Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:527df886969d0bc6973c8ca3c0b7e8d37d45f46595b54dcbf89b090f1dcea9d5
+oid sha256:78521ff6580ab7f50d3d41cfaa1fb28327ef67ef6135d172c511a6b3dc8094db
 size 9450448

last-checkpoint/global_step50/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849ae19261375dc15692d5dd1733f294cf906c7e50218e08b5c5bb9fa738519b
+size 28320208

last-checkpoint/global_step50/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:fe4b2d5cb95392b37a7ac5cb05ac85ad7077cfe0544aedb19cb56b879d2abcbf
+size 28320208

last-checkpoint/global_step50/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06211632295f5c74d55439b907e6a2cf0256330c6d58b06a5357aa32a037d8fc
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step40
+global_step50

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:687fd9224933a6639ad3e05d2b410304bda60de2ad16992bfc7ac503cfa587ef
+oid sha256:9962eb2386abb32ea16553388778695df372d215555516b65f9e5cfb2163b43a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154ed241fc000fbeb31a51d958cde287780c9ee809f5bcc1db2f2fd0ecc77ac4
+oid sha256:92e4f6b76020267287942c7931972209c4e9acdb3b3d493565a07f8e0047865f
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288483c81220cbf22f51f35045c4ef691c80220055a03dc4880f485f05c71ede
+oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06840530141085935,
+  "epoch": 0.08550662676357418,
   "eval_steps": 10,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 112.657,
       "eval_steps_per_second": 28.336,
       "step": 40
+    },
+    {
+      "epoch": 0.07695596408721676,
+      "grad_norm": 27.541791915893555,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 3.2613,
+      "step": 45
+    },
+    {
+      "epoch": 0.08550662676357418,
+      "grad_norm": 43.12064743041992,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 3.5703,
+      "step": 50
+    },
+    {
+      "epoch": 0.08550662676357418,
+      "eval_loss": 3.2112386226654053,
+      "eval_runtime": 4.6985,
+      "eval_samples_per_second": 104.927,
+      "eval_steps_per_second": 26.391,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -122,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1022465132199936.0,
+  "total_flos": 1274925658669056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null