Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb71748e42b13c2837465f68234941eb659aec9bba0474e8f36b5a6aee45509
+oid sha256:b5f1b072d203d5b76fe9560659963ef8f781250b4a92e1868c89f6c51fb112d6
 size 9450448

last-checkpoint/global_step70/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:a47f396fa71f1e96c9af42df609aca51b09333fd6dd0ca0ecb2d8f49a5f9b96d
+size 28320208

last-checkpoint/global_step70/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a33126a85874efb86475c39fa113d95974048c506496f03fa3c779530e2636
+size 28320208

last-checkpoint/global_step70/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af21c45ef7e37b5a61efd780540df6f6f32b3c48a8b0ecb3da9df86e8899eca
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step60
+global_step70

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff35af8b3912808d2b43107e888e92f4ea83535d354c13686a169c447ff88699
+oid sha256:041c1299befadbb78df28d6c51995637fdc42b23b8c9a0ddd6d7b9d2b7b43095
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa0847b6542d841a024e7000b745c034da050389afd214a7611da78af90f506
+oid sha256:d39b95751aa22f7c631b63c6ae50b62913410b70130404c3fc20f638c1f28ddb
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bde2757391e94ff5103cea79868bee6f1ccc90f20c64e82cf9933fa7b5accd0c
+oid sha256:4f98a8feef34550913a6c17e6d111551876ee5198dbf8b76141d29b9c822b726
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10260795211628901,
+  "epoch": 0.11970927746900385,
   "eval_steps": 10,
-  "global_step": 60,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,28 @@
       "eval_samples_per_second": 109.58,
       "eval_steps_per_second": 27.562,
       "step": 60
+    },
+    {
+      "epoch": 0.11115861479264642,
+      "grad_norm": 37.74872970581055,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 3.1812,
+      "step": 65
+    },
+    {
+      "epoch": 0.11970927746900385,
+      "grad_norm": 22.35642433166504,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.1637,
+      "step": 70
+    },
+    {
+      "epoch": 0.11970927746900385,
+      "eval_loss": 3.1739985942840576,
+      "eval_runtime": 4.7892,
+      "eval_samples_per_second": 102.941,
+      "eval_steps_per_second": 25.892,
+      "step": 70
     }
   ],
   "logging_steps": 5,
@@ -166,7 +188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1533697698299904.0,
+  "total_flos": 1786158224769024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null