Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe5865a16ea3adfb05ce08b6a2e27d9e54275ac76ed8498c3010b791b817458
+oid sha256:da2d0908d827d73911049b36e4b4e54b834332a60e7bf656045c037af02ba8d9
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb56247b15ebe2c924d648bf840df19f08dd2a840e337cf5b3e67562a43f355f
+oid sha256:e2f2ee6942d7906ff67c6040abfc8b61ed9c77b613bff537b6b97892e9823078
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d31179bc5d1762a031831bcb1c9b6e1688894a2d82366a2cb2821eadc9bee1
+oid sha256:0ada99bda9eb56b1e17b5e710139270a96fa28f2071366d96bbf58fda1c0e60e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007040270346381301,
+  "epoch": 0.014080540692762602,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 2.5545,
       "step": 25
+    },
+    {
+      "epoch": 0.007321881160236553,
+      "grad_norm": 3.004551887512207,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.1855,
+      "step": 26
+    },
+    {
+      "epoch": 0.007603491974091805,
+      "grad_norm": 2.196512460708618,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.9427,
+      "step": 27
+    },
+    {
+      "epoch": 0.007603491974091805,
+      "eval_loss": 0.9296455383300781,
+      "eval_runtime": 518.8812,
+      "eval_samples_per_second": 5.762,
+      "eval_steps_per_second": 0.721,
+      "step": 27
+    },
+    {
+      "epoch": 0.007885102787947058,
+      "grad_norm": 1.2902026176452637,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.6342,
+      "step": 28
+    },
+    {
+      "epoch": 0.008166713601802308,
+      "grad_norm": 2.955904483795166,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.8788,
+      "step": 29
+    },
+    {
+      "epoch": 0.00844832441565756,
+      "grad_norm": 3.204195976257324,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.7209,
+      "step": 30
+    },
+    {
+      "epoch": 0.008729935229512813,
+      "grad_norm": 1.4495835304260254,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.5066,
+      "step": 31
+    },
+    {
+      "epoch": 0.009011546043368065,
+      "grad_norm": 1.1010254621505737,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.4999,
+      "step": 32
+    },
+    {
+      "epoch": 0.009293156857223317,
+      "grad_norm": 0.9905458688735962,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.4371,
+      "step": 33
+    },
+    {
+      "epoch": 0.009574767671078569,
+      "grad_norm": 0.7902398705482483,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.433,
+      "step": 34
+    },
+    {
+      "epoch": 0.009856378484933821,
+      "grad_norm": 0.7530960440635681,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.4247,
+      "step": 35
+    },
+    {
+      "epoch": 0.010137989298789073,
+      "grad_norm": 0.981115996837616,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.4491,
+      "step": 36
+    },
+    {
+      "epoch": 0.010137989298789073,
+      "eval_loss": 0.7092130184173584,
+      "eval_runtime": 518.7764,
+      "eval_samples_per_second": 5.764,
+      "eval_steps_per_second": 0.721,
+      "step": 36
+    },
+    {
+      "epoch": 0.010419600112644326,
+      "grad_norm": 0.5802685618400574,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.4158,
+      "step": 37
+    },
+    {
+      "epoch": 0.010701210926499578,
+      "grad_norm": 0.7508324384689331,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.4274,
+      "step": 38
+    },
+    {
+      "epoch": 0.01098282174035483,
+      "grad_norm": 0.8648625612258911,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.4218,
+      "step": 39
+    },
+    {
+      "epoch": 0.011264432554210082,
+      "grad_norm": 0.8676905632019043,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.4303,
+      "step": 40
+    },
+    {
+      "epoch": 0.011546043368065334,
+      "grad_norm": 0.3803287148475647,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.4144,
+      "step": 41
+    },
+    {
+      "epoch": 0.011827654181920586,
+      "grad_norm": 0.3803757429122925,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.4255,
+      "step": 42
+    },
+    {
+      "epoch": 0.012109264995775838,
+      "grad_norm": 0.34761127829551697,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.4156,
+      "step": 43
+    },
+    {
+      "epoch": 0.01239087580963109,
+      "grad_norm": 0.3840619921684265,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.4275,
+      "step": 44
+    },
+    {
+      "epoch": 0.012672486623486343,
+      "grad_norm": 0.32926231622695923,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.4243,
+      "step": 45
+    },
+    {
+      "epoch": 0.012672486623486343,
+      "eval_loss": 0.7055554389953613,
+      "eval_runtime": 518.8734,
+      "eval_samples_per_second": 5.762,
+      "eval_steps_per_second": 0.721,
+      "step": 45
+    },
+    {
+      "epoch": 0.012954097437341595,
+      "grad_norm": 0.2857879400253296,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.41,
+      "step": 46
+    },
+    {
+      "epoch": 0.013235708251196845,
+      "grad_norm": 0.2769199013710022,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.409,
+      "step": 47
+    },
+    {
+      "epoch": 0.013517319065052097,
+      "grad_norm": 0.2755632996559143,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.4072,
+      "step": 48
+    },
+    {
+      "epoch": 0.01379892987890735,
+      "grad_norm": 0.3106071650981903,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.4099,
+      "step": 49
+    },
+    {
+      "epoch": 0.014080540692762602,
+      "grad_norm": 0.32463961839675903,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.3935,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.201976757334835e+16,
+  "total_flos": 6.305933818016563e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null