Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:052ef361567c1116245475bb2c6963a7cf33acb8fde0c052e3db06faff3d8020
+oid sha256:993bef54891e9f26928b34290e6027d8c9c9ce4065d79d42ca7be3baf1070577
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ebb4672a1cbf93ea06141aa3e6db6d0b9c07b73fcf957a99c41179241340a7
+oid sha256:0e5659b524e48a2f03547e258274127e7efcfbbf02c56da73569563c1781b871
 size 60387220

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:facdb6d766a802a4f41ae7ca1bf9ed0da8d62bf0691baea9ce44e43fff7b8488
+oid sha256:72e45582261b53d7ecaa35c88e1eccb7713c6d0eb5a23b772caf206808bfa0b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f98b0f987b6a53d8a80048752e47fb211cd0245c26efa29892e076b577ed88b1
+oid sha256:40873409734f7d9ee90459df93f961e6509fa0a5626c33d9d437e5203db441a6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021473710043560953,
+  "epoch": 0.024541382906926805,
   "eval_steps": 20,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -262,6 +262,51 @@
       "eval_samples_per_second": 5.068,
       "eval_steps_per_second": 0.659,
       "step": 340
+    },
+    {
+      "epoch": 0.022087244616234125,
+      "grad_norm": 0.6657942533493042,
+      "learning_rate": 0.00019854781968420192,
+      "loss": 1.5955,
+      "step": 360
+    },
+    {
+      "epoch": 0.022087244616234125,
+      "eval_loss": 1.4536309242248535,
+      "eval_runtime": 19.6042,
+      "eval_samples_per_second": 5.101,
+      "eval_steps_per_second": 0.663,
+      "step": 360
+    },
+    {
+      "epoch": 0.023314313761580465,
+      "grad_norm": 0.8438799977302551,
+      "learning_rate": 0.00019846600670866399,
+      "loss": 1.5271,
+      "step": 380
+    },
+    {
+      "epoch": 0.023314313761580465,
+      "eval_loss": 1.4461709260940552,
+      "eval_runtime": 19.7178,
+      "eval_samples_per_second": 5.072,
+      "eval_steps_per_second": 0.659,
+      "step": 380
+    },
+    {
+      "epoch": 0.024541382906926805,
+      "grad_norm": 0.6734594702720642,
+      "learning_rate": 0.0001983841937331261,
+      "loss": 1.4713,
+      "step": 400
+    },
+    {
+      "epoch": 0.024541382906926805,
+      "eval_loss": 1.4335358142852783,
+      "eval_runtime": 19.7501,
+      "eval_samples_per_second": 5.063,
+      "eval_steps_per_second": 0.658,
+      "step": 400
     }
   ],
   "logging_steps": 20,
@@ -269,7 +314,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 2.232155831666688e+16,
+  "total_flos": 2.60309133775872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null