Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4633e7ec5cd868b2dbd70c102625894528f5862fb8a9d93ec314fb04b4e1a8
+oid sha256:45cc30988e06e076ad7015710af5705a8a331318f493e51c9707525a0728b74b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf65c6ac04f9b8801242b782625c5c06a0b33584494b76a02a3a662b4e639283
+oid sha256:13499993dc923abc67babfacde62bbd3376d22ad5857c78a7f265ccc3f84611e
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2fc731ea935d8c8042146c2346f03f543488fb740ace2978182d0fd5f952727
+oid sha256:678b9545597981e0561935b4560b5685ae06bb237af557617b5c6286a1739a94
 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": 0.016842105263157894,
+  "epoch": 0.03368421052631579,
   "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": 10.698,
       "eval_steps_per_second": 5.349,
       "step": 10
+    },
+    {
+      "epoch": 0.020210526315789474,
+      "grad_norm": 2.382171392440796,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.2415,
+      "step": 12
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 1.840626835823059,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.6022,
+      "step": 15
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "eval_loss": 2.4173471927642822,
+      "eval_runtime": 23.3746,
+      "eval_samples_per_second": 10.695,
+      "eval_steps_per_second": 5.348,
+      "step": 15
+    },
+    {
+      "epoch": 0.03031578947368421,
+      "grad_norm": 1.4523637294769287,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.9354,
+      "step": 18
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "eval_loss": 1.888671875,
+      "eval_runtime": 23.3614,
+      "eval_samples_per_second": 10.701,
+      "eval_steps_per_second": 5.351,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347792213606400.0,
+  "total_flos": 1.26955844272128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null