Training in progress, step 650000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:570fd9971dd127676195908f1f0168c560d379e06053db1ec1c6889a24e76909
+oid sha256:d0094043a45ee455c34cdbf7e5ed868b844e2cc109c62c31adc8eabe0945cd55
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407afab53633fc482bbe780f5224c6b1388fc7b7dd3f17aa73388222d02bc81c
+oid sha256:afca04d573f1bb3162caabe1bb7b946edefb5cb8fa7beeabdf4a9618ee0ba3ea
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:069c7b8d28935c1bdaf707018f31232b5c5d0b17ca264ac835e0cab62f47f60b
+oid sha256:8afdb75bc9c4b3b8d3f36f77e21f0d34f0633a3fe673f092dd264b1121465456
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acfb6c5ca1e2a8aae6849b592c5e4c4b839246ca00f42f46fa8da24fee6f7051
+oid sha256:334f507bebbd8e2eb32a3a52e1460054ef235aff9b388a6044a2cf6124700604
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed15d29f5bdaa33109b0c66a9aa2dbc57339a469e3f71f40bec5ec342e0d6d49
+oid sha256:e1fe6196ed311cd8ddb4f7739bbce785a7482bd7a8a89fc83aadbb7b199e0b80
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962d2f5974f30660f555e22cdf0c12b334de1b8fc49a6a5192e63c3a6ee6eebe
+oid sha256:7c16cf0e46ab235f9e251974c64ca93772ae50300b4f1505ff50d8f4e2246708
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2e736f0ce5f395a825ebebcf342c762745706534807a9b43b2a6a713704726
+oid sha256:dea98aa1b40d4dde89de24ce301ffc44f0dee70fb25e51e28dfe6b65e5e6240d
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bff10bd0517565104b7a365f7830fc50ca6a2c535ddf94460fc2737ad38c9a7
+oid sha256:476caa126ce91db0ad93d8541266aa7e5c1a71c0473ab678864fc300fdd08e70
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24fffbd4923bc1f675f8117f531217edf35f82264eb436b97401dab9e4eeeaa0
+oid sha256:3637d3be8f9c8d6ff9f1958a71fe2d848eaecb87ddf0683d13eaae5352425491
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d716524e67d0b69cb1b5ffc99aa56ed5a73b186c4b6bfbd6ff0ef38267147113
+oid sha256:b62727907f78fc16c3f0e4b91fbdcc94bc537750512333e674d8d2c4dcd12411
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a35091ba68234fa026466686321e8ce53cfe05ba57973184932ffc7464e369
+oid sha256:cb24dd41ced00dc957e38e97b930833d2e52e5141588b4ec2f84d6e2ee23293d
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2793910098792973,
-  "global_step": 640000,
+  "epoch": 1.2993814944086615,
+  "global_step": 650000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7686,11 +7686,131 @@
       "learning_rate": 5.401619257572453e-05,
       "loss": 0.3007,
       "step": 640000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.390875461869379e-05,
+      "loss": 0.3011,
+      "step": 640500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.3801387994131576e-05,
+      "loss": 0.3012,
+      "step": 641000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.36940929955742e-05,
+      "loss": 0.3011,
+      "step": 641500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.358686991636209e-05,
+      "loss": 0.3005,
+      "step": 642000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.347971904963904e-05,
+      "loss": 0.3004,
+      "step": 642500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.3372640688351476e-05,
+      "loss": 0.3002,
+      "step": 643000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.326563512524748e-05,
+      "loss": 0.3005,
+      "step": 643500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.315870265287618e-05,
+      "loss": 0.2999,
+      "step": 644000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.3051843563586914e-05,
+      "loss": 0.3004,
+      "step": 644500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.294505814952835e-05,
+      "loss": 0.3003,
+      "step": 645000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.28383467026477e-05,
+      "loss": 0.2999,
+      "step": 645500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.2731709514689995e-05,
+      "loss": 0.2997,
+      "step": 646000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.262514687719722e-05,
+      "loss": 0.2999,
+      "step": 646500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.25186590815076e-05,
+      "loss": 0.3007,
+      "step": 647000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.24122464187547e-05,
+      "loss": 0.3007,
+      "step": 647500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.2305909179866635e-05,
+      "loss": 0.3002,
+      "step": 648000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.219964765556536e-05,
+      "loss": 0.3003,
+      "step": 648500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.209346213636584e-05,
+      "loss": 0.2997,
+      "step": 649000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.1987352912575244e-05,
+      "loss": 0.2995,
+      "step": 649500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.188132027429215e-05,
+      "loss": 0.2991,
+      "step": 650000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.326855661422541e+22,
+  "total_flos": 4.394457756168279e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407afab53633fc482bbe780f5224c6b1388fc7b7dd3f17aa73388222d02bc81c
+oid sha256:afca04d573f1bb3162caabe1bb7b946edefb5cb8fa7beeabdf4a9618ee0ba3ea
 size 449450757