Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b040c725068a69b0f89a6c0b6ee52b632d2b88bf7b1871f9fe4e6231c9460e
+oid sha256:f3fa576ebbac5fc3b324cc9cbf99e0215c9ef9d32897a7e26935ce4bd1ebf3fd
 size 684272496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cee20f300468d8dcff07bb22344d5a3e1400c3527649bd3c7966ff68b438a19
+oid sha256:147adc4caac65cc9aa85f3e11bd9475eb6f9fac89d62bcdb54d162ce7a0acd09
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a040b3377ea29e2e573174f608927490657c8c978fdb95169126a63ddf2673b
+oid sha256:81d341293548ca00e0e58d5d96dd5b9a987f30f65d8d779264a3bcee6bef50b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05917159763313609,
+  "epoch": 0.07889546351084813,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 9.621,
       "eval_steps_per_second": 4.81,
       "step": 15
+    },
+    {
+      "epoch": 0.0631163708086785,
+      "grad_norm": 1.6371982097625732,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.336,
+      "step": 16
+    },
+    {
+      "epoch": 0.0670611439842209,
+      "grad_norm": 1.4365739822387695,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.2788,
+      "step": 17
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 0.5848339796066284,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0984,
+      "step": 18
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "eval_loss": 0.21445059776306152,
+      "eval_runtime": 22.3011,
+      "eval_samples_per_second": 9.596,
+      "eval_steps_per_second": 4.798,
+      "step": 18
+    },
+    {
+      "epoch": 0.07495069033530571,
+      "grad_norm": 2.026401996612549,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2734,
+      "step": 19
+    },
+    {
+      "epoch": 0.07889546351084813,
+      "grad_norm": 1.0910876989364624,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.215,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.960375813668864e+16,
+  "total_flos": 2.613834418225152e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null