Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ba621e4641ab7c82c26d014cb445acf9574fc82b29177de94d6dc585760667
+oid sha256:8b53a762c6941655befe9fc0b11616f27e1c341e5f2cae25d9ba3f6fd47f71fe
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a90fe11ee29fac590ed77f2e34a82b2b2a0f7b2058c7bdb1e2d2ccab17071e4b
+oid sha256:d0b837c5994d4887f4310525b74b524dbc00aa3011b71e80d24d1e2111fa7390
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5c2489f942c0bfb1f653e1fc6bfc4d52b4ef6a98d19d8a41801976ad4c8d82
+oid sha256:f740901ed64f5f8faba4c4399f748c6779503ac7c16ef83516dab3603a5a5402
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
+oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0020325633588109504,
+  "epoch": 0.004065126717621901,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 129.969,
       "eval_steps_per_second": 64.989,
       "step": 9
+    },
+    {
+      "epoch": 0.0027100844784146007,
+      "grad_norm": 0.030115395784378052,
+      "learning_rate": 0.00012,
+      "loss": 10.3802,
+      "step": 12
+    },
+    {
+      "epoch": 0.003387605598018251,
+      "grad_norm": 0.030468817800283432,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 10.3799,
+      "step": 15
+    },
+    {
+      "epoch": 0.004065126717621901,
+      "grad_norm": 0.03643874451518059,
+      "learning_rate": 0.00018,
+      "loss": 10.3789,
+      "step": 18
+    },
+    {
+      "epoch": 0.004065126717621901,
+      "eval_loss": 10.378609657287598,
+      "eval_runtime": 114.6566,
+      "eval_samples_per_second": 130.084,
+      "eval_steps_per_second": 65.046,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3849125363712.0,
+  "total_flos": 7698250727424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null