Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870d5df01f219c103623aacc69d308b72573bfe1b9acc8d39b8a530e79900c80
+oid sha256:ba2c0cca31f098f614c5e2899a67ea75c9baabf478efe85dde1a62cedbf440dd
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982810f0534ab46a23dfc78c7e64f2c789ffbe4b8b641228ce639258cc47ca77
+oid sha256:8f5327a9bfdffedd78d6f803093679e8171964a0829b0a80d61c7be379a13991
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d25fe3ffb548db486237a57047b64320e2862182aa865d34187b2cb58d0ec76
+oid sha256:13c5c39f9b6daa1d7f3d7a5d83c285676ff1d110f0ea0172ff09b0c46c9806cc
 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": 0.01156871818602499,
+  "epoch": 0.02313743637204998,
   "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": 0.1372,
       "step": 25
+    },
+    {
+      "epoch": 0.012031466913465988,
+      "grad_norm": 5.2901458740234375,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.4054,
+      "step": 26
+    },
+    {
+      "epoch": 0.012494215640906987,
+      "grad_norm": 16.79204750061035,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.3945,
+      "step": 27
+    },
+    {
+      "epoch": 0.012494215640906987,
+      "eval_loss": 0.3398672342300415,
+      "eval_runtime": 108.8534,
+      "eval_samples_per_second": 16.72,
+      "eval_steps_per_second": 2.095,
+      "step": 27
+    },
+    {
+      "epoch": 0.012956964368347987,
+      "grad_norm": 12.270838737487793,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.9365,
+      "step": 28
+    },
+    {
+      "epoch": 0.013419713095788986,
+      "grad_norm": 9.225953102111816,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.3784,
+      "step": 29
+    },
+    {
+      "epoch": 0.013882461823229986,
+      "grad_norm": 4.924163341522217,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.401,
+      "step": 30
+    },
+    {
+      "epoch": 0.014345210550670985,
+      "grad_norm": 2.290313720703125,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.2295,
+      "step": 31
+    },
+    {
+      "epoch": 0.014807959278111986,
+      "grad_norm": 2.4892070293426514,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.1456,
+      "step": 32
+    },
+    {
+      "epoch": 0.015270708005552984,
+      "grad_norm": 1.4364653825759888,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.1347,
+      "step": 33
+    },
+    {
+      "epoch": 0.015733456732993985,
+      "grad_norm": 3.6731722354888916,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.1451,
+      "step": 34
+    },
+    {
+      "epoch": 0.016196205460434984,
+      "grad_norm": 3.2023043632507324,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.1694,
+      "step": 35
+    },
+    {
+      "epoch": 0.016658954187875982,
+      "grad_norm": 3.8125226497650146,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.3038,
+      "step": 36
+    },
+    {
+      "epoch": 0.016658954187875982,
+      "eval_loss": 0.21688657999038696,
+      "eval_runtime": 108.8202,
+      "eval_samples_per_second": 16.725,
+      "eval_steps_per_second": 2.095,
+      "step": 36
+    },
+    {
+      "epoch": 0.017121702915316984,
+      "grad_norm": 1.7498458623886108,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0593,
+      "step": 37
+    },
+    {
+      "epoch": 0.017584451642757983,
+      "grad_norm": 2.2368359565734863,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.1137,
+      "step": 38
+    },
+    {
+      "epoch": 0.018047200370198982,
+      "grad_norm": 5.773807048797607,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.3029,
+      "step": 39
+    },
+    {
+      "epoch": 0.01850994909763998,
+      "grad_norm": 1.4326202869415283,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0836,
+      "step": 40
+    },
+    {
+      "epoch": 0.01897269782508098,
+      "grad_norm": 1.1739600896835327,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.1741,
+      "step": 41
+    },
+    {
+      "epoch": 0.01943544655252198,
+      "grad_norm": 1.4607264995574951,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.1426,
+      "step": 42
+    },
+    {
+      "epoch": 0.01989819527996298,
+      "grad_norm": 4.282503128051758,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.3293,
+      "step": 43
+    },
+    {
+      "epoch": 0.02036094400740398,
+      "grad_norm": 3.917597770690918,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.1327,
+      "step": 44
+    },
+    {
+      "epoch": 0.020823692734844978,
+      "grad_norm": 3.9601786136627197,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.2175,
+      "step": 45
+    },
+    {
+      "epoch": 0.020823692734844978,
+      "eval_loss": 0.21302354335784912,
+      "eval_runtime": 108.8413,
+      "eval_samples_per_second": 16.722,
+      "eval_steps_per_second": 2.095,
+      "step": 45
+    },
+    {
+      "epoch": 0.02128644146228598,
+      "grad_norm": 2.9856042861938477,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.3059,
+      "step": 46
+    },
+    {
+      "epoch": 0.02174919018972698,
+      "grad_norm": 1.7201728820800781,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.1166,
+      "step": 47
+    },
+    {
+      "epoch": 0.022211938917167977,
+      "grad_norm": 2.847334623336792,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.1798,
+      "step": 48
+    },
+    {
+      "epoch": 0.022674687644608976,
+      "grad_norm": 2.4103736877441406,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.2387,
+      "step": 49
+    },
+    {
+      "epoch": 0.02313743637204998,
+      "grad_norm": 1.2504336833953857,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0647,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4940970105765888.0,
+  "total_flos": 9779003334328320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null