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:a3f0b78b244b67911ef6ddf26714da11ea0a3dbf6c8ac8884868fbb183bfc25c
+oid sha256:2f15319f9752fd56640bbddf0e8f14d84f1d9e41520c4ef6ae55878674acbbea
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f33a6bbaa2db18e9c976c023869cf06ae599c825e56352bdbf8ece599d1ca12
+oid sha256:fe4047f7fb7f0f8aaf1a8496362877186d2227bcdf11aa5b248a9be2ab42165f
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518b429e0446d874a46c68e645a8a9be310ea624bc19fad8dbf0c60a502d8577
+oid sha256:ea08a20338a9de9c853f6ce9dafb90883a73a29ebb9c8e72a3062bc566710086
 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": 0.00024838035311406867,
+  "epoch": 0.0004967607062281373,
   "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": 13.234,
       "eval_steps_per_second": 6.617,
       "step": 3
+    },
+    {
+      "epoch": 0.0003311738041520916,
+      "grad_norm": 1.495574951171875,
+      "learning_rate": 8e-05,
+      "loss": 2.3509,
+      "step": 4
+    },
+    {
+      "epoch": 0.0004139672551901145,
+      "grad_norm": 1.435874342918396,
+      "learning_rate": 0.0001,
+      "loss": 2.236,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004967607062281373,
+      "grad_norm": 2.2076618671417236,
+      "learning_rate": 0.00012,
+      "loss": 3.0957,
+      "step": 6
+    },
+    {
+      "epoch": 0.0004967607062281373,
+      "eval_loss": 0.5404369831085205,
+      "eval_runtime": 383.6732,
+      "eval_samples_per_second": 13.256,
+      "eval_steps_per_second": 6.628,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1741423367946240.0,
+  "total_flos": 2928757482455040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null