Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c841db0f6abb394c5c5cc53e41ac9d3f254b63dd7de214bffa670564b75faa3e
+oid sha256:cc4686983b37bec8223e73524ae716a13ec48ff4d26053b07aac639c1976d874
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d06f8c5ca13affd83f2e53dfde10712eddb261261ee885ea42703dce62c3cd0
+oid sha256:9f0ea7967420b595acdeeb10bff627cdc616fdac77c4d8f473d696610aea1e12
 size 20814996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67773813a54698cff5170703d0ad671479f015fe9426368cf5216033a5859f7b
+oid sha256:7e80e63932c8eae7c99e68576eba41b28c2be6da6d5728e9d2106b0941dfcd24
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007416334476684898,
+  "epoch": 0.011124501715027348,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 7.955,
       "eval_steps_per_second": 7.955,
       "step": 10
+    },
+    {
+      "epoch": 0.008157967924353388,
+      "grad_norm": 24.458194732666016,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.4457,
+      "step": 11
+    },
+    {
+      "epoch": 0.008899601372021879,
+      "grad_norm": 21.18819236755371,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.5617,
+      "step": 12
+    },
+    {
+      "epoch": 0.009641234819690368,
+      "grad_norm": 20.3893985748291,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 3.4987,
+      "step": 13
+    },
+    {
+      "epoch": 0.010382868267358857,
+      "grad_norm": 14.517038345336914,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.4438,
+      "step": 14
+    },
+    {
+      "epoch": 0.011124501715027348,
+      "grad_norm": 12.411314964294434,
+      "learning_rate": 0.0001,
+      "loss": 2.0407,
+      "step": 15
+    },
+    {
+      "epoch": 0.011124501715027348,
+      "eval_loss": 0.4047902226448059,
+      "eval_runtime": 71.2049,
+      "eval_samples_per_second": 7.977,
+      "eval_steps_per_second": 7.977,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 813146528808960.0,
+  "total_flos": 1219719793213440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null