Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19578da7be21b66f352572006632cfb377c54cc6c83a341e66d04de3b1e9224c
+oid sha256:ddbfce897a555c88107f76de9ae66ca937095237ba2c420d224677b6519ebc6e
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770a0f145c53a38b107e2a48f179135e61c22c0c2b87834e1ef830c61057ca7c
+oid sha256:5c8d52de9a6cb58763caff040015fca04f8556a4605ae295156114cbe89344bc
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c334162029911df951f21e152e5ddf37f5d979575a6d060ad1d369247ccd5d4
+oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
 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": 0.01718213058419244,
+  "epoch": 0.03436426116838488,
   "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": 1.528,
       "step": 25
+    },
+    {
+      "epoch": 0.017869415807560136,
+      "grad_norm": 0.8513308763504028,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.5835,
+      "step": 26
+    },
+    {
+      "epoch": 0.018556701030927835,
+      "grad_norm": 0.6795158982276917,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.5386,
+      "step": 27
+    },
+    {
+      "epoch": 0.018556701030927835,
+      "eval_loss": 0.748094916343689,
+      "eval_runtime": 253.4746,
+      "eval_samples_per_second": 4.837,
+      "eval_steps_per_second": 0.608,
+      "step": 27
+    },
+    {
+      "epoch": 0.019243986254295534,
+      "grad_norm": 0.7328270077705383,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.551,
+      "step": 28
+    },
+    {
+      "epoch": 0.01993127147766323,
+      "grad_norm": 0.7274560928344727,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.4977,
+      "step": 29
+    },
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 0.7910637259483337,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.4872,
+      "step": 30
+    },
+    {
+      "epoch": 0.021305841924398626,
+      "grad_norm": 0.8576248288154602,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.4049,
+      "step": 31
+    },
+    {
+      "epoch": 0.021993127147766325,
+      "grad_norm": 0.9982084631919861,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.3457,
+      "step": 32
+    },
+    {
+      "epoch": 0.02268041237113402,
+      "grad_norm": 0.7275662422180176,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.345,
+      "step": 33
+    },
+    {
+      "epoch": 0.02336769759450172,
+      "grad_norm": 0.7337255477905273,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.3482,
+      "step": 34
+    },
+    {
+      "epoch": 0.024054982817869417,
+      "grad_norm": 0.8252787590026855,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.3413,
+      "step": 35
+    },
+    {
+      "epoch": 0.024742268041237112,
+      "grad_norm": 0.9308682084083557,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.3861,
+      "step": 36
+    },
+    {
+      "epoch": 0.024742268041237112,
+      "eval_loss": 0.6290791034698486,
+      "eval_runtime": 252.791,
+      "eval_samples_per_second": 4.85,
+      "eval_steps_per_second": 0.609,
+      "step": 36
+    },
+    {
+      "epoch": 0.02542955326460481,
+      "grad_norm": 0.8834632635116577,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.2901,
+      "step": 37
+    },
+    {
+      "epoch": 0.02611683848797251,
+      "grad_norm": 0.7757920026779175,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.238,
+      "step": 38
+    },
+    {
+      "epoch": 0.026804123711340205,
+      "grad_norm": 0.9437708854675293,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.1715,
+      "step": 39
+    },
+    {
+      "epoch": 0.027491408934707903,
+      "grad_norm": 0.9284512400627136,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.091,
+      "step": 40
+    },
+    {
+      "epoch": 0.028178694158075602,
+      "grad_norm": 0.8415759205818176,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.1651,
+      "step": 41
+    },
+    {
+      "epoch": 0.0288659793814433,
+      "grad_norm": 0.8733612895011902,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.1425,
+      "step": 42
+    },
+    {
+      "epoch": 0.029553264604810996,
+      "grad_norm": 0.9334592819213867,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.1424,
+      "step": 43
+    },
+    {
+      "epoch": 0.030240549828178694,
+      "grad_norm": 0.8202064037322998,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.1921,
+      "step": 44
+    },
+    {
+      "epoch": 0.030927835051546393,
+      "grad_norm": 0.7855863571166992,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.1513,
+      "step": 45
+    },
+    {
+      "epoch": 0.030927835051546393,
+      "eval_loss": 0.5508877038955688,
+      "eval_runtime": 252.7564,
+      "eval_samples_per_second": 4.851,
+      "eval_steps_per_second": 0.609,
+      "step": 45
+    },
+    {
+      "epoch": 0.03161512027491409,
+      "grad_norm": 0.8433973789215088,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.0264,
+      "step": 46
+    },
+    {
+      "epoch": 0.03230240549828179,
+      "grad_norm": 0.8501434922218323,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.0172,
+      "step": 47
+    },
+    {
+      "epoch": 0.032989690721649485,
+      "grad_norm": 0.8408077359199524,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.1105,
+      "step": 48
+    },
+    {
+      "epoch": 0.03367697594501718,
+      "grad_norm": 0.8546326160430908,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.1052,
+      "step": 49
+    },
+    {
+      "epoch": 0.03436426116838488,
+      "grad_norm": 0.8061237931251526,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.0345,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1739149811712e+16,
+  "total_flos": 6.3478299623424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null