Training in progress, step 49, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be04c9972e630958da8e44f9e4c9f9dcc16a03ca8ed2f4a5769d950bd0776ae2
+oid sha256:a3a249c8004081b9004e69983f978e119b5bf2063bc16bae03b87b6c29ca74a0
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b84d2d470a3f640e4b2cc4ce5ce8e6839289bdc697bdd545f7d7c8dd8c51b39
+oid sha256:d155b28f5e7ed79a50ef3a32a655a17e7d9d4a06d622aba236d8bd6b5b6c0883
 size 328468404

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd2a2f2b84ec4af4de6e78c117101bf220fbb0d23f8d3186fde1f407aca376f
+oid sha256:9be25ff62256a472fa1f448e3d453c1943f4c5ebc354b49207e62f20236deb6a
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd5de8cc5f988a2c3a2846ee47dd1b1c807c4b36aee9e6556e2dd8a5d0ef776a
+oid sha256:41f415cc44747810bca05c75d13f5253fa09a627c8a57f4da3e109dd0e1d508c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a3a3147e9469653998f2b1fc733e316bbebf9c0ef7c13d269390e72efd2c6b
+oid sha256:b4dff8eb55605cbb8ac33421a282c2a3344fd33ccc979ba253b9e98ac353951c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb24ecc1303aadd1770afee5c5d48c535ac4827ae4531643a669c0d145e5db0
+oid sha256:16dedcb8131c0bf718453558c27ee6713605b2e55751923de748d81e923d0f55
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fabed08622e08b27f1841ea221cb1eb063940b7a5bf0e62bf1a780665944540
+oid sha256:aab4a9e4ef073c8d05cbd3393b8f5e2be7efebf8d31894ffbc118b030a35e18a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6633663366336635,
+  "epoch": 1.9405940594059405,
   "eval_steps": 7,
-  "global_step": 42,
+  "global_step": 49,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,28 @@
       "eval_samples_per_second": 65.965,
       "eval_steps_per_second": 4.656,
       "step": 42
+    },
+    {
+      "epoch": 1.7821782178217822,
+      "grad_norm": 0.8776001930236816,
+      "learning_rate": 4.5247197834790876e-05,
+      "loss": 1.1555,
+      "step": 45
+    },
+    {
+      "epoch": 1.900990099009901,
+      "grad_norm": 0.8503000140190125,
+      "learning_rate": 3.821205322452863e-05,
+      "loss": 1.2638,
+      "step": 48
+    },
+    {
+      "epoch": 1.9405940594059405,
+      "eval_loss": 1.384788155555725,
+      "eval_runtime": 1.2856,
+      "eval_samples_per_second": 66.119,
+      "eval_steps_per_second": 4.667,
+      "step": 49
     }
   ],
   "logging_steps": 3,
@@ -180,7 +202,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.194386467502162e+17,
+  "total_flos": 1.3934508787525222e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null