Training in progress, step 1400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bbc7079009dcb015a118d176ee96ef3fa9f81f5e32596bd48e471250f7cd019
+oid sha256:51a5c4269980c54f82bc3da566ba2c9f23039e5604c94f38ff35d314135c4a3a
 size 2843370360

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d9a7aedcce194e7334bb3ff1bbd48d5ae2a679ca306c2690cc2f3503f52f78
+oid sha256:f99a4feff5614541872efc0ede3d0a150a715ce72bba1d6deecbce49223acefa
 size 1421660981

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37cb7810664b13600938b962e95e12c94aaeb9d2b88cf011246a5ed3f6f5583d
+oid sha256:b0b77b5900549b5144ba01f867f512f9757676e061b6356487054256b9dbf9a5
 size 14639

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31560d2c60ddf21d021e78a5d14bba7dc363334c5f64fc9eb49d0b82d96fc2a
+oid sha256:b4735c8454ebaaf0f7e5072d8f53d7dcffa20fd292c672caa239ebbcbcd191bb
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.35946421270983664,
-  "best_model_checkpoint": "/home2/s5432073/language-tech-project/results/ltp-roberta-large-defaultltp-roberta-large-default-0/checkpoint-800",
-  "epoch": 4.733727810650888,
-  "global_step": 800,
+  "best_metric": 0.40153906255014676,
+  "best_model_checkpoint": "/home2/s5432073/language-tech-project/results/ltp-roberta-large-defaultltp-roberta-large-default-0/checkpoint-1200",
+  "epoch": 8.284023668639053,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,11 +154,122 @@
       "eval_samples_per_second": 609.632,
       "eval_steps_per_second": 19.292,
       "step": 800
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 4.299065420560748e-06,
+      "loss": 0.2582,
+      "step": 1000
+    },
+    {
+      "epoch": 5.92,
+      "eval_f1": 0.3779236416443889,
+      "eval_f1_all": [
+        0.5119617224880383,
+        0.5549872122762148,
+        0.09523809523809525,
+        0.24793388429752064,
+        0.6457739791073124,
+        0.10112359550561797,
+        0.31351351351351353,
+        0.0,
+        0.7588785046728972,
+        0.6312056737588652,
+        0.44999999999999996,
+        0.5300546448087431,
+        0.0,
+        0.015384615384615385,
+        0.5868995633187772,
+        0.17857142857142858,
+        0.6494401378122309,
+        0.7022222222222223,
+        0.12851405622489961,
+        0.45676998368678634
+      ],
+      "eval_loss": 0.30811235308647156,
+      "eval_runtime": 3.5499,
+      "eval_samples_per_second": 534.102,
+      "eval_steps_per_second": 16.902,
+      "step": 1000
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 3.0529595015576325e-06,
+      "loss": 0.2446,
+      "step": 1200
+    },
+    {
+      "epoch": 7.1,
+      "eval_f1": 0.40153906255014676,
+      "eval_f1_all": [
+        0.5172413793103449,
+        0.5871121718377088,
+        0.12,
+        0.3759398496240602,
+        0.630952380952381,
+        0.17258883248730966,
+        0.3768115942028986,
+        0.0,
+        0.7563683866753755,
+        0.6462513199577613,
+        0.4758064516129032,
+        0.5527369826435248,
+        0.0,
+        0.015037593984962405,
+        0.5758683729433272,
+        0.21203438395415472,
+        0.6746794871794872,
+        0.7136563876651982,
+        0.17777777777777778,
+        0.44991789819376027
+      ],
+      "eval_loss": 0.30632713437080383,
+      "eval_runtime": 3.2144,
+      "eval_samples_per_second": 589.85,
+      "eval_steps_per_second": 18.666,
+      "step": 1200
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 1.8068535825545173e-06,
+      "loss": 0.2344,
+      "step": 1400
+    },
+    {
+      "epoch": 8.28,
+      "eval_f1": 0.39818355623683893,
+      "eval_f1_all": [
+        0.5059665871121718,
+        0.6030267753201397,
+        0.13071895424836602,
+        0.3609022556390977,
+        0.6425073457394711,
+        0.17616580310880828,
+        0.3827751196172249,
+        0.0,
+        0.7609942638623327,
+        0.6363636363636364,
+        0.4672131147540983,
+        0.5517241379310345,
+        0.0,
+        0.015151515151515152,
+        0.5907099035933392,
+        0.14012738853503187,
+        0.7006960556844547,
+        0.7053571428571428,
+        0.1484375,
+        0.4448336252189142
+      ],
+      "eval_loss": 0.30558517575263977,
+      "eval_runtime": 3.0733,
+      "eval_samples_per_second": 616.921,
+      "eval_steps_per_second": 19.523,
+      "step": 1400
     }
   ],
   "max_steps": 1690,
   "num_train_epochs": 10,
-  "total_flos": 4392119246594136.0,
+  "total_flos": 7696217086325736.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d9a7aedcce194e7334bb3ff1bbd48d5ae2a679ca306c2690cc2f3503f52f78
+oid sha256:f99a4feff5614541872efc0ede3d0a150a715ce72bba1d6deecbce49223acefa
 size 1421660981