Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c36e4bbcb82981cdc2c5160e767238f64ee490581878f19543006aff1e772d
+oid sha256:6848ad7fe0ab9ebd010e4b53d428e9a2ecbf51eac7025ec3372d035f504cfda7
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec7a883119f92e3ee0a3f6e4dc4c034dfa53ea9273838ff860d472622248688
+oid sha256:9568be57a32d71e64a0a8a76e2f0252a12fca42f5ea09f44aeb7dc5a1241d96e
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532fbdc029a82d211e1ef30e3e4f92c1f8faca903ca2670d8826965b31e126bf
+oid sha256:4c30a031a5dd4c570fd24101d516cbee229a4a54d7a97d450184c72ae0b9a52b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00043835616438356166,
+  "epoch": 0.0008767123287671233,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 9.192,
       "eval_steps_per_second": 4.596,
       "step": 5
+    },
+    {
+      "epoch": 0.0005260273972602739,
+      "grad_norm": 12.26352310180664,
+      "learning_rate": 6e-05,
+      "loss": 4.1608,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006136986301369863,
+      "grad_norm": 8.713861465454102,
+      "learning_rate": 7e-05,
+      "loss": 3.7209,
+      "step": 7
+    },
+    {
+      "epoch": 0.0007013698630136987,
+      "grad_norm": 8.520092964172363,
+      "learning_rate": 8e-05,
+      "loss": 3.3179,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007890410958904109,
+      "grad_norm": 8.435450553894043,
+      "learning_rate": 9e-05,
+      "loss": 2.7645,
+      "step": 9
+    },
+    {
+      "epoch": 0.0008767123287671233,
+      "grad_norm": 7.701727390289307,
+      "learning_rate": 0.0001,
+      "loss": 2.4773,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008767123287671233,
+      "eval_loss": 2.0398104190826416,
+      "eval_runtime": 4178.7123,
+      "eval_samples_per_second": 9.195,
+      "eval_steps_per_second": 4.597,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2883817203302400.0,
+  "total_flos": 5767634406604800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null