Training in progress, epoch 2, checkpoint

last-checkpoint/global_step2371/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3e5e7e338e56c0fbb48dba67f5ad0e53df13693caeda65462254f6067e8d9f
+size 28315088

last-checkpoint/global_step2371/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8f7b1661851c1b8fbee6ffeba88cce356bccb656ec91070303ba55c1fc1eb2
+size 28315088

last-checkpoint/global_step2371/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8c03a6449fd7949a535a46dce0b2d86946a69c104e0bbe9fe2ac1a6e1cc5be
+size 2850543502

last-checkpoint/global_step2371/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0963d69e05ca8b0f098eb885f18d94e378a847bcb3061cf12600b23aec9607
+size 2850543310

last-checkpoint/latest

@@ -1 +1 @@
-global_step1581
+global_step2371

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f08f5222c04ba8a25b70996b406c1e95dc834c73f15f3e7248da94c55fa3d6d3
+oid sha256:9ebcc4f849c319e84877c5a5616307940f594a3127631dce316993029034eeb0
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707f46a874ccec694d9a9ebdb8230159a79dc68e5bca12742f90f6e6d892b27e
+oid sha256:05b01af9cac14bdb0b4fce5f6be228a514d12ae472bc890371393ba7752dafc0
 size 14512

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.288722038269043,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-1581",
-  "epoch": 2.0,
+  "best_metric": 2.2401010990142822,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-2371",
+  "epoch": 2.9993674889310564,
   "eval_steps": 500,
-  "global_step": 1581,
+  "global_step": 2371,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,13 +63,38 @@
       "eval_steps_per_second": 0.131,
       "eval_translation_length": 53391,
       "step": 1581
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0001,
+      "loss": 2.4165,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.2401010990142822,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 53401,
+      "eval_runtime": 1342.5303,
+      "eval_samples_per_second": 2.094,
+      "eval_steps_per_second": 0.131,
+      "eval_translation_length": 53401,
+      "step": 2371
     }
   ],
   "logging_steps": 500,
   "max_steps": 23700,
   "num_train_epochs": 30,
   "save_steps": 500,
-  "total_flos": 771945142419456.0,
+  "total_flos": 1158039818207232.0,
   "trial_name": null,
   "trial_params": null
 }