Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aa5d6432bd0f4e47557eb82558c81de1e5d18973a293ad9b60f6d3a221be59f
+oid sha256:05d3b6bacd198c2d78d6ec4df8fe08fce01829fa46a934ea4bb7e8a2e8db8902
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b639cfeda604c126931a0c3262889c6456a730e444a817b77dcacfc1656d7cbe
+oid sha256:73714c8030a56679c1d165eea466f4c53a8bcb514e9f33e106b6b3e528a33191
 size 191012170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33d1a6cb8d6446adacc258c7bc58ee9973b85879c1ae13ced530a1739605627
+oid sha256:9cbde92c40f44796fa92ccdce1b42a550c278b3c9c47995b873b107e5adf740a
 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": 0.002053071908843607,
+  "epoch": 0.004106143817687214,
   "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": 31.477,
       "eval_steps_per_second": 15.746,
       "step": 10
+    },
+    {
+      "epoch": 0.0024636862906123286,
+      "grad_norm": 10.116308212280273,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 8.9857,
+      "step": 12
+    },
+    {
+      "epoch": 0.003079607863265411,
+      "grad_norm": 10.924723625183105,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 7.3211,
+      "step": 15
+    },
+    {
+      "epoch": 0.003079607863265411,
+      "eval_loss": 0.8407554030418396,
+      "eval_runtime": 65.2409,
+      "eval_samples_per_second": 31.437,
+      "eval_steps_per_second": 15.726,
+      "step": 15
+    },
+    {
+      "epoch": 0.003695529435918493,
+      "grad_norm": 13.506694793701172,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 8.1083,
+      "step": 18
+    },
+    {
+      "epoch": 0.004106143817687214,
+      "eval_loss": 0.8125434517860413,
+      "eval_runtime": 65.1722,
+      "eval_samples_per_second": 31.47,
+      "eval_steps_per_second": 15.743,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1462662995116032.0,
+  "total_flos": 2925325990232064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null