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:b6a2c4a5302057ae4bf5ebde0e11e45540f94682117bd98ab4a74f4464b2c67d
+oid sha256:3558277e560a59b9badeb6bac2729bade34c78b8b20452984d4887b54497dbb4
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc334085c8ce887a496861d7033a48b8bbcb1129f48e78c7c567869cc09bccf2
+oid sha256:5dc8054f5f2102f9bf053d9fe6c4659c0c0ba6ab9b32c5e930f053d851021ce4
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c6291480501dedfdd188a2dde82d0e9dc6215c3786cd8b8b61e96d2ad44a53
+oid sha256:3483100185f9bb64a1baea7d0678dd8819a763e19d4dc3947a4c495c2a757eec
 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": 0.00032123353678124,
+  "epoch": 0.00064246707356248,
   "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": 10.736,
       "eval_steps_per_second": 10.736,
       "step": 3
+    },
+    {
+      "epoch": 0.0004283113823749866,
+      "grad_norm": 0.5536651015281677,
+      "learning_rate": 8e-05,
+      "loss": 1.1659,
+      "step": 4
+    },
+    {
+      "epoch": 0.0005353892279687332,
+      "grad_norm": 0.4006960093975067,
+      "learning_rate": 0.0001,
+      "loss": 1.0878,
+      "step": 5
+    },
+    {
+      "epoch": 0.00064246707356248,
+      "grad_norm": 0.34919866919517517,
+      "learning_rate": 0.00012,
+      "loss": 1.0365,
+      "step": 6
+    },
+    {
+      "epoch": 0.00064246707356248,
+      "eval_loss": 1.0633049011230469,
+      "eval_runtime": 184.7088,
+      "eval_samples_per_second": 10.649,
+      "eval_steps_per_second": 10.649,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 936521553149952.0,
+  "total_flos": 1669451464310784.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null