Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a4cb3e8a1d1b551551164b20f7d64ac05601ce998412c9f7f85cb6d7a74c30
+oid sha256:fd87f0847e09344045a25e17d3ade5b44bc8c2026cac0add69bcde206f8beaa6
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e75e3bc82d2bf28b0cb89531ee359a73b0ed5c6877b18d578801883cb412ee70
+oid sha256:346b276a380a8aee9559e75c91a0b09fba4ed9fcdb5805569da99d5a629970bd
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c2503ae81e12d5082c4278925da3338d45258340e6a04f5936064b4fee9049
+oid sha256:71a1465b568049063c0707d9322eb5b7d29583306348c6dcd79a87cdb3bd71f9
 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": 0.023622047244094488,
+  "epoch": 0.047244094488188976,
   "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": 10.036,
       "eval_steps_per_second": 5.018,
       "step": 3
+    },
+    {
+      "epoch": 0.031496062992125984,
+      "grad_norm": 4.027983665466309,
+      "learning_rate": 8e-05,
+      "loss": 8.5513,
+      "step": 4
+    },
+    {
+      "epoch": 0.03937007874015748,
+      "grad_norm": 4.555736541748047,
+      "learning_rate": 0.0001,
+      "loss": 7.9343,
+      "step": 5
+    },
+    {
+      "epoch": 0.047244094488188976,
+      "grad_norm": 5.244207859039307,
+      "learning_rate": 0.00012,
+      "loss": 8.4064,
+      "step": 6
+    },
+    {
+      "epoch": 0.047244094488188976,
+      "eval_loss": 7.6861042976379395,
+      "eval_runtime": 5.4901,
+      "eval_samples_per_second": 9.836,
+      "eval_steps_per_second": 4.918,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 522790813827072.0,
+  "total_flos": 1045581627654144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null