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:f638571cb04f507ad43635ec9dc1d7c0890f4bbf5cd767c08abb91345e5bef51
+oid sha256:4a97a5a5e4223d5d1a7b9d699505c3f2e27209c7080f28ee4c920665cf741fd1
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b918a94275a3c9e20bac7864b73323307fda7e58d59470f55c5b41b5827de74a
+oid sha256:01eff959233dbf56448a96733fdb1bf847580c3278a09a0e4965850271000de6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cd6212ea449919b16c27f03f3bc6259bca70d0644963554b54b0854f760edf
+oid sha256:3ebefa66f685e689769adaafd457264ae6777a954ae0a77f34d7684be2682c30
 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": 0.007237635705669481,
+  "epoch": 0.014475271411338963,
   "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": 9.248,
       "eval_steps_per_second": 4.65,
       "step": 3
+    },
+    {
+      "epoch": 0.009650180940892641,
+      "grad_norm": 22.9996395111084,
+      "learning_rate": 8e-05,
+      "loss": 37.4163,
+      "step": 4
+    },
+    {
+      "epoch": 0.012062726176115802,
+      "grad_norm": 29.07944107055664,
+      "learning_rate": 0.0001,
+      "loss": 39.3024,
+      "step": 5
+    },
+    {
+      "epoch": 0.014475271411338963,
+      "grad_norm": 33.20098114013672,
+      "learning_rate": 0.00012,
+      "loss": 34.4348,
+      "step": 6
+    },
+    {
+      "epoch": 0.014475271411338963,
+      "eval_loss": 8.189959526062012,
+      "eval_runtime": 19.1162,
+      "eval_samples_per_second": 9.155,
+      "eval_steps_per_second": 4.603,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 949861251809280.0,
+  "total_flos": 1899722503618560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null