Training in progress, step 2000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ad9ec05bbeaeea6847c8e5f34048897f15864d2e6417f92fe0384bcbe38a37
+oid sha256:ac9be1851d65c933b7df18eb2598af95761916b0452ddb06e81bc6019ee4aaa3
 size 484015877

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1dc530845fe5a0bb9f5e1d6d74bc0636c41628b3927424ca3ceb56e67cc3ed6
+oid sha256:8a2e10ed5cdaff6f3b984879342cc4b4ed1ec68389e993b3b2415fd84410e5bd
 size 242014297

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdeb9ad2ec0b208042e20d040a22710fabc05e2dd9799b2ad24d60acdb7ae1f4
+oid sha256:1515038a3750a082fe43582d81ae01e0e929d02a90dbd2b2a2db82ae50b60938
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4afba0142ee523929b01f1d1ea569b3d2c52550df725ed2ab1f846d29ecaac4
+oid sha256:30c5bbe7039a98199ba21ef040f9c1afa7247704578d4073dec2220319914364
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed8c3a989c90e8906959eca2e634a75ff7806fbfde38d988307faba643b8a69f
+oid sha256:f380f7c1d04e6f53aaea8030db0857aeddd02fa8a9eb1ce68514bd4a8b17ea4c
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.5385440798738839,
-  "best_model_checkpoint": "results/checkpoint-1500",
-  "epoch": 0.3,
-  "global_step": 1500,
+  "best_metric": 0.5495869647995661,
+  "best_model_checkpoint": "results/checkpoint-2000",
+  "epoch": 0.4,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,11 +66,31 @@
       "eval_samples_per_second": 36.226,
       "eval_steps_per_second": 1.811,
       "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.126315789473685e-05,
+      "loss": 0.7745,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4,
+      "eval_bleu": 0.11999069408174769,
+      "eval_exact_match": 0.152,
+      "eval_loss": 0.8501775860786438,
+      "eval_rouge1": 0.5495869647995661,
+      "eval_rouge2": 0.37385624817390106,
+      "eval_rougeL": 0.5307934771920211,
+      "eval_rougeLsum": 0.5391651788581161,
+      "eval_runtime": 56.8684,
+      "eval_samples_per_second": 35.169,
+      "eval_steps_per_second": 1.758,
+      "step": 2000
     }
   ],
   "max_steps": 15000,
   "num_train_epochs": 3,
-  "total_flos": 3850447817932800.0,
+  "total_flos": 5140995336437760.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1dc530845fe5a0bb9f5e1d6d74bc0636c41628b3927424ca3ceb56e67cc3ed6
+oid sha256:8a2e10ed5cdaff6f3b984879342cc4b4ed1ec68389e993b3b2415fd84410e5bd
 size 242014297