Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9548a77ac47543fe5cd9098da7d80bdad1a481f7d391c1b1837b39c89b34b91
+oid sha256:10954919e25df70d17d47d08da3641147eb86f58bed58ae63b019a1a93108720
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7bf078e3475f0d9b2ca772ed9487f4584102e8b342fd0f576bc43218f0456ed
+oid sha256:4308a7cd1cc9b3f277cc27fb3bdab37ec8a0ee103ea9425bca8fa06db8574099
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80ed5260c665ec391e7987f088050b51c569dfcb0e921c9adb929626eebe1be
+oid sha256:96c743e1bffaaa9e09888245c887191bdc321fd3a825e0b54e0754fb6d8a0f61
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a79978dfa6ddff8a4a28cad2123636c6cf98c07bfa70cc82cdf0bf87e99549
+oid sha256:c41fe81b4cb3e7753621de49d816bff984b46a2120fc17d84d3662502b8a590a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4257484ea11c477006dc780c9b0c26532943f017f72314db875d838e616c9b
+oid sha256:930bb06c7aac50b5c7b779e8e688eee40b177540cfffeeec9b6d5599d14d8338
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42569b05c8f9b5ecc94e944ba0b72fe1d228cd39bd27a20c266097383c04c439
+oid sha256:115011f931f8c895df84b559f917c9148825f6404fba1d054d029b7141d9da6e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29673590504451036,
+  "epoch": 0.44510385756676557,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 0.0341,
       "step": 50
+    },
+    {
+      "epoch": 0.3026706231454006,
+      "grad_norm": 0.23903632164001465,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.0517,
+      "step": 51
+    },
+    {
+      "epoch": 0.3086053412462908,
+      "grad_norm": 0.4485885798931122,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0368,
+      "step": 52
+    },
+    {
+      "epoch": 0.314540059347181,
+      "grad_norm": 0.2551536560058594,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.0331,
+      "step": 53
+    },
+    {
+      "epoch": 0.32047477744807124,
+      "grad_norm": 0.32670527696609497,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0466,
+      "step": 54
+    },
+    {
+      "epoch": 0.32047477744807124,
+      "eval_loss": 0.034560102969408035,
+      "eval_runtime": 8.8747,
+      "eval_samples_per_second": 64.002,
+      "eval_steps_per_second": 2.028,
+      "step": 54
+    },
+    {
+      "epoch": 0.3264094955489614,
+      "grad_norm": 0.21245713531970978,
+      "learning_rate": 5e-05,
+      "loss": 0.0219,
+      "step": 55
+    },
+    {
+      "epoch": 0.3323442136498516,
+      "grad_norm": 0.2684561312198639,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0383,
+      "step": 56
+    },
+    {
+      "epoch": 0.33827893175074186,
+      "grad_norm": 0.3183412551879883,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0325,
+      "step": 57
+    },
+    {
+      "epoch": 0.34421364985163205,
+      "grad_norm": 0.22641129791736603,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0304,
+      "step": 58
+    },
+    {
+      "epoch": 0.35014836795252224,
+      "grad_norm": 0.23570093512535095,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0274,
+      "step": 59
+    },
+    {
+      "epoch": 0.3560830860534125,
+      "grad_norm": 0.25089505314826965,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0383,
+      "step": 60
+    },
+    {
+      "epoch": 0.3620178041543027,
+      "grad_norm": 0.2983970642089844,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0408,
+      "step": 61
+    },
+    {
+      "epoch": 0.36795252225519287,
+      "grad_norm": 1.905240774154663,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0407,
+      "step": 62
+    },
+    {
+      "epoch": 0.37388724035608306,
+      "grad_norm": 0.33676159381866455,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0397,
+      "step": 63
+    },
+    {
+      "epoch": 0.37388724035608306,
+      "eval_loss": 0.03145001456141472,
+      "eval_runtime": 8.8871,
+      "eval_samples_per_second": 63.913,
+      "eval_steps_per_second": 2.025,
+      "step": 63
+    },
+    {
+      "epoch": 0.3798219584569733,
+      "grad_norm": 0.22375427186489105,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0261,
+      "step": 64
+    },
+    {
+      "epoch": 0.3857566765578635,
+      "grad_norm": 0.15232010185718536,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.02,
+      "step": 65
+    },
+    {
+      "epoch": 0.3916913946587537,
+      "grad_norm": 0.8229625821113586,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0277,
+      "step": 66
+    },
+    {
+      "epoch": 0.39762611275964393,
+      "grad_norm": 0.3698793649673462,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0258,
+      "step": 67
+    },
+    {
+      "epoch": 0.4035608308605341,
+      "grad_norm": 0.19600550830364227,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0262,
+      "step": 68
+    },
+    {
+      "epoch": 0.4094955489614243,
+      "grad_norm": 0.31710517406463623,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0248,
+      "step": 69
+    },
+    {
+      "epoch": 0.41543026706231456,
+      "grad_norm": 0.2836054563522339,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0232,
+      "step": 70
+    },
+    {
+      "epoch": 0.42136498516320475,
+      "grad_norm": 0.23305663466453552,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0384,
+      "step": 71
+    },
+    {
+      "epoch": 0.42729970326409494,
+      "grad_norm": 0.27690601348876953,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.046,
+      "step": 72
+    },
+    {
+      "epoch": 0.42729970326409494,
+      "eval_loss": 0.030352195724844933,
+      "eval_runtime": 8.8701,
+      "eval_samples_per_second": 64.035,
+      "eval_steps_per_second": 2.029,
+      "step": 72
+    },
+    {
+      "epoch": 0.4332344213649852,
+      "grad_norm": 0.12935283780097961,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0193,
+      "step": 73
+    },
+    {
+      "epoch": 0.4391691394658754,
+      "grad_norm": 0.16147606074810028,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0311,
+      "step": 74
+    },
+    {
+      "epoch": 0.44510385756676557,
+      "grad_norm": 0.22025907039642334,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0305,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4986123154764595e+17,
+  "total_flos": 2.255337347392471e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null