Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a5d8df64063469dc71c74c663c4b1d681310529678e10d5f489ede1abd8fb7
+oid sha256:90c26a85e38465a485240c658909a17687699416af3e79f864da8043bd0f62fc
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3657eb26bc52c44b6e2fd5cf559ef3b8a788c9cb9360e89c53d7142597093848
+oid sha256:f80c9ff111119d40461ca73630d31c5328cada50105f577839c77ebc90090796
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4013f5415f2c9bc2c3fb43af59e9a1c2d939420d74ac20199f32225d57bbe5b8
+oid sha256:3a5c53b4ddb1f83c87db0874b9ca8a72613eb4fb4e16a727f1e944d64a00fe7b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d7496cd5cad5fcd343f51f06f864ca525a833da3ba71e9c4d90915510423ac
+oid sha256:7cbe95d5ecd33771846042e20aabf210775f4e6a78ced16f0764898d40abeba5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009780548933308882,
+  "epoch": 0.012225686166636102,
   "eval_steps": 34,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -155,6 +155,41 @@
       "learning_rate": 0.00013333333333333334,
       "loss": 8.2326,
       "step": 20
+    },
+    {
+      "epoch": 0.010269576379974325,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014,
+      "loss": 9.7804,
+      "step": 21
+    },
+    {
+      "epoch": 0.01075860382663977,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 9.2763,
+      "step": 22
+    },
+    {
+      "epoch": 0.011247631273305215,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 9.1653,
+      "step": 23
+    },
+    {
+      "epoch": 0.011736658719970658,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016,
+      "loss": 8.6687,
+      "step": 24
+    },
+    {
+      "epoch": 0.012225686166636102,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 9.1022,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -174,7 +209,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.408959351914496e+16,
+  "total_flos": 5.51119918989312e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null