Training in progress, step 740000

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/scratch/project/open-28-68/experiments/PIXE4L/checkpoint-500000",
   "architectures": [
     "PIXELForPreTraining"
   ],

last-checkpoint/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/scratch/project/open-28-68/experiments/PIXE4L/checkpoint-500000",
   "architectures": [
     "PIXELForPreTraining"
   ],

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be007eb114cc618f1ceaa130909e92fd5731bc7aad8602b4ed98f81b57d25bf
+oid sha256:805548c743510f486c0e3cafaf62492563552db80c61a528b88dfc14156e2814
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4c2b3e5d29d09f4a111c5075cde8ee07ba7f3b202fd9634b12a3a9c596859e
+oid sha256:296c6aaab4847ecb5d07fe54cb49d65e61e6090c68bde2218dfe7ea08ed3e660
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472c99e6947863db3f1c3d882d64923234eaab4acafbf699ca3ec4467c8ba935
+oid sha256:bf344b9ec4215ee98f16bce0e02ee40b6e5c092279cc7f6a32dfe236cff7afc6
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cced04411b336cffec34790d9efd6c44e0f42ec0710b270ba40018e4d2110bd3
+oid sha256:cc92effedeccd16901849219ae891115ace4bd7a1c1cdf152eb099e8c96c6bee
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3761d69b35d8301192dc513e1e8b4eb43934633a73f8a9567ed32e9ce5136e04
+oid sha256:857478dd9ec2db044674ad6be04e7144b86c5a76821e6954aafd045fa1b312a6
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb187bb03db539c4db87f036b94065ed1b4bc8ae6a103a3d335b3b87fb02788
+oid sha256:3f382ada430034469f2e78c286fdd07014f90f8504536cd744210fbc5182b298
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a234a61c6f373c55eead9dc4f863dd69f6b355d0e31c4f71324cdbe0628f412
+oid sha256:4c85d98bde2befb457801eca3140a143937cc9b5b6f825a80d2457ebead30cda
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a481c02af20ead0436feb53d8a01d57cdc94addc339ab22944f77b00d9318fa
+oid sha256:d9f62f8da6710d79d7851f439066c1bf95a591d8db103277b62b735026a20c3f
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae53946121d7ea1cdb1ff678f657136fa4e5d4bad1a9f26aa0386c6bb047c44e
+oid sha256:42c7ae700f0e8d07226680467466582dded5a78267c78b9a89a379334bbfa4fb
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64797a5397bc5a26908cb86c3611823652cf8c230fe6c26bd266a0f5beb30f2f
+oid sha256:8f35f777a57f1fd6316999cc25ac21cb7e613cb7f78dba83f1169b4266f82461
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647e93cd3a2419679fdb9a7ca8861633886e70429797716b24c74206efebd08a
+oid sha256:81b89358714a44d405abb646a2ee62534cee1adcea99cfb2ad730fe2c194dd0c
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4593053706435737,
-  "global_step": 730000,
+  "epoch": 1.0199296880605224,
+  "global_step": 740000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8766,11 +8766,131 @@
       "learning_rate": 3.6097654906852405e-05,
       "loss": 0.2947,
       "step": 730000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.600756545654988e-05,
+      "loss": 0.2941,
+      "step": 730500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.591759627988353e-05,
+      "loss": 0.2945,
+      "step": 731000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.582774762282568e-05,
+      "loss": 0.2945,
+      "step": 731500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.573801973101913e-05,
+      "loss": 0.2942,
+      "step": 732000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.564841284977646e-05,
+      "loss": 0.2943,
+      "step": 732500
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.5558927224079534e-05,
+      "loss": 0.2949,
+      "step": 733000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.546956309857859e-05,
+      "loss": 0.2946,
+      "step": 733500
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.5380320717591716e-05,
+      "loss": 0.2944,
+      "step": 734000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.5291200325104234e-05,
+      "loss": 0.2936,
+      "step": 734500
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.5202202164767836e-05,
+      "loss": 0.2943,
+      "step": 735000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.511332647990014e-05,
+      "loss": 0.294,
+      "step": 735500
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.5024573513483864e-05,
+      "loss": 0.2939,
+      "step": 736000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.493594350816619e-05,
+      "loss": 0.2944,
+      "step": 736500
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.484743670625822e-05,
+      "loss": 0.2943,
+      "step": 737000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.4759053349734126e-05,
+      "loss": 0.2938,
+      "step": 737500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.467079368023068e-05,
+      "loss": 0.2937,
+      "step": 738000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.458265793904642e-05,
+      "loss": 0.2947,
+      "step": 738500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.449464636714107e-05,
+      "loss": 0.2941,
+      "step": 739000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.4406759205134966e-05,
+      "loss": 0.2939,
+      "step": 739500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.431899669330819e-05,
+      "loss": 0.2936,
+      "step": 740000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.935320741341352e+22,
+  "total_flos": 5.002915204156979e+22,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ca84487dad0574bdcb73e4b4abf612d6d434fdea0be0c3c3d3353642927743
+oid sha256:4ea440fc076fb2514e98c2cd96a97d8addd24cd23a802fc2aa93d591ef3c28a9
 size 3835

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4c2b3e5d29d09f4a111c5075cde8ee07ba7f3b202fd9634b12a3a9c596859e
+oid sha256:296c6aaab4847ecb5d07fe54cb49d65e61e6090c68bde2218dfe7ea08ed3e660
 size 449450757

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ca84487dad0574bdcb73e4b4abf612d6d434fdea0be0c3c3d3353642927743
+oid sha256:4ea440fc076fb2514e98c2cd96a97d8addd24cd23a802fc2aa93d591ef3c28a9
 size 3835