Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9931d45a893f0323f83d7d925638eca694ec3dbaf515cb37d35d2f9089de6f1
+oid sha256:484b564556001283f0d8c372e1e22820eb2c2ababff7b29414fc5d7dd1d5cd90
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ebf159b5d8f003517833f1873b407503277ecf0057e96f68a4a691657f463df
+oid sha256:7f5b35a6fc72d8a9de74bdd173b4d56c093bd702a665fe32978ad4ba92d53fa3
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7423aaa4727bbaa077813be10674017129ec52b829027d020081dfa616515cb7
+oid sha256:cecf351b617076c45c0034f29458db064d42fc3eea5373ffe2c7217695d60873
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5893186003683242,
+  "epoch": 0.6629834254143646,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 42.39,
       "eval_steps_per_second": 10.69,
       "step": 40
+    },
+    {
+      "epoch": 0.6187845303867403,
+      "grad_norm": 0.6819091439247131,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1203,
+      "step": 42
+    },
+    {
+      "epoch": 0.6629834254143646,
+      "grad_norm": 0.7172572612762451,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1542,
+      "step": 45
+    },
+    {
+      "epoch": 0.6629834254143646,
+      "eval_loss": 1.1671010255813599,
+      "eval_runtime": 2.7155,
+      "eval_samples_per_second": 42.349,
+      "eval_steps_per_second": 10.679,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8985885328539648.0,
+  "total_flos": 1.0105787951087616e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null