Upload 8 files

Finetuned on entities

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f128e341188b9eacd001a6e7fc9031eda23366662ad095781567489c262699
+oid sha256:8a85e06e7c385cca92f4a8f54b47798afabd1695c9355dcce12069def7eec593
 size 4921022932

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db582a24c8f3cb13bacddf4482af3b34d4db048210f388d45381562bb066929
+oid sha256:d8cc71cd9ef90537c1cbf650dbdb17b128ca8378784b87ba9a7ed30067db3471
 size 2460468737

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20721249d9b8d8bc576b72185919e68c93dae68b49c2363c0236e1172512edff
+oid sha256:5370b871c1a234b36198f0c8eae1923196c8067fcf05542ebf23b694806d4378
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd539ae79de480492c3270d14ced42f10b1174f0cad170e082f8fbf6aa55b60c
+oid sha256:a49346f519a1a9f14fcadd47fb8b2a3d1bafcf68ea79e99ae6a44a8272fb4777
 size 627

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.34489724040031433,
   "best_model_checkpoint": "./checkpoint-my/checkpoint-1500",
-  "epoch": 5.127337945170382,
+  "epoch": 7.56789812129618,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -167,13 +167,93 @@
       "eval_samples_per_second": 5.218,
       "eval_steps_per_second": 1.305,
       "step": 5000
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 1.247863247863248e-05,
+      "loss": 0.1189,
+      "step": 5500
+    },
+    {
+      "epoch": 5.64,
+      "eval_bleu": 27.4615,
+      "eval_gen_len": 32.2204,
+      "eval_loss": 0.34533679485321045,
+      "eval_runtime": 186.2569,
+      "eval_samples_per_second": 5.433,
+      "eval_steps_per_second": 1.358,
+      "step": 5500
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.1794871794871796e-05,
+      "loss": 0.1166,
+      "step": 6000
+    },
+    {
+      "epoch": 6.15,
+      "eval_bleu": 27.6321,
+      "eval_gen_len": 32.2816,
+      "eval_loss": 0.34552034735679626,
+      "eval_runtime": 185.1476,
+      "eval_samples_per_second": 5.466,
+      "eval_steps_per_second": 1.366,
+      "step": 6000
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 1.125462495795493e-05,
+      "loss": 0.1171,
+      "step": 6500
+    },
+    {
+      "epoch": 6.56,
+      "eval_bleu": 27.3986,
+      "eval_gen_len": 32.4397,
+      "eval_loss": 0.34709280729293823,
+      "eval_runtime": 204.1804,
+      "eval_samples_per_second": 4.956,
+      "eval_steps_per_second": 1.239,
+      "step": 6500
+    },
+    {
+      "epoch": 7.06,
+      "learning_rate": 1.0581903800874538e-05,
+      "loss": 0.1157,
+      "step": 7000
+    },
+    {
+      "epoch": 7.06,
+      "eval_bleu": 27.5083,
+      "eval_gen_len": 32.2816,
+      "eval_loss": 0.34769660234451294,
+      "eval_runtime": 209.4596,
+      "eval_samples_per_second": 4.831,
+      "eval_steps_per_second": 1.208,
+      "step": 7000
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 9.909182643794148e-06,
+      "loss": 0.1121,
+      "step": 7500
+    },
+    {
+      "epoch": 7.57,
+      "eval_bleu": 27.4437,
+      "eval_gen_len": 32.2194,
+      "eval_loss": 0.34789395332336426,
+      "eval_runtime": 209.9641,
+      "eval_samples_per_second": 4.82,
+      "eval_steps_per_second": 1.205,
+      "step": 7500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 14625,
+  "max_steps": 14865,
   "num_train_epochs": 15,
   "save_steps": 500,
-  "total_flos": 3.467034171046625e+17,
+  "total_flos": 5.2005742820563354e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa984e3cea098421ca0a4e48e9cd6b184a4ab34fc980cad163565e996bb9d67a
+oid sha256:644b2690039d83439e28a3112267a0e4adac0af05d4ef5abe06d9d8bbb23d339
 size 4155