Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26148420a8411ad0a8ec334040e12f7f0c9cf209b6ef1886744db02e5f4e42f7
+oid sha256:736cc904fe42db75124c502528802e9986d173013d003a76fa9d16139e9279c2
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d1210268ee2b6da43f13e1e4eb884f59fcb11064907ce037f238155c184a77
+oid sha256:167b1d5b76ee3885fc545df3e4b62dfe930b2982fe317685ea87e7124c4c5dd0
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c1e071484f39f84a54d4490ceb32e39b610b1d7872dd7015147a94ea051100
+oid sha256:78f41be5c88476689759b9aea9c9a092f32c18103b8517aabcee6889335d5829
 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": 0.02573340195573855,
+  "epoch": 0.0514668039114771,
   "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": 4.471,
       "step": 25
+    },
+    {
+      "epoch": 0.02676273803396809,
+      "grad_norm": 0.3135339617729187,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 4.7955,
+      "step": 26
+    },
+    {
+      "epoch": 0.027792074112197633,
+      "grad_norm": 0.3900616466999054,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 5.0081,
+      "step": 27
+    },
+    {
+      "epoch": 0.027792074112197633,
+      "eval_loss": 2.386911153793335,
+      "eval_runtime": 227.018,
+      "eval_samples_per_second": 3.603,
+      "eval_steps_per_second": 0.454,
+      "step": 27
+    },
+    {
+      "epoch": 0.028821410190427176,
+      "grad_norm": 0.26265034079551697,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 4.799,
+      "step": 28
+    },
+    {
+      "epoch": 0.029850746268656716,
+      "grad_norm": 0.30579325556755066,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 4.5961,
+      "step": 29
+    },
+    {
+      "epoch": 0.03088008234688626,
+      "grad_norm": 0.42424359917640686,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 4.8045,
+      "step": 30
+    },
+    {
+      "epoch": 0.0319094184251158,
+      "grad_norm": 0.3576556444168091,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 4.8802,
+      "step": 31
+    },
+    {
+      "epoch": 0.032938754503345345,
+      "grad_norm": 0.3096839189529419,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 4.7263,
+      "step": 32
+    },
+    {
+      "epoch": 0.033968090581574885,
+      "grad_norm": 0.425644189119339,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 4.6257,
+      "step": 33
+    },
+    {
+      "epoch": 0.034997426659804425,
+      "grad_norm": 0.3519304394721985,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 4.7576,
+      "step": 34
+    },
+    {
+      "epoch": 0.03602676273803397,
+      "grad_norm": 0.38826555013656616,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 4.7818,
+      "step": 35
+    },
+    {
+      "epoch": 0.03705609881626351,
+      "grad_norm": 0.33783453702926636,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 4.7301,
+      "step": 36
+    },
+    {
+      "epoch": 0.03705609881626351,
+      "eval_loss": 2.3819499015808105,
+      "eval_runtime": 226.8579,
+      "eval_samples_per_second": 3.606,
+      "eval_steps_per_second": 0.454,
+      "step": 36
+    },
+    {
+      "epoch": 0.03808543489449305,
+      "grad_norm": 0.30728089809417725,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 4.6269,
+      "step": 37
+    },
+    {
+      "epoch": 0.0391147709727226,
+      "grad_norm": 0.26561239361763,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 4.8023,
+      "step": 38
+    },
+    {
+      "epoch": 0.04014410705095214,
+      "grad_norm": 0.333359956741333,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 4.6354,
+      "step": 39
+    },
+    {
+      "epoch": 0.041173443129181676,
+      "grad_norm": 0.280263215303421,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 4.9582,
+      "step": 40
+    },
+    {
+      "epoch": 0.04220277920741122,
+      "grad_norm": 0.3637993633747101,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 5.0495,
+      "step": 41
+    },
+    {
+      "epoch": 0.04323211528564076,
+      "grad_norm": 0.3035355806350708,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 4.8531,
+      "step": 42
+    },
+    {
+      "epoch": 0.0442614513638703,
+      "grad_norm": 0.2905413806438446,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 4.8934,
+      "step": 43
+    },
+    {
+      "epoch": 0.04529078744209985,
+      "grad_norm": 0.2680681049823761,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 4.8269,
+      "step": 44
+    },
+    {
+      "epoch": 0.04632012352032939,
+      "grad_norm": 0.2697928547859192,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 4.5012,
+      "step": 45
+    },
+    {
+      "epoch": 0.04632012352032939,
+      "eval_loss": 2.379274845123291,
+      "eval_runtime": 226.8561,
+      "eval_samples_per_second": 3.606,
+      "eval_steps_per_second": 0.454,
+      "step": 45
+    },
+    {
+      "epoch": 0.04734945959855893,
+      "grad_norm": 0.34642162919044495,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 4.8511,
+      "step": 46
+    },
+    {
+      "epoch": 0.048378795676788475,
+      "grad_norm": 0.3296074867248535,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 4.8204,
+      "step": 47
+    },
+    {
+      "epoch": 0.049408131755018014,
+      "grad_norm": 0.27953025698661804,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 5.0973,
+      "step": 48
+    },
+    {
+      "epoch": 0.050437467833247554,
+      "grad_norm": 0.3788706660270691,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 5.0161,
+      "step": 49
+    },
+    {
+      "epoch": 0.0514668039114771,
+      "grad_norm": 0.32087740302085876,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 4.8925,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.169303525117133e+16,
+  "total_flos": 6.077221192492646e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null