Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25cdbee56a012b7a943582eda10041858b682e93d3787fb300a047e047c5c0c5
+oid sha256:09eff9893217e15f444ab4707c62f221fd380bb76726191e460e21c372c9981f
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8846d4eed0b4d93132681b7d90736d48a7c25867d6931180ee6f49c679550274
+oid sha256:f5b2763534353825914723f5ca7f7396bb2e289598bad77d5bcf75530b4b8cf0
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ff3241625db89c21a92f1e0ba7ceddc1f490ba16891c8844f47e3134d48a1c
+oid sha256:c6fd42b640f00a8092cbcf8172f91307bcc479d2b1c5085a4ff026b0254ba8aa
 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": 0.009454029780193808,
+  "epoch": 0.018908059560387616,
   "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": 11.7031,
       "step": 9
+    },
+    {
+      "epoch": 0.011344835736232569,
+      "grad_norm": 8.001744270324707,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.9033,
+      "step": 12
+    },
+    {
+      "epoch": 0.014181044670290712,
+      "grad_norm": 5.943373680114746,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.1325,
+      "step": 15
+    },
+    {
+      "epoch": 0.015126447648310093,
+      "eval_loss": 2.807215690612793,
+      "eval_runtime": 4.5014,
+      "eval_samples_per_second": 99.081,
+      "eval_steps_per_second": 49.541,
+      "step": 16
+    },
+    {
+      "epoch": 0.017017253604348855,
+      "grad_norm": 6.981635093688965,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.5672,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 43111321436160.0,
+  "total_flos": 86222642872320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null