Training in progress, epoch 2, checkpoint

last-checkpoint/global_step1581/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc367dbb9740751e85fd2958b4867e548bfad92bc52db0c411c1d02943344cf
-size 56626640
+oid sha256:91eacaa84680aa82b20a3df8182dc93d0ce047ed089f25b4731f846316837cb6
+size 28315088

last-checkpoint/global_step1581/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f583059aebf5c348baa213b71780e3beb0ed5bea73b3eaaae551a3ee1fa3b6
-size 56626640
+oid sha256:c297b2e76489c10915e73396d64e91d8ba6c2dd74c95b2df3b59bea16e5b8948
+size 28315088

last-checkpoint/global_step1581/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5d9a7306e11004f5b07be5adcf241a253323781fe1b13c03e09f6e9c51b1a4f
-size 11136132566
+oid sha256:a0cfb139e4c8441e6ab6518b594be2262638a6362ae882d8fa66311577c967c5
+size 2850543502

last-checkpoint/global_step1581/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71dd45f808f455f2743152cc5c2c5389f3f01dc02239d02a8986dbc29229ccf
-size 11136132374
+oid sha256:a28252787a7c5302116de0d3ed69eaebf466c0d5f045b2ab3ef114b4d7e96000
+size 2850543310

last-checkpoint/latest

@@ -1 +1 @@
-global_step790
+global_step1581

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a7aa1548464e6c880ebd42aba4c07ee57fb38feb25979f4c82c0f0bec9f0e6
+oid sha256:f08f5222c04ba8a25b70996b406c1e95dc834c73f15f3e7248da94c55fa3d6d3
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d40d71f540bdd7fdb4af7e756f13010eb6a96ab531b88e35903b066788ad63
+oid sha256:707f46a874ccec694d9a9ebdb8230159a79dc68e5bca12742f90f6e6d892b27e
 size 14512

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.392251491546631,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-790",
-  "epoch": 0.9993674889310563,
+  "best_metric": 2.288722038269043,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-1581",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 790,
+  "global_step": 1581,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -32,13 +32,44 @@
       "eval_steps_per_second": 0.126,
       "eval_translation_length": 53098,
       "step": 790
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 9.445572420019074e-05,
+      "loss": 2.5652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 9.999999999999999e-05,
+      "loss": 2.468,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.288722038269043,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 53391,
+      "eval_runtime": 1340.9293,
+      "eval_samples_per_second": 2.096,
+      "eval_steps_per_second": 0.131,
+      "eval_translation_length": 53391,
+      "step": 1581
     }
   ],
   "logging_steps": 500,
   "max_steps": 23700,
   "num_train_epochs": 30,
   "save_steps": 500,
-  "total_flos": 385850466631680.0,
+  "total_flos": 771945142419456.0,
   "trial_name": null,
   "trial_params": null
 }