Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a298c097c824164ea0cb53b61f88c4251893d258e0162862c7969450667c3ab
+oid sha256:83221abbf72b3ad635f578bbdae6ec07dac1bdc3763014b9dd41a0dc25af20ca
 size 125918320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da61dbb3feadc88fef877c953c688110a62c06741d2771262052c18df3feb737
+oid sha256:be465246389297d0e1d559bd8fbfd1aac299a1c0bde1f88af141b7c2500e2eec
 size 64683604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe53da7d994df8630f89cf936617740f54c0387adf260c7a778e59f4186c4eb7
+oid sha256:a74f0fa67ad2ea453853ea9c83fafb9413743a4d7deb09428e0f1e45b1df8364
 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": 0.00030957356241776953,
+  "epoch": 0.0006191471248355391,
   "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": 12.926,
       "eval_steps_per_second": 6.465,
       "step": 3
+    },
+    {
+      "epoch": 0.00041276474989035937,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 3.5043,
+      "step": 4
+    },
+    {
+      "epoch": 0.0005159559373629492,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 3.7374,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006191471248355391,
+      "grad_norm": 3.124617099761963,
+      "learning_rate": 0.00012,
+      "loss": 1.8695,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006191471248355391,
+      "eval_loss": NaN,
+      "eval_runtime": 315.8984,
+      "eval_samples_per_second": 12.919,
+      "eval_steps_per_second": 6.461,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1567738828947456.0,
+  "total_flos": 3135477657894912.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null