Training in progress, step 1000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64eb00a81e36715c933630bbedd1e6f963107105001649122261384d496e16a
+oid sha256:3ccbcaebfbb76527ceb05727868c381237a1a0817d744ea9290958afffa2eabe
 size 2843370360

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b459f1fb342e2b0b281660cd52bb52d7ef3398b855eb214494208049233b930
+oid sha256:063bd6581e269cf7fc1f68d19960a05c6ea27758161676f7fbc5d4c6a0c03e31
 size 1421660981

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ce148be18af7e294e208c23394ce790567ade1b147c385e87109b039a2f3e4e
-size 14575
+oid sha256:b5f5203f955ff1ed135286a43aa26372be9c45be922fb743af25a7b85b6c2fbe
+size 14639

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8636707e906db799535a0e24d8b11f4682008d2f9dce23ea4add566cf191f0eb
+oid sha256:68a6f395aca12d068a355806ad25a39cc1cf9ac8d7df16949ceeaa9f78f9ba22
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.15828796157072217,
-  "best_model_checkpoint": "/home2/s5432073/language-tech-project/results/ltp-roberta-large-defaultltp-roberta-large-default-9/checkpoint-200",
-  "epoch": 1.183431952662722,
-  "global_step": 200,
+  "best_metric": 0.37526293741944416,
+  "best_model_checkpoint": "/home2/s5432073/language-tech-project/results/ltp-roberta-large-defaultltp-roberta-large-default-9/checkpoint-1000",
+  "epoch": 5.9171597633136095,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43,11 +43,159 @@
       "eval_samples_per_second": 724.543,
       "eval_steps_per_second": 22.929,
       "step": 200
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.037383177570094e-06,
+      "loss": 0.3276,
+      "step": 400
+    },
+    {
+      "epoch": 2.37,
+      "eval_f1": 0.27070745440431776,
+      "eval_f1_all": [
+        0.3987730061349693,
+        0.37480314960629924,
+        0.0,
+        0.0,
+        0.6236125126135217,
+        0.05917159763313609,
+        0.3404255319148936,
+        0.0,
+        0.7367021276595745,
+        0.5967130214917826,
+        0.11518324607329843,
+        0.4112149532710281,
+        0.0,
+        0.0,
+        0.15251798561151078,
+        0.0,
+        0.6607431340872374,
+        0.624390243902439,
+        0.017621145374449337,
+        0.30227743271221535
+      ],
+      "eval_loss": 0.3264588415622711,
+      "eval_runtime": 2.8315,
+      "eval_samples_per_second": 669.617,
+      "eval_steps_per_second": 21.19,
+      "step": 400
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 6.791277258566978e-06,
+      "loss": 0.2941,
+      "step": 600
+    },
+    {
+      "epoch": 3.55,
+      "eval_f1": 0.3284303777422183,
+      "eval_f1_all": [
+        0.5230769230769231,
+        0.5660847880299252,
+        0.014388489208633093,
+        0.09090909090909091,
+        0.6258776328986961,
+        0.0588235294117647,
+        0.2923976608187135,
+        0.0,
+        0.7289595758780648,
+        0.6356589147286822,
+        0.28971962616822433,
+        0.40816326530612246,
+        0.0,
+        0.015625,
+        0.47457627118644063,
+        0.06382978723404255,
+        0.6955153422501967,
+        0.635897435897436,
+        0.09795918367346938,
+        0.3511450381679389
+      ],
+      "eval_loss": 0.31264743208885193,
+      "eval_runtime": 2.8103,
+      "eval_samples_per_second": 674.672,
+      "eval_steps_per_second": 21.35,
+      "step": 600
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 5.545171339563863e-06,
+      "loss": 0.2732,
+      "step": 800
+    },
+    {
+      "epoch": 4.73,
+      "eval_f1": 0.3619965683236828,
+      "eval_f1_all": [
+        0.5528089887640449,
+        0.5821596244131456,
+        0.0945945945945946,
+        0.18965517241379312,
+        0.6472868217054263,
+        0.13829787234042554,
+        0.3692307692307692,
+        0.0,
+        0.7455386649041639,
+        0.638095238095238,
+        0.37606837606837606,
+        0.4579025110782866,
+        0.0,
+        0.015503875968992248,
+        0.5087179487179486,
+        0.07719298245614035,
+        0.6716917922948074,
+        0.6666666666666667,
+        0.08298755186721991,
+        0.425531914893617
+      ],
+      "eval_loss": 0.3080659508705139,
+      "eval_runtime": 2.7772,
+      "eval_samples_per_second": 682.698,
+      "eval_steps_per_second": 21.604,
+      "step": 800
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 4.299065420560748e-06,
+      "loss": 0.2559,
+      "step": 1000
+    },
+    {
+      "epoch": 5.92,
+      "eval_f1": 0.37526293741944416,
+      "eval_f1_all": [
+        0.5243619489559165,
+        0.5671641791044777,
+        0.06896551724137931,
+        0.1724137931034483,
+        0.6521327014218009,
+        0.11363636363636363,
+        0.3711340206185567,
+        0.0,
+        0.7530312699425653,
+        0.6465116279069768,
+        0.42857142857142855,
+        0.5034387895460799,
+        0.0,
+        0.015384615384615385,
+        0.5711743772241993,
+        0.17629179331306988,
+        0.6535162950257289,
+        0.6972477064220184,
+        0.11290322580645162,
+        0.4773790951638066
+      ],
+      "eval_loss": 0.30820420384407043,
+      "eval_runtime": 2.6936,
+      "eval_samples_per_second": 703.901,
+      "eval_steps_per_second": 22.275,
+      "step": 1000
     }
   ],
   "max_steps": 1690,
   "num_train_epochs": 10,
-  "total_flos": 1089865359765408.0,
+  "total_flos": 5502978001057296.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b459f1fb342e2b0b281660cd52bb52d7ef3398b855eb214494208049233b930
+oid sha256:063bd6581e269cf7fc1f68d19960a05c6ea27758161676f7fbc5d4c6a0c03e31
 size 1421660981