Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78521ff6580ab7f50d3d41cfaa1fb28327ef67ef6135d172c511a6b3dc8094db
+oid sha256:4fb71748e42b13c2837465f68234941eb659aec9bba0474e8f36b5a6aee45509
 size 9450448

last-checkpoint/global_step60/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:fe436c7df9ccc6cf85593e62ebe2006f105251148a28d0519c5d7d1bcef4b65e
+size 28320208

last-checkpoint/global_step60/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:f25645073d1c44b876e3657b0df53cc848d05b9b8ddcb28c1eba321bb0a50059
+size 28320208

last-checkpoint/global_step60/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3174085a6dac16f3a33fea2851984ab26d9e9f0802d2c53525dd61b4917c062
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step50
+global_step60

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9962eb2386abb32ea16553388778695df372d215555516b65f9e5cfb2163b43a
+oid sha256:ff35af8b3912808d2b43107e888e92f4ea83535d354c13686a169c447ff88699
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e4f6b76020267287942c7931972209c4e9acdb3b3d493565a07f8e0047865f
+oid sha256:faa0847b6542d841a024e7000b745c034da050389afd214a7611da78af90f506
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
+oid sha256:bde2757391e94ff5103cea79868bee6f1ccc90f20c64e82cf9933fa7b5accd0c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08550662676357418,
+  "epoch": 0.10260795211628901,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,28 @@
       "eval_samples_per_second": 104.927,
       "eval_steps_per_second": 26.391,
       "step": 50
+    },
+    {
+      "epoch": 0.0940572894399316,
+      "grad_norm": 24.017574310302734,
+      "learning_rate": 0.0001,
+      "loss": 3.0906,
+      "step": 55
+    },
+    {
+      "epoch": 0.10260795211628901,
+      "grad_norm": 72.96064758300781,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 3.1746,
+      "step": 60
+    },
+    {
+      "epoch": 0.10260795211628901,
+      "eval_loss": 3.197736978530884,
+      "eval_runtime": 4.499,
+      "eval_samples_per_second": 109.58,
+      "eval_steps_per_second": 27.562,
+      "step": 60
     }
   ],
   "logging_steps": 5,
@@ -144,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1274925658669056.0,
+  "total_flos": 1533697698299904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null