Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00f54e75e7ebf2e38d73960ea24f96e4846b33ed382b11eb04bff5488632f4a6
+oid sha256:a1151790881d72a0c9aae3018127f13bd480036895137272840c8ad9d29daa25
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c275310fa0353a45cc2b626d58bf4c1c99b62a41bae287a260e4d5f72d2524
+oid sha256:f0e02a97dd420652bc09048614b14b09dd80b036cebbf1eef575bf1bc78d3235
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48293ee1c07c7be1425c18c218bf31738d68b5bcf0d7c5c0bc8747f529706fab
+oid sha256:8077dc599d0e2178961c634ebb1554fd0bb63f56537a068f9b3ec5adbcb0bb0f
 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": 0.004228776826302992,
+  "epoch": 0.008457553652605984,
   "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": 1.559,
       "step": 9
+    },
+    {
+      "epoch": 0.00507453219156359,
+      "grad_norm": 1.1918922662734985,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.7637,
+      "step": 12
+    },
+    {
+      "epoch": 0.006343165239454488,
+      "grad_norm": 0.7861229777336121,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.458,
+      "step": 15
+    },
+    {
+      "epoch": 0.006766042922084787,
+      "eval_loss": 1.489386796951294,
+      "eval_runtime": 86.7212,
+      "eval_samples_per_second": 11.485,
+      "eval_steps_per_second": 5.743,
+      "step": 16
+    },
+    {
+      "epoch": 0.007611798287345386,
+      "grad_norm": 0.9497506022453308,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5591,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5288752935075840.0,
+  "total_flos": 1.066014263476224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null