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:f121231cd6bd0f0ed44f262d87d79900f9c40f298229b8415917f4b24a38a7fd
+oid sha256:4777ca66f64962143c07aca10bea0db73000acb3e3dc94a1594efa53ac7b8113
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:228c4c8867285c663cdd90060f68f44137006d648f4fc64bc8217a2b881c2448
+oid sha256:ab7dffdca6b3835ba52ecd9787f62863f8cd456c4bf734ba19a03211c2e206c9
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54966f2465e62f3f23221c1b18d8d6c1829302b329b674439c498e34e1b28ba
+oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
 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": 0.004624277456647399,
+  "epoch": 0.009248554913294798,
   "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": 81.678,
       "eval_steps_per_second": 81.678,
       "step": 3
+    },
+    {
+      "epoch": 0.006165703275529865,
+      "grad_norm": 0.06343778967857361,
+      "learning_rate": 8e-05,
+      "loss": 10.3694,
+      "step": 4
+    },
+    {
+      "epoch": 0.007707129094412331,
+      "grad_norm": 0.04486631974577904,
+      "learning_rate": 0.0001,
+      "loss": 10.3676,
+      "step": 5
+    },
+    {
+      "epoch": 0.009248554913294798,
+      "grad_norm": 0.05424387380480766,
+      "learning_rate": 0.00012,
+      "loss": 10.3747,
+      "step": 6
+    },
+    {
+      "epoch": 0.009248554913294798,
+      "eval_loss": 10.369335174560547,
+      "eval_runtime": 1.7112,
+      "eval_samples_per_second": 80.062,
+      "eval_steps_per_second": 80.062,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 156907339776.0,
+  "total_flos": 313814679552.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null