Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd3f31da6ff143a810a9c458feec08d267d144a368de1ea76e6e63920a52f33
+oid sha256:dd07dd78b4b3df1671a88ed8bc86467cd58f7f0ddf93f39ca52434c5faf84b07
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60233da244fcffe138ef395493b249973c44bdd6c3d5ed637712164ebf8facd9
+oid sha256:7255aa0c5f6a8eb55f8011ec9819309282e44156609911ff0c295372a7a4a206
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a6e54f9735ac650e1bce7d31fe07be9de05d82d7f44a83bbaaeae992231fe8
+oid sha256:0a13307056da4bbb211ad48ade25632cd037a6f559d3df7d1e4eebdbef92276c
 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": 0.0005363607920261028,
+  "epoch": 0.0010727215840522057,
   "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": 22.774,
       "eval_steps_per_second": 11.387,
       "step": 3
+    },
+    {
+      "epoch": 0.0007151477227014706,
+      "grad_norm": 5.9732136726379395,
+      "learning_rate": 8e-05,
+      "loss": 9.4021,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008939346533768382,
+      "grad_norm": 3.995457887649536,
+      "learning_rate": 0.0001,
+      "loss": 8.6841,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010727215840522057,
+      "grad_norm": 4.911398410797119,
+      "learning_rate": 0.00012,
+      "loss": 9.7591,
+      "step": 6
+    },
+    {
+      "epoch": 0.0010727215840522057,
+      "eval_loss": 2.488743543624878,
+      "eval_runtime": 103.5404,
+      "eval_samples_per_second": 22.754,
+      "eval_steps_per_second": 11.377,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 569617680433152.0,
+  "total_flos": 1226868850163712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null