Upload with huggingface_hub

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f15460627a73f5a7810580fc1400107c8567b84291d910de6c908e2d0c3061
+oid sha256:662103ebc4d59eac4149a3a57c8d37aeb12848773184e387b33fd963e993f876
 size 535706209

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c9f4f6379f05b6336b225c87d388cd0859702bb1578ef217f5cbe5a701836b
+oid sha256:8920085e7fda657cc8fb7247be4b9e23e2acc75760e51050e178cdc1d5973bd0
 size 267857393

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6434b53c20a9a79004b47b094f4bce06e5cef0e480bad66f94ed659d4db0636
+oid sha256:ebc4b64a931ca6f38f6d683f5b3a967bb59072455b66cd85eeb8c432cdef6f43
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77a8263d2c9ab2d2fd99749ca0bd684b2d23ea39ae6b5deffc35ec07d427d80
+oid sha256:06f7f9516085d32bba7de1113c329a9952874023962aa001b1e05c81482101c2
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.5875,
   "best_model_checkpoint": "./results/checkpoint-500",
-  "epoch": 20.0,
-  "global_step": 4000,
+  "epoch": 17.5,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -878,139 +878,11 @@
       "eval_steps_per_second": 1.672,
       "eval_total_time_in_seconds": 13.319745748999594,
       "step": 3500
-    },
-    {
-      "epoch": 17.75,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016661749145000612,
-      "eval_loss": 2.8149163722991943,
-      "eval_runtime": 29.9288,
-      "eval_samples_per_second": 26.73,
-      "eval_steps_per_second": 1.671,
-      "eval_total_time_in_seconds": 13.32939931600049,
-      "step": 3550
-    },
-    {
-      "epoch": 18.0,
-      "learning_rate": 2.0000000000000003e-06,
-      "loss": 0.009,
-      "step": 3600
-    },
-    {
-      "epoch": 18.0,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01670996660875062,
-      "eval_loss": 2.823868989944458,
-      "eval_runtime": 30.0163,
-      "eval_samples_per_second": 26.652,
-      "eval_steps_per_second": 1.666,
-      "eval_total_time_in_seconds": 13.367973287000495,
-      "step": 3600
-    },
-    {
-      "epoch": 18.25,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01669507317250009,
-      "eval_loss": 2.8000104427337646,
-      "eval_runtime": 29.9679,
-      "eval_samples_per_second": 26.695,
-      "eval_steps_per_second": 1.668,
-      "eval_total_time_in_seconds": 13.35605853800007,
-      "step": 3650
-    },
-    {
-      "epoch": 18.5,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.01666891421250057,
-      "eval_loss": 2.8489391803741455,
-      "eval_runtime": 30.0714,
-      "eval_samples_per_second": 26.603,
-      "eval_steps_per_second": 1.663,
-      "eval_total_time_in_seconds": 13.335131370000454,
-      "step": 3700
-    },
-    {
-      "epoch": 18.75,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016747756885000624,
-      "eval_loss": 2.8278234004974365,
-      "eval_runtime": 30.1511,
-      "eval_samples_per_second": 26.533,
-      "eval_steps_per_second": 1.658,
-      "eval_total_time_in_seconds": 13.398205508000501,
-      "step": 3750
-    },
-    {
-      "epoch": 19.0,
-      "learning_rate": 1.0000000000000002e-06,
-      "loss": 0.0058,
-      "step": 3800
-    },
-    {
-      "epoch": 19.0,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016664527845000523,
-      "eval_loss": 2.8291778564453125,
-      "eval_runtime": 29.9616,
-      "eval_samples_per_second": 26.701,
-      "eval_steps_per_second": 1.669,
-      "eval_total_time_in_seconds": 13.331622276000417,
-      "step": 3800
-    },
-    {
-      "epoch": 19.25,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.0166671570925007,
-      "eval_loss": 2.848686456680298,
-      "eval_runtime": 29.9999,
-      "eval_samples_per_second": 26.667,
-      "eval_steps_per_second": 1.667,
-      "eval_total_time_in_seconds": 13.333725674000561,
-      "step": 3850
-    },
-    {
-      "epoch": 19.5,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016675078326250058,
-      "eval_loss": 2.8558411598205566,
-      "eval_runtime": 30.0771,
-      "eval_samples_per_second": 26.598,
-      "eval_steps_per_second": 1.662,
-      "eval_total_time_in_seconds": 13.340062661000047,
-      "step": 3900
-    },
-    {
-      "epoch": 19.75,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.016670747563749727,
-      "eval_loss": 2.8526947498321533,
-      "eval_runtime": 30.0232,
-      "eval_samples_per_second": 26.646,
-      "eval_steps_per_second": 1.665,
-      "eval_total_time_in_seconds": 13.336598050999783,
-      "step": 3950
-    },
-    {
-      "epoch": 20.0,
-      "learning_rate": 0.0,
-      "loss": 0.0043,
-      "step": 4000
-    },
-    {
-      "epoch": 20.0,
-      "eval_accuracy": 0.5875,
-      "eval_latency_in_seconds": 0.0166365546787506,
-      "eval_loss": 2.8533031940460205,
-      "eval_runtime": 29.9376,
-      "eval_samples_per_second": 26.722,
-      "eval_steps_per_second": 1.67,
-      "eval_total_time_in_seconds": 13.30924374300048,
-      "step": 4000
     }
   ],
   "max_steps": 4000,
   "num_train_epochs": 20,
-  "total_flos": 8478064705536000.0,
+  "total_flos": 7418306617344000.0,
   "trial_name": null,
   "trial_params": null
 }