      "loss": 0.2971,
+      "step": 266000
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00013273675437346487,
+      "loss": 0.2972,
+      "step": 267000
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 0.00013258424520678618,
+      "loss": 0.2969,
+      "step": 268000
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.00013243116098722663,
+      "loss": 0.2968,
+      "step": 269000
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 0.00013227750338889077,
+      "loss": 0.2966,
+      "step": 270000
+    },
+    {
+      "epoch": 4.12,
+      "eval_runtime": 1.1084,
+      "eval_samples_per_second": 902.192,
+      "eval_steps_per_second": 14.435,
+      "step": 270000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.8226048155845795e+22,
+  "total_flos": 1.892704419546778e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab3051ab890d6ef671960c94245505fe32b7894ead10b5d7877e9fabce99ffc
+oid sha256:2a8d446dc34b2bbf6e36c989da495609d6f957caff490ddd65c84402cd84a1a7
 size 449471589