Training in progress, epoch 2, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3201ed294d0d4cb0620b86d3e3c64940685d6fa936768a015324e31e3dbf8e69
+oid sha256:2c4363d06929aee26c9e927701774792fb7453e840d38a5ad5a3f1d36b1be96b
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589c0721a9a73ac1d51de75d5857ffb3ba271b84ee793c8ae2c32776e7fcde71
+oid sha256:96e4c9ef9cd2909c6491e22429888102a5089a17edf046aff201c9c1677a0ddc
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae00bd8b8e83d970fa0946a2f0647cb96a40344898cf84cce24800471e2a072a
+oid sha256:240c04ca9a3cb29b976a770fef919a933d604a3470e1df27947f582528033848
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0cf8c394b20eb3c60c2fd4e5a5c8545b8684708631b650e021db195d048838
+oid sha256:d9ba60403de9780e4b1c2244a6784efea5c6643ffcd4f768f2fe7e0521babfed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3418445587158203,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-3163",
-  "epoch": 1.0,
+  "best_metric": 2.3292136192321777,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-6326",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 3163,
+  "global_step": 6326,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -62,13 +62,68 @@
       "eval_steps_per_second": 0.623,
       "eval_translation_length": 53280,
       "step": 3163
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 6.960608899658203e-06,
+      "loss": 2.4199,
+      "step": 3500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.946420724891154e-06,
+      "loss": 2.3982,
+      "step": 4000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 6.930073714847756e-06,
+      "loss": 2.4308,
+      "step": 4500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 6.911578109282458e-06,
+      "loss": 2.4074,
+      "step": 5000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 6.890945493828278e-06,
+      "loss": 2.3945,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.868188792739579e-06,
+      "loss": 2.4344,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.3292136192321777,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 53147,
+      "eval_runtime": 562.613,
+      "eval_samples_per_second": 4.998,
+      "eval_steps_per_second": 0.626,
+      "eval_translation_length": 53147,
+      "step": 6326
     }
   ],
   "logging_steps": 500,
   "max_steps": 63260,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.7326415288991744e+16,
+  "total_flos": 3.465283057798349e+16,
   "trial_name": null,
   "trial_params": null
 }