Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b3acfe54a3eb4716133926a53fac8061d144f51c740bcd2f7c24ca94566de34
+oid sha256:18880f0009d88f2e4ace1c51f20a265e75c72b04356aa8dd0aed83cdcd7313c1
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c259a649b9e031e9eddd15b1f4b601cf60ee875b631bbc1ed58a0ac387cd7d45
+oid sha256:a4b4f5a1f31de8907a7cfea15ac3338b0a020e3ad5a36cee4920e5eea86613b7
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d01044cb3e12131a6e3de922bc2b20d92d9a1ef7b0ba4d2134c51637c33a41e4
+oid sha256:7a17cd15b2e15390a515768c1bc1fccdfba01249f8a67e0095eb77b09ca8fe95
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00030028677386904494,
+  "epoch": 0.0006005735477380899,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 0.8769,
       "step": 9
+    },
+    {
+      "epoch": 0.00036034412864285393,
+      "grad_norm": 0.27589112520217896,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.7145,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004504301608035674,
+      "grad_norm": 0.3418157696723938,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.6903,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004804588381904719,
+      "eval_loss": 0.6653794646263123,
+      "eval_runtime": 1652.2191,
+      "eval_samples_per_second": 8.487,
+      "eval_steps_per_second": 4.243,
+      "step": 16
+    },
+    {
+      "epoch": 0.0005405161929642808,
+      "grad_norm": 0.2595500349998474,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6711,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8093431863705600.0,
+  "total_flos": 1.68216426971136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null