Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3f6ad851b3c4195818f60c81424d18340984ac6a7bbf4d8f6eb6977ed7adb9
+oid sha256:cb63d175031a0616e05f9429310940ca0c0b79db08ded5f02cd2825cc952d8eb
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ae7d1c1f1369f8a786a8da4197cc465369b65469d364c1d69f57eaa9c6a0a4
+oid sha256:f1ce3f3d755a5d386242838143d3aaa39ba7fc0dce18a381acf5dc5f42da2140
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61630a9df826f43c43e9d9f3f658b33939478e91788026e7879f5a1c25f3bc5a
+oid sha256:3e3ce1e356308cda3ddd2d4705f7af2f5fe7e2c1b340a29fcba2536848f7853d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:9d56d291cd18ad7810448a139510801dad1c82b4d3f55f294cbe92a611a910b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5333333333333333,
+  "epoch": 0.8,
   "eval_steps": 4,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "learning_rate": 0.0001,
       "loss": 6.183,
       "step": 10
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.2767314910888672,
+      "eval_runtime": 0.3687,
+      "eval_samples_per_second": 21.7,
+      "eval_steps_per_second": 10.85,
+      "step": 12
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 7.032001495361328,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.2529,
+      "step": 15
     }
   ],
   "logging_steps": 5,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 324298258513920.0,
+  "total_flos": 486447387770880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null