Upload with huggingface_hub

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662103ebc4d59eac4149a3a57c8d37aeb12848773184e387b33fd963e993f876
+oid sha256:12a32c1ffd066ca1031cd47bf55dac97d1ede03a36350b6ba3a53e8de9eb5edc
 size 535706209

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8920085e7fda657cc8fb7247be4b9e23e2acc75760e51050e178cdc1d5973bd0
+oid sha256:965c186cd34ef48998516f3897fd2372344d01d738e192274e7d532d01033468
 size 267857393

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc4b64a931ca6f38f6d683f5b3a967bb59072455b66cd85eeb8c432cdef6f43
+oid sha256:ae116f337ea13c917bfe72f8a9fcdc2abd9868b6c33c59696f86db0f3d03d8fa
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f7f9516085d32bba7de1113c329a9952874023962aa001b1e05c81482101c2
+oid sha256:e826da7143c69baae8b508f53f18edfd96a876769ed8e0e96003652aa5c53cc8
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.5875,
   "best_model_checkpoint": "./results/checkpoint-500",
-  "epoch": 17.5,
-  "global_step": 3500,
+  "epoch": 12.5,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -628,261 +628,11 @@
       "eval_steps_per_second": 1.676,
       "eval_total_time_in_seconds": 13.303364610000244,
       "step": 2500
-    },
-    {
-      "epoch": 12.75,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016587090722500763,
-      "eval_loss": 2.5341074466705322,
-      "eval_runtime": 29.8717,
-      "eval_samples_per_second": 26.781,
-      "eval_steps_per_second": 1.674,
-      "eval_total_time_in_seconds": 13.269672578000609,
-      "step": 2550
-    },
-    {
-      "epoch": 13.0,
-      "learning_rate": 7e-06,
-      "loss": 0.0127,
-      "step": 2600
-    },
-    {
-      "epoch": 13.0,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016596427140000286,
-      "eval_loss": 2.550121784210205,
-      "eval_runtime": 29.7591,
-      "eval_samples_per_second": 26.883,
-      "eval_steps_per_second": 1.68,
-      "eval_total_time_in_seconds": 13.27714171200023,
-      "step": 2600
-    },
-    {
-      "epoch": 13.25,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01661448852124977,
-      "eval_loss": 2.5775039196014404,
-      "eval_runtime": 29.7738,
-      "eval_samples_per_second": 26.869,
-      "eval_steps_per_second": 1.679,
-      "eval_total_time_in_seconds": 13.291590816999815,
-      "step": 2650
-    },
-    {
-      "epoch": 13.5,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01660655404249951,
-      "eval_loss": 2.5819220542907715,
-      "eval_runtime": 29.8343,
-      "eval_samples_per_second": 26.815,
-      "eval_steps_per_second": 1.676,
-      "eval_total_time_in_seconds": 13.285243233999608,
-      "step": 2700
-    },
-    {
-      "epoch": 13.75,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01656317381874942,
-      "eval_loss": 2.562864303588867,
-      "eval_runtime": 29.749,
-      "eval_samples_per_second": 26.892,
-      "eval_steps_per_second": 1.681,
-      "eval_total_time_in_seconds": 13.250539054999535,
-      "step": 2750
-    },
-    {
-      "epoch": 14.0,
-      "learning_rate": 6e-06,
-      "loss": 0.0112,
-      "step": 2800
-    },
-    {
-      "epoch": 14.0,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016711680048749712,
-      "eval_loss": 2.6634762287139893,
-      "eval_runtime": 30.0388,
-      "eval_samples_per_second": 26.632,
-      "eval_steps_per_second": 1.665,
-      "eval_total_time_in_seconds": 13.36934403899977,
-      "step": 2800
-    },
-    {
-      "epoch": 14.25,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01673866046249941,
-      "eval_loss": 2.649559259414673,
-      "eval_runtime": 30.035,
-      "eval_samples_per_second": 26.636,
-      "eval_steps_per_second": 1.665,
-      "eval_total_time_in_seconds": 13.390928369999529,
-      "step": 2850
-    },
-    {
-      "epoch": 14.5,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016693803422499515,
-      "eval_loss": 2.6672680377960205,
-      "eval_runtime": 29.947,
-      "eval_samples_per_second": 26.714,
-      "eval_steps_per_second": 1.67,
-      "eval_total_time_in_seconds": 13.35504273799961,
-      "step": 2900
-    },
-    {
-      "epoch": 14.75,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016712438349999276,
-      "eval_loss": 2.7292675971984863,
-      "eval_runtime": 29.9456,
-      "eval_samples_per_second": 26.715,
-      "eval_steps_per_second": 1.67,
-      "eval_total_time_in_seconds": 13.36995067999942,
-      "step": 2950
-    },
-    {
-      "epoch": 15.0,
-      "learning_rate": 5e-06,
-      "loss": 0.0108,
-      "step": 3000
-    },
-    {
-      "epoch": 15.0,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016635910904999492,
-      "eval_loss": 2.664646625518799,
-      "eval_runtime": 29.8887,
-      "eval_samples_per_second": 26.766,
-      "eval_steps_per_second": 1.673,
-      "eval_total_time_in_seconds": 13.308728723999593,
-      "step": 3000
-    },
-    {
-      "epoch": 15.25,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01662152344999981,
-      "eval_loss": 2.6646552085876465,
-      "eval_runtime": 29.7986,
-      "eval_samples_per_second": 26.847,
-      "eval_steps_per_second": 1.678,
-      "eval_total_time_in_seconds": 13.29721875999985,
-      "step": 3050
-    },
-    {
-      "epoch": 15.5,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01662379797125027,
-      "eval_loss": 2.743170738220215,
-      "eval_runtime": 29.9125,
-      "eval_samples_per_second": 26.745,
-      "eval_steps_per_second": 1.672,
-      "eval_total_time_in_seconds": 13.299038377000215,
-      "step": 3100
-    },
-    {
-      "epoch": 15.75,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01665628889874938,
-      "eval_loss": 2.7203001976013184,
-      "eval_runtime": 29.9599,
-      "eval_samples_per_second": 26.702,
-      "eval_steps_per_second": 1.669,
-      "eval_total_time_in_seconds": 13.325031118999505,
-      "step": 3150
-    },
-    {
-      "epoch": 16.0,
-      "learning_rate": 4.000000000000001e-06,
-      "loss": 0.0063,
-      "step": 3200
-    },
-    {
-      "epoch": 16.0,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016667092492499477,
-      "eval_loss": 2.742436408996582,
-      "eval_runtime": 29.9228,
-      "eval_samples_per_second": 26.735,
-      "eval_steps_per_second": 1.671,
-      "eval_total_time_in_seconds": 13.333673993999582,
-      "step": 3200
-    },
-    {
-      "epoch": 16.25,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01662819170624971,
-      "eval_loss": 2.707371711730957,
-      "eval_runtime": 29.8589,
-      "eval_samples_per_second": 26.793,
-      "eval_steps_per_second": 1.675,
-      "eval_total_time_in_seconds": 13.302553364999767,
-      "step": 3250
-    },
-    {
-      "epoch": 16.5,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01665227038250009,
-      "eval_loss": 2.725658655166626,
-      "eval_runtime": 29.9363,
-      "eval_samples_per_second": 26.723,
-      "eval_steps_per_second": 1.67,
-      "eval_total_time_in_seconds": 13.321816306000073,
-      "step": 3300
-    },
-    {
-      "epoch": 16.75,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016652315160000625,
-      "eval_loss": 2.734884738922119,
-      "eval_runtime": 29.9186,
-      "eval_samples_per_second": 26.739,
-      "eval_steps_per_second": 1.671,
-      "eval_total_time_in_seconds": 13.3218521280005,
-      "step": 3350
-    },
-    {
-      "epoch": 17.0,
-      "learning_rate": 3e-06,
-      "loss": 0.0051,
-      "step": 3400
-    },
-    {
-      "epoch": 17.0,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016673584761250596,
-      "eval_loss": 2.7681331634521484,
-      "eval_runtime": 29.9551,
-      "eval_samples_per_second": 26.707,
-      "eval_steps_per_second": 1.669,
-      "eval_total_time_in_seconds": 13.338867809000476,
-      "step": 3400
-    },
-    {
-      "epoch": 17.25,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016725112717500677,
-      "eval_loss": 2.771609306335449,
-      "eval_runtime": 30.0889,
-      "eval_samples_per_second": 26.588,
-      "eval_steps_per_second": 1.662,
-      "eval_total_time_in_seconds": 13.380090174000543,
-      "step": 3450
-    },
-    {
-      "epoch": 17.5,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016649682186249494,
-      "eval_loss": 2.784963369369507,
-      "eval_runtime": 29.8969,
-      "eval_samples_per_second": 26.759,
-      "eval_steps_per_second": 1.672,
-      "eval_total_time_in_seconds": 13.319745748999594,
-      "step": 3500
     }
   ],
   "max_steps": 4000,
   "num_train_epochs": 20,
-  "total_flos": 7418306617344000.0,
+  "total_flos": 5298790440960000.0,
   "trial_name": null,
   "trial_params": null
 }