Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979ef015fcecd9f4634b22d768f4d8a0d145529520334910eb9989f622e5cfa7
+oid sha256:be13dd30deabc91c7f1eef1ea22aab61332e961ca304f0aa8146e4813cfc895e
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc1ba9f58b917f003266e63a11787d2fa749f235aaf801c180eb929adaee72e
+oid sha256:3ebf79a01fc9a02fad4f28b72dd1075124faa66205558b9ec484f91d21bd5a4b
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a083a129159440f3f40c21dbf044f9db32e87979479354f79b35c86bfc3bdd
+oid sha256:d8874dd5e607118e18f489ed9ad8aaab7c3de4c272a2acaa47fb9a2cd05a480a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e33da60be502927a2afa2046e81eb3da1ce22fa49e674a279bab92f8b0f7cf7
+oid sha256:605d23f463d574da26fdafa2a2fc396d0b00160053ea75ca175c5c8e6f2990e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002889194862650385,
+  "epoch": 0.00577838972530077,
   "eval_steps": 8,
-  "global_step": 8,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 9.37,
       "eval_steps_per_second": 4.686,
       "step": 8
+    },
+    {
+      "epoch": 0.003250344220481683,
+      "grad_norm": 0.5005409121513367,
+      "learning_rate": 9e-05,
+      "loss": 2.455,
+      "step": 9
+    },
+    {
+      "epoch": 0.004333792293975577,
+      "grad_norm": 0.5685995817184448,
+      "learning_rate": 0.00012,
+      "loss": 2.3321,
+      "step": 12
+    },
+    {
+      "epoch": 0.005417240367469472,
+      "grad_norm": 0.3448821008205414,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.2488,
+      "step": 15
+    },
+    {
+      "epoch": 0.00577838972530077,
+      "eval_loss": 2.2601964473724365,
+      "eval_runtime": 995.6768,
+      "eval_samples_per_second": 9.367,
+      "eval_steps_per_second": 4.684,
+      "step": 16
     }
   ],
   "logging_steps": 3,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.256153676546048e+16,
+  "total_flos": 8.512307353092096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null