Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b01c9493d62d83796df36fc0a86a430d24dfb8684ddec35d5fba6f8cf20f20
+oid sha256:04bfe7cbf5fdf6c12c66bdfbd4ca6c6514b29ad860026dd80db4336fd3cc0273
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a75142a9a067bad73241aa28b03c82dc8ae465658ce895ed7e89829d36f3c54
+oid sha256:c5029b63f2a422e2350412128b96e8f21cf7b67990b5f5c93be04728f27f1487
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b44c40f905ff4005f2fd07fb75c94e05853aefb266132b37a651600dcd3674
+oid sha256:e28f3b74a45f2c0dd30153fccda1a09054d4dff99c523026499904ccc7b004ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00030028677386904494,
+  "epoch": 0.0006005735477380899,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 8.513,
       "eval_steps_per_second": 4.257,
       "step": 10
+    },
+    {
+      "epoch": 0.00036034412864285393,
+      "grad_norm": 0.27762144804000854,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.7966,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004504301608035674,
+      "grad_norm": 0.4063872694969177,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7659,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004504301608035674,
+      "eval_loss": 0.7490118741989136,
+      "eval_runtime": 1647.3075,
+      "eval_samples_per_second": 8.512,
+      "eval_steps_per_second": 4.256,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005405161929642808,
+      "grad_norm": 0.29023927450180054,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.7313,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006005735477380899,
+      "eval_loss": 0.6987407803535461,
+      "eval_runtime": 1647.474,
+      "eval_samples_per_second": 8.511,
+      "eval_steps_per_second": 4.256,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8093431863705600.0,
+  "total_flos": 1.68216426971136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null