Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2ca049aa7242fc9c322b0fab8011ffd3e1d571a79640f234028b78081ea1f2
+oid sha256:dc23af3af8edcc2583c76cb038ee0ab1273481f1095d522d5ff88300c3a43e6e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d921b43e830f454a0b2c80e9838d50c8559cf565845c7a2cab1632fd24ffe09
+oid sha256:98a929084f8855f23eecffeb3d9d0956a22b85f6197464dbd1cdb30385c3448a
 size 43122580

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ab7e7cc91d8e81564292ef8b01b149cbda6e90f2b1f61711f1527f1bd6413ad
+oid sha256:c1c69b1cab68eedeb20a7a2f6dae4bcafb8fd3614223404432fa886a8349b124
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c79abdee3197794b53f19b69d372310697abffec34b12816e16fe7c787a1347
+oid sha256:46c1c66f8dfc333ab8909acd4d3d3424ff4614f1cc0a55da45ce3aac978468d7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd56eb3a9bc90ffd641d97d678447367d5db97128e19918d8c0022864fb000b
+oid sha256:4e983f405a1a428731c9fb2cfa9409d89f047a5632780bbd7fa48429b301a9db
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806ac1016e21c3aa525ce59382f25c1af12183f5e5ea5f19231eb1f297ece05b
+oid sha256:32aeb81637fab6301be2e2247e68aac5f94e8605d06512d35276a41135901979
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0043896673982779,
+  "epoch": 0.006584501097416849,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,28 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 4.2593,
       "step": 25
+    },
+    {
+      "epoch": 0.005065000844166808,
+      "grad_norm": 18.301593780517578,
+      "learning_rate": 5e-05,
+      "loss": 3.7172,
+      "step": 30
+    },
+    {
+      "epoch": 0.005065000844166808,
+      "eval_loss": 0.9802479147911072,
+      "eval_runtime": 110.0082,
+      "eval_samples_per_second": 90.684,
+      "eval_steps_per_second": 11.336,
+      "step": 30
+    },
+    {
+      "epoch": 0.005909167651527942,
+      "grad_norm": 30.921207427978516,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4898,
+      "step": 35
     }
   ],
   "logging_steps": 5,
@@ -85,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4439961914638336e+16,
+  "total_flos": 5.174757577405235e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null