Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4597b43566bbab6691b66e0147b6adf20d66742313ece94d53f28a67f9a34c2f
+oid sha256:1d3e004f33bcb4b20f6924424a7bd4b3c2232c2cf102f316a310917c59bf41f6
 size 647614116

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df012ab88d466c974857dcadf0160d90947b23aea6ee5b630e57486acbc4f3dd
+oid sha256:5560059478b267921d76a899f71a125eb1e4ec8b685bcb1a7d4a096e4cd0fd65
 size 1295003019

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:224ab8bac8385ad5cd65120aaad5f1944b24829738d5225dfdebdff6202eafbb
+oid sha256:e4ab93550d3f9dfc6f76f03e70886ac01b80969be8e3a31c462f631cd3ea276c
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749ce24f99c226ec84ff663347d221965c45f5b51c1c10bc2024b50639eeac34
+oid sha256:cf451ff600a5ce12ef50b2a8254f31f0e920eae89a966335b89742fc3f30ada9
 size 1465

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.012656629346953,
-  "best_model_checkpoint": "./led_doc_nmt/checkpoint-197",
-  "epoch": 1.0,
+  "best_metric": 15.451761251904164,
+  "best_model_checkpoint": "./led_doc_nmt/checkpoint-394",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 197,
+  "global_step": 394,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25,6 +25,31 @@
       "eval_samples_per_second": 3.543,
       "eval_steps_per_second": 0.112,
       "step": 197
+    },
+    {
+      "epoch": 1.015228426395939,
+      "grad_norm": 1.129528522491455,
+      "learning_rate": 1.9949238578680203e-05,
+      "loss": 2.3201,
+      "step": 200
+    },
+    {
+      "epoch": 1.5228426395939088,
+      "grad_norm": 1.330965518951416,
+      "learning_rate": 1.4873096446700508e-05,
+      "loss": 2.0319,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 15.451761251904164,
+      "eval_comet": 0.3909361151943732,
+      "eval_loss": 1.7004817724227905,
+      "eval_meteor": 0.33229419612988736,
+      "eval_runtime": 389.476,
+      "eval_samples_per_second": 3.589,
+      "eval_steps_per_second": 0.113,
+      "step": 394
     }
   ],
   "logging_steps": 100,
@@ -53,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8493494307913728.0,
+  "total_flos": 1.6986988615827456e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null