Training in progress, epoch 4, checkpoint

last-checkpoint/README.md

@@ -563,6 +563,10 @@ You can finetune this model on your own dataset.
 | 3.4871 | 1624 | 1.9654        | 0.2392                | 1.5037         |
 | 3.7371 | 1740 | 2.1107        | 0.2234                | 1.4557         |
 | 3.9871 | 1856 | 2.0709        | 0.2094                | 1.4287         |
+| 4.2328 | 1972 | 1.9489        | 0.2072                | 1.4167         |
+| 4.4828 | 2088 | 1.8238        | 0.2019                | 1.4155         |
+| 4.7328 | 2204 | 2.1587        | 0.2005                | 1.4136         |
+| 4.9828 | 2320 | 1.929         | 0.2005                | 1.4132         |
 
 
 ### Framework Versions

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45eeac36057b0a84a3d410d1974ea4ef60e1f6732308a7c19c7fd4aa6ff3adf0
+oid sha256:2415efd86ddb31b8ccd116ba8fb00cf3a2bb32e6d5d2ef1d307b59571c494cb5
 size 1130520122

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df76c36ed895286d93c7e35de2022f1a4142ca300d68137813a64ef7c2467b2
+oid sha256:aa6de6db3864cbe5490abac662a29ae3c7a4c0dce0a1063f4172a3ba474b3b0e
 size 565251810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ac986d8316aed04b3cf90a12a44166385897956e05972f0500d5a12c28b4e2
+oid sha256:ee7def8d6e19abe0010fc23ee8ceef6f2e3224be5f40cd1c4f4ae996d6eab300
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4113c75337369f487518d15e4b953b9a64a66968b355fbea0722908652f445
+oid sha256:0d07db50179fc1817acd2aeda9c1e69355a330f49f4a4908ab69b93d19e89e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.004310344827586,
+  "epoch": 4.982758620689655,
   "eval_steps": 116,
-  "global_step": 1864,
+  "global_step": 2320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -375,6 +375,98 @@
       "eval_qnli-contrastive_samples_per_second": 1383.695,
       "eval_qnli-contrastive_steps_per_second": 86.481,
       "step": 1856
+    },
+    {
+      "epoch": 4.232758620689655,
+      "grad_norm": 4.497424602508545,
+      "learning_rate": 3.680019472369961e-07,
+      "loss": 1.9489,
+      "step": 1972
+    },
+    {
+      "epoch": 4.232758620689655,
+      "eval_nli-pairs_loss": 1.4166995286941528,
+      "eval_nli-pairs_runtime": 1.3578,
+      "eval_nli-pairs_samples_per_second": 1472.956,
+      "eval_nli-pairs_steps_per_second": 92.06,
+      "step": 1972
+    },
+    {
+      "epoch": 4.232758620689655,
+      "eval_qnli-contrastive_loss": 0.2071654498577118,
+      "eval_qnli-contrastive_runtime": 1.489,
+      "eval_qnli-contrastive_samples_per_second": 1343.182,
+      "eval_qnli-contrastive_steps_per_second": 83.949,
+      "step": 1972
+    },
+    {
+      "epoch": 4.482758620689655,
+      "grad_norm": 8.940858840942383,
+      "learning_rate": 1.7030146916085187e-07,
+      "loss": 1.8238,
+      "step": 2088
+    },
+    {
+      "epoch": 4.482758620689655,
+      "eval_nli-pairs_loss": 1.4154555797576904,
+      "eval_nli-pairs_runtime": 1.4109,
+      "eval_nli-pairs_samples_per_second": 1417.564,
+      "eval_nli-pairs_steps_per_second": 88.598,
+      "step": 2088
+    },
+    {
+      "epoch": 4.482758620689655,
+      "eval_qnli-contrastive_loss": 0.20185217261314392,
+      "eval_qnli-contrastive_runtime": 1.4817,
+      "eval_qnli-contrastive_samples_per_second": 1349.799,
+      "eval_qnli-contrastive_steps_per_second": 84.362,
+      "step": 2088
+    },
+    {
+      "epoch": 4.732758620689655,
+      "grad_norm": 4.952300548553467,
+      "learning_rate": 4.5391654754460885e-08,
+      "loss": 2.1587,
+      "step": 2204
+    },
+    {
+      "epoch": 4.732758620689655,
+      "eval_nli-pairs_loss": 1.4136021137237549,
+      "eval_nli-pairs_runtime": 1.3576,
+      "eval_nli-pairs_samples_per_second": 1473.214,
+      "eval_nli-pairs_steps_per_second": 92.076,
+      "step": 2204
+    },
+    {
+      "epoch": 4.732758620689655,
+      "eval_qnli-contrastive_loss": 0.20051518082618713,
+      "eval_qnli-contrastive_runtime": 1.585,
+      "eval_qnli-contrastive_samples_per_second": 1261.81,
+      "eval_qnli-contrastive_steps_per_second": 78.863,
+      "step": 2204
+    },
+    {
+      "epoch": 4.982758620689655,
+      "grad_norm": 10.16062068939209,
+      "learning_rate": 1.1034588846758897e-10,
+      "loss": 1.929,
+      "step": 2320
+    },
+    {
+      "epoch": 4.982758620689655,
+      "eval_nli-pairs_loss": 1.4131741523742676,
+      "eval_nli-pairs_runtime": 1.2998,
+      "eval_nli-pairs_samples_per_second": 1538.653,
+      "eval_nli-pairs_steps_per_second": 96.166,
+      "step": 2320
+    },
+    {
+      "epoch": 4.982758620689655,
+      "eval_qnli-contrastive_loss": 0.2004699856042862,
+      "eval_qnli-contrastive_runtime": 1.449,
+      "eval_qnli-contrastive_samples_per_second": 1380.303,
+      "eval_qnli-contrastive_steps_per_second": 86.269,
+      "step": 2320
     }
   ],
   "logging_steps": 116,
@@ -389,7 +481,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }