Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c64e251c9b2e06e7006eda7b7a100b3946421ac22568a237a5cbdb5e6e0bcf6
+oid sha256:57c70eecbb605830eed8afa6c291753906e4924192662b52c282aa211f38258c
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b537415099b4fb84548a99ebaec35907a0fc4490d5fe0a4c84c07ffa2bf7bf50
+oid sha256:609cbf6a4993f8285635eeb10c841bd596cbd605eada2cff60dd42e16c85e204
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0714e6bfccc9a358cd19a2b45b95d9f9395b83263bcb92f939aea996ebca9f91
+oid sha256:d761a865805231e466975dc557ac832a6f542610cb998ae0219bb55a7ba68b7d
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9173b9e78ef03aad0f04cce45b6dd4cd762fd1e3af45be45f1edc8608b48941
+oid sha256:87d4e73dab5b4a75d4f3cf3fb27527e28899c234f2c83e5118101993055d7a25
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3df3773229a01fb4d0668ee0953bfa25c738916ccfae043256be725b68d3f8d
+oid sha256:2a382728146b27225e38b8e01d45648e3fa48bcb35e4b2715ad4ce673fcd096c
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6310a13a94705357977cd171448552ccc093815d826e16064315b8e259c7fd
+oid sha256:c39412d919b7b82dcf9c9c10833616604451f675b8dda18c6254956563df2fe2
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0576,
+  "epoch": 0.1152,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 227.65,
       "eval_steps_per_second": 7.141,
       "step": 9
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 1.4526073932647705,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 2.378,
+      "step": 12
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 1.4305192232131958,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 2.3302,
+      "step": 15
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 1.1190311908721924,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 2.2509,
+      "step": 18
+    },
+    {
+      "epoch": 0.1152,
+      "eval_loss": 2.1677029132843018,
+      "eval_runtime": 4.5951,
+      "eval_samples_per_second": 228.939,
+      "eval_steps_per_second": 7.182,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4576824797364224e+16,
+  "total_flos": 2.9053119979585536e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null