Training in progress, step 124, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caeddd11e4b9cc9d83e11d9ec3987e94c5436376e83a9998ce3068e458397d51
+oid sha256:672b05673b812e5e9c2b96e7fc581c47c8bc45fe637a2c64823fa5c26313a4d1
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705b00d71daa4142253c16c1bebea91dabaa93d2b6338a801dde26f42519f2dc
+oid sha256:fcd0849778cac2f59c2171424c9084ba127563d2e4a8b6176002dcd78d4fcb10
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ac7f1c5347e279b4947122f9a4f1ea87fde404d3dbf35cb5a047b4265298f9
+oid sha256:e848e9332425e8f19037f20611574d35f1552d094f74408669d2f10122fbcb5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bfc2360018b511a262b59e99fcddde6a9bd8f019814a20e26529e523d531e5
+oid sha256:3ccd887015d7faf1da47941525d069c3cb7c1208d0267f6e00e06c9dcf3b23ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7545638945233266,
+  "epoch": 1.0060851926977687,
   "eval_steps": 31,
-  "global_step": 93,
+  "global_step": 124,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -256,6 +256,84 @@
       "eval_samples_per_second": 15.452,
       "eval_steps_per_second": 1.931,
       "step": 93
+    },
+    {
+      "epoch": 0.7789046653144016,
+      "grad_norm": 4.811842918395996,
+      "learning_rate": 8.656768508095853e-05,
+      "loss": 2.2144,
+      "step": 96
+    },
+    {
+      "epoch": 0.8032454361054767,
+      "grad_norm": 4.506133556365967,
+      "learning_rate": 8.566252245770909e-05,
+      "loss": 2.0727,
+      "step": 99
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 3.898118734359741,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.9802,
+      "step": 102
+    },
+    {
+      "epoch": 0.8519269776876268,
+      "grad_norm": 4.056739807128906,
+      "learning_rate": 8.377951038078302e-05,
+      "loss": 2.034,
+      "step": 105
+    },
+    {
+      "epoch": 0.8762677484787018,
+      "grad_norm": 4.857217788696289,
+      "learning_rate": 8.280295144952536e-05,
+      "loss": 1.9623,
+      "step": 108
+    },
+    {
+      "epoch": 0.9006085192697769,
+      "grad_norm": 4.711864948272705,
+      "learning_rate": 8.18039110138882e-05,
+      "loss": 2.3024,
+      "step": 111
+    },
+    {
+      "epoch": 0.9249492900608519,
+      "grad_norm": 4.590112686157227,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.9634,
+      "step": 114
+    },
+    {
+      "epoch": 0.949290060851927,
+      "grad_norm": 6.305273056030273,
+      "learning_rate": 7.974113933756707e-05,
+      "loss": 2.0567,
+      "step": 117
+    },
+    {
+      "epoch": 0.973630831643002,
+      "grad_norm": 3.979123115539551,
+      "learning_rate": 7.86788218175523e-05,
+      "loss": 2.024,
+      "step": 120
+    },
+    {
+      "epoch": 0.9979716024340771,
+      "grad_norm": 3.4800965785980225,
+      "learning_rate": 7.75968492656029e-05,
+      "loss": 2.2663,
+      "step": 123
+    },
+    {
+      "epoch": 1.0060851926977687,
+      "eval_loss": 0.5130282640457153,
+      "eval_runtime": 13.4323,
+      "eval_samples_per_second": 15.485,
+      "eval_steps_per_second": 1.936,
+      "step": 124
     }
   ],
   "logging_steps": 3,
@@ -275,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2373610700629606e+17,
+  "total_flos": 1.646904300577751e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null