Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e7c0f9e01fbbf7e8189164b6b10acdc9b4c4392b2b9bd48b6c4eca4c93f3b06
+oid sha256:f72eab8e82d4a3ebfaeeded13c0552334b26e14302a5161a2630c8bd5a24bd1a
 size 684272496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f8c88c5719fb5d77ea2b4e52225486b1f404429c2649703e01def31c635a23
+oid sha256:eccfb167eaa95d50bf83be9f2a408f5f20ddcabfc89c0c7b899facf90592dbe1
 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": 9.646,
       "eval_steps_per_second": 4.823,
       "step": 15
+    },
+    {
+      "epoch": 0.0631163708086785,
+      "grad_norm": 1.3745402097702026,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.3157,
+      "step": 16
+    },
+    {
+      "epoch": 0.0670611439842209,
+      "grad_norm": 1.2767657041549683,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.2803,
+      "step": 17
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 0.49950045347213745,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0943,
+      "step": 18
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "eval_loss": 0.21179427206516266,
+      "eval_runtime": 22.2542,
+      "eval_samples_per_second": 9.616,
+      "eval_steps_per_second": 4.808,
+      "step": 18
+    },
+    {
+      "epoch": 0.07495069033530571,
+      "grad_norm": 1.7894467115402222,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2785,
+      "step": 19
+    },
+    {
+      "epoch": 0.07889546351084813,
+      "grad_norm": 0.9164059162139893,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.209,
+      "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