Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c8d03dc3c61474f9d2508fa77152c201e7449fb38ce400c82583ff612548114
+oid sha256:5bed83cbf30195b0409d913080a886a87db72479b93608c38d32d6813e7073a4
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e07eddc47b2b37de406923aa696f3957e0637935f3fd68b0232c550918137a7
+oid sha256:0890a0f9b813ae6f0635fa6a23d5e853a1cca9ebd7f28606040c2f8483067153
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fac8dc3559aa6a81370bb141163d5dc06aeeb8795a754c1c7ff70e9049a5afd
+oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
 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": 0.0026263952724885093,
+  "epoch": 0.005252790544977019,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 10.581,
       "eval_steps_per_second": 5.302,
       "step": 3
+    },
+    {
+      "epoch": 0.0035018603633180127,
+      "grad_norm": 0.3287069797515869,
+      "learning_rate": 8e-05,
+      "loss": 1.3581,
+      "step": 4
+    },
+    {
+      "epoch": 0.004377325454147516,
+      "grad_norm": 0.3288503885269165,
+      "learning_rate": 0.0001,
+      "loss": 1.1164,
+      "step": 5
+    },
+    {
+      "epoch": 0.005252790544977019,
+      "grad_norm": 0.43857482075691223,
+      "learning_rate": 0.00012,
+      "loss": 1.4435,
+      "step": 6
+    },
+    {
+      "epoch": 0.005252790544977019,
+      "eval_loss": 0.9882233738899231,
+      "eval_runtime": 45.5803,
+      "eval_samples_per_second": 10.553,
+      "eval_steps_per_second": 5.287,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899723258593280.0,
+  "total_flos": 3799446517186560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null