Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0185379de1df1af423c9ed26cd6d2a2d497ae8b74c49e91b2730cf754b65de39
+oid sha256:40319307ffecbee59bfe6f9166aa64b6b410b39cf17749336c9a22115ebb5f36
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9d1f4385ba8319e9ae7448c5d2d91616195cfa80cfa54903c66ff881ffae321
+oid sha256:ee615c2d72be7caeb3e3bcf5a13bf0f47aca34ff19271a2809b1b7a950b69950
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02f134912ce9a6e1af16e34500fe5858213e0164df9bf0779ab77e778327ed6
+oid sha256:6e10e7e084e9d9c969a8d9c919cc8f1ecdc23be93922140c6c36dc329b7d816c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010626051536349952,
+  "epoch": 0.0021252103072699905,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 13.303,
       "eval_steps_per_second": 6.657,
       "step": 3
+    },
+    {
+      "epoch": 0.0014168068715133268,
+      "grad_norm": 0.7416192293167114,
+      "learning_rate": 8e-05,
+      "loss": 1.7618,
+      "step": 4
+    },
+    {
+      "epoch": 0.0017710085893916587,
+      "grad_norm": 1.3207190036773682,
+      "learning_rate": 0.0001,
+      "loss": 2.6044,
+      "step": 5
+    },
+    {
+      "epoch": 0.0021252103072699905,
+      "grad_norm": 1.1416175365447998,
+      "learning_rate": 0.00012,
+      "loss": 2.1539,
+      "step": 6
+    },
+    {
+      "epoch": 0.0021252103072699905,
+      "eval_loss": 2.316065788269043,
+      "eval_runtime": 84.663,
+      "eval_samples_per_second": 14.044,
+      "eval_steps_per_second": 7.028,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 647347486851072.0,
+  "total_flos": 1202216761294848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null