Training in progress, step 310000

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/scratch/project/dd-22-48/experiments/pixel-small/pixel-small/checkpoint-290000",
   "architectures": [
     "PIXELForPreTraining"
   ],

last-checkpoint/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/scratch/project/dd-22-48/experiments/pixel-small/pixel-small/checkpoint-290000",
   "architectures": [
     "PIXELForPreTraining"
   ],

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24fd1effc786c2233fdf34af4b099eff768d956d0bc963f95cfe54130f46f6a4
+oid sha256:7d30543a63c3f49005c19382ae197f2cf2879229339898c2554a8df1a8a2421f
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f0bc998c8c06256cb91869f76891887d067c2f9c20c8788b0dca6b3ad6ca11
+oid sha256:07e69690c144d55eab2611717957556e397812111ed907e27900f2d419339d70
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde6f8fd4d14f48af81d5d82a8cd759def420f78e1b703b22c636bee803f12c9
-size 14439
+oid sha256:548110cdd23dffd1b7f96561a08e3cbe6bf67f48bac9ee8d0ebf3314491785e9
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832d8466b4e7e88ef694c8232544e65041e73b3ee2898ceff0bc790c1b587f8a
+oid sha256:992c07370b8db97dbb38b7b82bcfcf2b4063ad427f2a7c1da17dc6b7936247f4
 size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda76c49a6fd65be7a0e6f97adba0e99ae8ee53bcc455b836ddb29b2aed047b8
-size 14439
+oid sha256:309d45549a36b33343b31b19dff62c40cbca438acddc29ad6300e29a9b1364dd
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa08d606f5576889586b0131f054f767347536bc8282ba2f180514fa58798dd
+oid sha256:0b9ac8da3681828a13f22af7d6fffaed7afbe91d2bf410206cc27808e2ecc0ca
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25cbeea4d686c41f3d146553ed7c30451ac8df4fde4a1f39e397f53ea3d468f9
+oid sha256:9df044a6fee5eeed1506b8dbce5bf547aca68cd5a201fa67f209077ea7b2dfb1
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330bd685917df8b1fbae2148906f7052c5b81a3ff7fb1875852c5926aee0bf41
-size 14439
+oid sha256:c04c575cebc96e7d40383dac3dbdc79efa292cede7a20d6c65225e6c903061e2
+size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c09bcc07426d9c6688ac63a955b16de5936384e559ba4a03ebe59ef81ef814d
-size 14439
+oid sha256:472356308bd424b33e07d9161a75bf7fa03c160c8593923578d6c5cdc5036926
+size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b6c36ce69b8a3eb376852eb39272f44b56a71cb9695804d2ec07e8dd226ccc
-size 14439
+oid sha256:74c5657fa915531128d8604d48f9f541ac95d7782dff879847610bd62a46c3d1
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7914b9f1e3709b1198ec189eb9bb9105cd6b88dedbcbbdd4128934a703cf33e3
+oid sha256:9b8c10dab6d3ee824fc8fe4628d3bf3ceea806ce0d2fbe513f32af4d508ab89e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.191458071632097,
-  "global_step": 300000,
+  "epoch": 9.497840007353167,
+  "global_step": 310000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6006,11 +6006,211 @@
       "eval_samples_per_second": 1927.692,
       "eval_steps_per_second": 30.843,
       "step": 300000
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 0.00011893996636109606,
+      "loss": 0.3307,
+      "step": 300500
+    },
+    {
+      "epoch": 9.22,
+      "learning_rate": 0.00011847572270435852,
+      "loss": 0.3304,
+      "step": 301000
+    },
+    {
+      "epoch": 9.22,
+      "eval_loss": 0.7778551578521729,
+      "eval_runtime": 0.503,
+      "eval_samples_per_second": 1988.252,
+      "eval_steps_per_second": 31.812,
+      "step": 301000
+    },
+    {
+      "epoch": 9.24,
+      "learning_rate": 0.00011801187847126579,
+      "loss": 0.3302,
+      "step": 301500
+    },
+    {
+      "epoch": 9.25,
+      "learning_rate": 0.00011754843873434411,
+      "loss": 0.3302,
+      "step": 302000
+    },
+    {
+      "epoch": 9.25,
+      "eval_loss": 0.7812706232070923,
+      "eval_runtime": 0.4986,
+      "eval_samples_per_second": 2005.479,
+      "eval_steps_per_second": 32.088,
+      "step": 302000
+    },
+    {
+      "epoch": 9.27,
+      "learning_rate": 0.00011708540856169612,
+      "loss": 0.3308,
+      "step": 302500
+    },
+    {
+      "epoch": 9.28,
+      "learning_rate": 0.00011662279301694567,
+      "loss": 0.3306,
+      "step": 303000
+    },
+    {
+      "epoch": 9.28,
+      "eval_loss": 0.7797490358352661,
+      "eval_runtime": 0.5088,
+      "eval_samples_per_second": 1965.516,
+      "eval_steps_per_second": 31.448,
+      "step": 303000
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 0.0001161605971591822,
+      "loss": 0.3299,
+      "step": 303500
+    },
+    {
+      "epoch": 9.31,
+      "learning_rate": 0.00011569882604290559,
+      "loss": 0.3299,
+      "step": 304000
+    },
+    {
+      "epoch": 9.31,
+      "eval_loss": 0.7792276740074158,
+      "eval_runtime": 0.5025,
+      "eval_samples_per_second": 1989.889,
+      "eval_steps_per_second": 31.838,
+      "step": 304000
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 0.00011523748471797075,
+      "loss": 0.3299,
+      "step": 304500
+    },
+    {
+      "epoch": 9.34,
+      "learning_rate": 0.00011477657822953255,
+      "loss": 0.3301,
+      "step": 305000
+    },
+    {
+      "epoch": 9.34,
+      "eval_loss": 0.7853004336357117,
+      "eval_runtime": 0.5155,
+      "eval_samples_per_second": 1939.771,
+      "eval_steps_per_second": 31.036,
+      "step": 305000
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 0.00011431611161799043,
+      "loss": 0.3295,
+      "step": 305500
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 0.0001138560899189335,
+      "loss": 0.3293,
+      "step": 306000
+    },
+    {
+      "epoch": 9.38,
+      "eval_loss": 0.7775614857673645,
+      "eval_runtime": 0.5102,
+      "eval_samples_per_second": 1960.019,
+      "eval_steps_per_second": 31.36,
+      "step": 306000
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 0.00011339651816308543,
+      "loss": 0.3294,
+      "step": 306500
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 0.00011293740137624925,
+      "loss": 0.3292,
+      "step": 307000
+    },
+    {
+      "epoch": 9.41,
+      "eval_loss": 0.784292995929718,
+      "eval_runtime": 0.5164,
+      "eval_samples_per_second": 1936.403,
+      "eval_steps_per_second": 30.982,
+      "step": 307000
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 0.00011247874457925261,
+      "loss": 0.3294,
+      "step": 307500
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 0.0001120205527878927,
+      "loss": 0.329,
+      "step": 308000
+    },
+    {
+      "epoch": 9.44,
+      "eval_loss": 0.7785166501998901,
+      "eval_runtime": 0.5211,
+      "eval_samples_per_second": 1919.185,
+      "eval_steps_per_second": 30.707,
+      "step": 308000
+    },
+    {
+      "epoch": 9.45,
+      "learning_rate": 0.00011156283101288165,
+      "loss": 0.3291,
+      "step": 308500
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 0.00011110558425979132,
+      "loss": 0.3291,
+      "step": 309000
+    },
+    {
+      "epoch": 9.47,
+      "eval_loss": 0.7782018780708313,
+      "eval_runtime": 0.5137,
+      "eval_samples_per_second": 1946.512,
+      "eval_steps_per_second": 31.144,
+      "step": 309000
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 0.00011064881752899906,
+      "loss": 0.3288,
+      "step": 309500
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 0.00011019253581563262,
+      "loss": 0.3294,
+      "step": 310000
+    },
+    {
+      "epoch": 9.5,
+      "eval_loss": 0.7799496054649353,
+      "eval_runtime": 0.5222,
+      "eval_samples_per_second": 1914.938,
+      "eval_steps_per_second": 30.639,
+      "step": 310000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 9.584542271667217e+21,
+  "total_flos": 9.904029410441717e+21,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874bd8e6f0867613bf71e3c5db79d9f3895b88c8bf378c2c5f2571339ab86d76
+oid sha256:2aabb20fef7a59474ee6bfde9597f1a91afcd82e7396daea5b4217f0347b7490
 size 3247

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f0bc998c8c06256cb91869f76891887d067c2f9c20c8788b0dca6b3ad6ca11
+oid sha256:07e69690c144d55eab2611717957556e397812111ed907e27900f2d419339d70
 size 102501541

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874bd8e6f0867613bf71e3c5db79d9f3895b88c8bf378c2c5f2571339ab86d76
+oid sha256:2aabb20fef7a59474ee6bfde9597f1a91afcd82e7396daea5b4217f0347b7490
 size 3247