Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9134d7f523591dbe15d08ac52b320c201ecc62305a5d7061d927ff1d75504362
+oid sha256:dc5dc84a51e205fd90e2621942ba5f3b890e38bff1df9e3062c7ace07308f5ba
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18dc31c966bd73590b6ebb1a8e5e94c38a9e462928cd389b2cc45106485ca317
+oid sha256:475070eb12288fff51c139c75e77ad9c002859f88bf45e7a73cb2d2ef8e1e2b0
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 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": 0.009507962918944617,
+  "epoch": 0.019015925837889233,
   "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": 219.083,
       "eval_steps_per_second": 109.789,
       "step": 10
+    },
+    {
+      "epoch": 0.011409555502733539,
+      "grad_norm": 0.040299348533153534,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.7613,
+      "step": 12
+    },
+    {
+      "epoch": 0.014261944378416925,
+      "grad_norm": 0.044069357216358185,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.7623,
+      "step": 15
+    },
+    {
+      "epoch": 0.014261944378416925,
+      "eval_loss": 11.762299537658691,
+      "eval_runtime": 2.0611,
+      "eval_samples_per_second": 214.93,
+      "eval_steps_per_second": 107.708,
+      "step": 15
+    },
+    {
+      "epoch": 0.01711433325410031,
+      "grad_norm": 0.04311707988381386,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.761,
+      "step": 18
+    },
+    {
+      "epoch": 0.019015925837889233,
+      "eval_loss": 11.76194953918457,
+      "eval_runtime": 2.1131,
+      "eval_samples_per_second": 209.647,
+      "eval_steps_per_second": 105.06,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1018500218880.0,
+  "total_flos": 2037000437760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null