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:fd35864bd69b7f99459862c09297a4fd22715243bb5093e89a80098ec0684e16
+oid sha256:b2571169a9842531ceea70ef73b26eff5def8a8e9d0c11528402700c141e00d8
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f06e6baaad70b74088cc936aab5abb89e700202afbde115abbd20a7bb3be7ae
+oid sha256:f33b222ebc1b4389474297cdb5def5494cc054f98b6ae39c5665acf4cea9c020
 size 1324026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9af5373aa88895259568af4bb4ee43ae11bdbf1ba2f7d2b539d2b279040940d
+oid sha256:3fb5f1f2063cc0fc9d69930536ad8305cd213d31011d601a76e1f19f1f368b7a
 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": 0.001380897583429229,
+  "epoch": 0.002761795166858458,
   "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": 14.706,
       "eval_steps_per_second": 7.361,
       "step": 3
+    },
+    {
+      "epoch": 0.0018411967779056386,
+      "grad_norm": 0.7256842255592346,
+      "learning_rate": 8e-05,
+      "loss": 11.911,
+      "step": 4
+    },
+    {
+      "epoch": 0.0023014959723820483,
+      "grad_norm": 0.5256912112236023,
+      "learning_rate": 0.0001,
+      "loss": 11.9209,
+      "step": 5
+    },
+    {
+      "epoch": 0.002761795166858458,
+      "grad_norm": 0.6058363318443298,
+      "learning_rate": 0.00012,
+      "loss": 11.9211,
+      "step": 6
+    },
+    {
+      "epoch": 0.002761795166858458,
+      "eval_loss": 11.920125007629395,
+      "eval_runtime": 62.2091,
+      "eval_samples_per_second": 14.708,
+      "eval_steps_per_second": 7.362,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3046832603136.0,
+  "total_flos": 6093665206272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null