Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2efb1cba585f94a5a93dac5e6ac3c2170ce2f7940c880140eeb638cae3f5d97c
+oid sha256:b9d72e83434e43ecc29a2d1896117839d6cf77c59cf806dafbd4c50ab20b2616
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835fc4764e1bf9d75c3ca23c4c3e164eb6dad9c6ec6649f6542e46675bdbecfa
+oid sha256:d097e0250b581121592987375dbaf7027f7451f51b93f98aafcb5a8e56d4da2d
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e081351a022c45bf031e060833aff1ba860157aceb2df94543881413eca763a
+oid sha256:4c8969108774412257f3bec7d27805c014858246b2ae2cafcc98af96054f2f98
 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": 0.07622677465459743,
+  "epoch": 0.0857551214864221,
   "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": 6.288,
       "eval_steps_per_second": 0.79,
       "step": 40
+    },
+    {
+      "epoch": 0.0800381133873273,
+      "grad_norm": 0.9819179773330688,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1547,
+      "step": 42
+    },
+    {
+      "epoch": 0.0857551214864221,
+      "grad_norm": 0.888201892375946,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1645,
+      "step": 45
+    },
+    {
+      "epoch": 0.0857551214864221,
+      "eval_loss": 2.2474822998046875,
+      "eval_runtime": 140.5849,
+      "eval_samples_per_second": 6.288,
+      "eval_steps_per_second": 0.79,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2068108629966848e+17,
+  "total_flos": 1.3576622208712704e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null