1122

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "/home/ubuntu/Pythonprojects/kcbert2/models/t5/t5-legacy/",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7250ce1ab70dc1a9fd526bb4d5d8eb5222e08cdf5b654e319428c72c219d89
+oid sha256:dda6fb47598a3c4d7e0183f11bcc07d7b518fcb40f9facd62984206e748d3a01
 size 1783379133

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e23f9bb16399dbb6299333937b7d2eeb28058c49c33ee3ff3a2e4f28f9930cb
+oid sha256:427d75649726c7fc41848295a130297c7ec168feb884b0560d83dfdda7cfb76a
 size 891730879

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d5b1bae4964fb2f4d01538a124e8fa3d09ef60275a74b9b04e9572c2256028
+oid sha256:b95803f7c7708b5b515d43cad3bc8ce32a703e43dd162abb60ddc0b762fca184
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06cbc2ad564cf4cd4ae1683a2a75297d61e4bb88322c20b1f9c2c3540e65749c
+oid sha256:ccc836a9c4b5ccd266a159052e75698e88fc2f725341bb9a62ac20a2edf57466
 size 623

trainer_state.json

@@ -1,146 +1,116 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.838626976214215,
-  "global_step": 6500,
+  "epoch": 11.965708791795748,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.9184420704841614,
-      "eval_runtime": 226.0895,
-      "eval_samples_per_second": 110.098,
-      "eval_steps_per_second": 27.524,
-      "step": 438
+      "eval_loss": 0.5735206007957458,
+      "eval_runtime": 226.9724,
+      "eval_samples_per_second": 109.67,
+      "eval_steps_per_second": 27.417,
+      "step": 1755
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.8269533514976501,
-      "eval_runtime": 222.6047,
-      "eval_samples_per_second": 111.822,
-      "eval_steps_per_second": 27.955,
-      "step": 876
+      "eval_loss": 0.5326883792877197,
+      "eval_runtime": 225.773,
+      "eval_samples_per_second": 110.252,
+      "eval_steps_per_second": 27.563,
+      "step": 3510
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.7799285054206848,
-      "eval_runtime": 267.0428,
-      "eval_samples_per_second": 93.214,
-      "eval_steps_per_second": 23.303,
-      "step": 1314
+      "eval_loss": 0.5004657506942749,
+      "eval_runtime": 223.9431,
+      "eval_samples_per_second": 111.153,
+      "eval_steps_per_second": 27.788,
+      "step": 5265
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.7528017163276672,
-      "eval_runtime": 225.2214,
-      "eval_samples_per_second": 110.522,
-      "eval_steps_per_second": 27.631,
-      "step": 1752
+      "eval_loss": 0.48436784744262695,
+      "eval_runtime": 223.6051,
+      "eval_samples_per_second": 111.321,
+      "eval_steps_per_second": 27.83,
+      "step": 7020
     },
     {
-      "epoch": 4.57,
-      "learning_rate": 6.9558599695586e-05,
-      "loss": 0.9432,
-      "step": 2000
+      "epoch": 5.0,
+      "eval_loss": 0.4659739136695862,
+      "eval_runtime": 221.9535,
+      "eval_samples_per_second": 112.15,
+      "eval_steps_per_second": 28.037,
+      "step": 8775
     },
     {
-      "epoch": 5.0,
-      "eval_loss": 0.7184237241744995,
-      "eval_runtime": 225.9905,
-      "eval_samples_per_second": 110.146,
-      "eval_steps_per_second": 27.537,
-      "step": 2190
+      "epoch": 5.7,
+      "learning_rate": 5.251661918328585e-05,
+      "loss": 0.4274,
+      "step": 10000
     },
     {
       "epoch": 6.0,
-      "eval_loss": 0.6917603611946106,
-      "eval_runtime": 229.2094,
-      "eval_samples_per_second": 108.599,
-      "eval_steps_per_second": 27.15,
-      "step": 2628
+      "eval_loss": 0.4595305621623993,
+      "eval_runtime": 232.1017,
+      "eval_samples_per_second": 107.246,
+      "eval_steps_per_second": 26.812,
+      "step": 10530
     },
     {
       "epoch": 7.0,
-      "eval_loss": 0.6674416065216064,
-      "eval_runtime": 228.8661,
-      "eval_samples_per_second": 108.762,
-      "eval_steps_per_second": 27.191,
-      "step": 3066
+      "eval_loss": 0.44809117913246155,
+      "eval_runtime": 230.3824,
+      "eval_samples_per_second": 108.046,
+      "eval_steps_per_second": 27.012,
+      "step": 12285
     },
     {
       "epoch": 8.0,
-      "eval_loss": 0.6534304022789001,
-      "eval_runtime": 238.4381,
-      "eval_samples_per_second": 104.396,
-      "eval_steps_per_second": 26.099,
-      "step": 3504
+      "eval_loss": 0.44372686743736267,
+      "eval_runtime": 220.8242,
+      "eval_samples_per_second": 112.723,
+      "eval_steps_per_second": 28.181,
+      "step": 14040
     },
     {
       "epoch": 9.0,
-      "eval_loss": 0.6406867504119873,
-      "eval_runtime": 235.4552,
-      "eval_samples_per_second": 105.719,
-      "eval_steps_per_second": 26.43,
-      "step": 3942
-    },
-    {
-      "epoch": 9.13,
-      "learning_rate": 3.9117199391171995e-05,
-      "loss": 0.6607,
-      "step": 4000
+      "eval_loss": 0.4426543712615967,
+      "eval_runtime": 226.8705,
+      "eval_samples_per_second": 109.719,
+      "eval_steps_per_second": 27.43,
+      "step": 15795
     },
     {
       "epoch": 10.0,
-      "eval_loss": 0.6275271773338318,
-      "eval_runtime": 231.6414,
-      "eval_samples_per_second": 107.459,
-      "eval_steps_per_second": 26.865,
-      "step": 4380
+      "eval_loss": 0.4342004656791687,
+      "eval_runtime": 221.9982,
+      "eval_samples_per_second": 112.127,
+      "eval_steps_per_second": 28.032,
+      "step": 17550
     },
     {
       "epoch": 11.0,
-      "eval_loss": 0.6164868474006653,
-      "eval_runtime": 229.8159,
-      "eval_samples_per_second": 108.313,
-      "eval_steps_per_second": 27.078,
-      "step": 4818
-    },
-    {
-      "epoch": 12.0,
-      "eval_loss": 0.610621452331543,
-      "eval_runtime": 234.5136,
-      "eval_samples_per_second": 106.143,
-      "eval_steps_per_second": 26.536,
-      "step": 5256
-    },
-    {
-      "epoch": 13.0,
-      "eval_loss": 0.6076993942260742,
-      "eval_runtime": 221.8665,
-      "eval_samples_per_second": 112.194,
-      "eval_steps_per_second": 28.048,
-      "step": 5694
-    },
-    {
-      "epoch": 13.7,
-      "learning_rate": 8.675799086757991e-06,
-      "loss": 0.5624,
-      "step": 6000
+      "eval_loss": 0.43299490213394165,
+      "eval_runtime": 221.9453,
+      "eval_samples_per_second": 112.154,
+      "eval_steps_per_second": 28.038,
+      "step": 19305
     },
     {
-      "epoch": 14.0,
-      "eval_loss": 0.6030386686325073,
-      "eval_runtime": 225.3038,
-      "eval_samples_per_second": 110.482,
-      "eval_steps_per_second": 27.62,
-      "step": 6132
+      "epoch": 11.4,
+      "learning_rate": 5.0332383665717e-06,
+      "loss": 0.2777,
+      "step": 20000
     }
   ],
-  "max_steps": 6570,
-  "num_train_epochs": 15,
-  "total_flos": 5.075204254610227e+17,
+  "max_steps": 21060,
+  "num_train_epochs": 12,
+  "total_flos": 4.092582190428979e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92440562452781ca3f73efd16bc795762158e4972a2597602a92148285739f94
+oid sha256:5570b0e849e910b9f449b5cd2078e8f63540a7824db3dbf9415c2f63993b48b3
 size 2991