Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa9a91274d9b0b92b4c6eb46f15f3c433a773032d7ae483f119a3a8af9a36ec7
+oid sha256:6ae275a5d593847471da51ddbf95ee47dc795cb5d50da9d179bbffe093604b45
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb92b2a82a75d56e875a2d34e5ec55de6c6cfca370ba857a6308dcb13fa66cde
+oid sha256:52ae1c8b35c043691704e73b10234ab2aeffc45287c0c7e0d309e1505148642f
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8d8412de774bcc9c6826e721d9aa613d29d76af4b510c94281cb78a6b9db24
+oid sha256:3dc5fd93b9b05230499931de5440078d246a5022cd07a79303d2793ff0bce7b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10576414595452142,
+  "epoch": 0.21152829190904285,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 8.948,
       "eval_steps_per_second": 4.497,
       "step": 25
+    },
+    {
+      "epoch": 0.10999471179270227,
+      "grad_norm": 0.2562794089317322,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.1286,
+      "step": 26
+    },
+    {
+      "epoch": 0.11422527763088314,
+      "grad_norm": 1.385337471961975,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1934,
+      "step": 27
+    },
+    {
+      "epoch": 0.11845584346906399,
+      "grad_norm": 0.28447943925857544,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.1475,
+      "step": 28
+    },
+    {
+      "epoch": 0.12268640930724485,
+      "grad_norm": 0.4681300222873688,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.1723,
+      "step": 29
+    },
+    {
+      "epoch": 0.12691697514542571,
+      "grad_norm": 0.33006489276885986,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1467,
+      "step": 30
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "grad_norm": 1.173805832862854,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.1347,
+      "step": 31
+    },
+    {
+      "epoch": 0.13537810682178741,
+      "grad_norm": 0.3175932466983795,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.154,
+      "step": 32
+    },
+    {
+      "epoch": 0.13960867265996826,
+      "grad_norm": 0.19901403784751892,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.1594,
+      "step": 33
+    },
+    {
+      "epoch": 0.14383923849814914,
+      "grad_norm": 1.1052857637405396,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.2117,
+      "step": 34
+    },
+    {
+      "epoch": 0.14806980433633,
+      "grad_norm": 0.11121287196874619,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.1437,
+      "step": 35
+    },
+    {
+      "epoch": 0.15230037017451084,
+      "grad_norm": 0.18161903321743011,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.1203,
+      "step": 36
+    },
+    {
+      "epoch": 0.1565309360126917,
+      "grad_norm": 0.1642102152109146,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.1832,
+      "step": 37
+    },
+    {
+      "epoch": 0.16076150185087257,
+      "grad_norm": 0.2714860439300537,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.1728,
+      "step": 38
+    },
+    {
+      "epoch": 0.16499206768905342,
+      "grad_norm": 0.3132612109184265,
+      "learning_rate": 5e-05,
+      "loss": 0.149,
+      "step": 39
+    },
+    {
+      "epoch": 0.16922263352723427,
+      "grad_norm": 0.17970287799835205,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.1759,
+      "step": 40
+    },
+    {
+      "epoch": 0.17345319936541512,
+      "grad_norm": 0.2791941463947296,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.1519,
+      "step": 41
+    },
+    {
+      "epoch": 0.177683765203596,
+      "grad_norm": 0.38692009449005127,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1627,
+      "step": 42
+    },
+    {
+      "epoch": 0.18191433104177684,
+      "grad_norm": 0.1635783314704895,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1533,
+      "step": 43
+    },
+    {
+      "epoch": 0.1861448968799577,
+      "grad_norm": 0.23903019726276398,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.1517,
+      "step": 44
+    },
+    {
+      "epoch": 0.19037546271813854,
+      "grad_norm": 0.551013708114624,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1954,
+      "step": 45
+    },
+    {
+      "epoch": 0.19460602855631942,
+      "grad_norm": 0.722944438457489,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.1574,
+      "step": 46
+    },
+    {
+      "epoch": 0.19883659439450027,
+      "grad_norm": 0.6895685791969299,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.1543,
+      "step": 47
+    },
+    {
+      "epoch": 0.20306716023268112,
+      "grad_norm": 4.492163181304932,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.252,
+      "step": 48
+    },
+    {
+      "epoch": 0.20729772607086197,
+      "grad_norm": 0.8367879986763,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.1803,
+      "step": 49
+    },
+    {
+      "epoch": 0.21152829190904285,
+      "grad_norm": 0.26023951172828674,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.1944,
+      "step": 50
+    },
+    {
+      "epoch": 0.21152829190904285,
+      "eval_loss": 0.162020742893219,
+      "eval_runtime": 22.2041,
+      "eval_samples_per_second": 8.962,
+      "eval_steps_per_second": 4.504,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.73005226082304e+16,
+  "total_flos": 7.46010452164608e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null