Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf52b0ada46970d3e1855ea26ffccd2f3233bd666c365028f484d061e1c0a17
+oid sha256:8bbcde4cfa01463b2b127e5e23714f2f90debc9e3e722328670f98410cac8364
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f403744b21ccb9fe07dcbb80edbb1c4d243f8221833ca24906e82e06bf28b584
+oid sha256:5a44a38f71ee75703bb570e8101481509bdf3085c448c97d9b3f941b5573bcf7
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dccf15704fbdf23856e1119baffae48b962f09fb2232cc45a115390986e7d5d
+oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
 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": 0.0042215467747382645,
+  "epoch": 0.008443093549476529,
   "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": 0.467,
       "step": 25
+    },
+    {
+      "epoch": 0.004390408645727794,
+      "grad_norm": 11.489653587341309,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.6607,
+      "step": 26
+    },
+    {
+      "epoch": 0.004559270516717325,
+      "grad_norm": 10.87166690826416,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.251,
+      "step": 27
+    },
+    {
+      "epoch": 0.004559270516717325,
+      "eval_loss": 0.19702549278736115,
+      "eval_runtime": 549.5055,
+      "eval_samples_per_second": 9.075,
+      "eval_steps_per_second": 1.136,
+      "step": 27
+    },
+    {
+      "epoch": 0.004728132387706856,
+      "grad_norm": 4.551630973815918,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.1867,
+      "step": 28
+    },
+    {
+      "epoch": 0.004896994258696386,
+      "grad_norm": 4.584312915802002,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.1185,
+      "step": 29
+    },
+    {
+      "epoch": 0.005065856129685917,
+      "grad_norm": 3.1855695247650146,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0763,
+      "step": 30
+    },
+    {
+      "epoch": 0.005234718000675448,
+      "grad_norm": 3.6154963970184326,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.1514,
+      "step": 31
+    },
+    {
+      "epoch": 0.005403579871664978,
+      "grad_norm": 2.6439056396484375,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.106,
+      "step": 32
+    },
+    {
+      "epoch": 0.005572441742654508,
+      "grad_norm": 3.4792051315307617,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.2561,
+      "step": 33
+    },
+    {
+      "epoch": 0.005741303613644039,
+      "grad_norm": 2.5845413208007812,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0694,
+      "step": 34
+    },
+    {
+      "epoch": 0.00591016548463357,
+      "grad_norm": 5.633108615875244,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.2615,
+      "step": 35
+    },
+    {
+      "epoch": 0.0060790273556231,
+      "grad_norm": 1.69390070438385,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0489,
+      "step": 36
+    },
+    {
+      "epoch": 0.0060790273556231,
+      "eval_loss": 0.14112035930156708,
+      "eval_runtime": 549.905,
+      "eval_samples_per_second": 9.069,
+      "eval_steps_per_second": 1.135,
+      "step": 36
+    },
+    {
+      "epoch": 0.006247889226612631,
+      "grad_norm": 3.9095728397369385,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.177,
+      "step": 37
+    },
+    {
+      "epoch": 0.006416751097602162,
+      "grad_norm": 3.213510751724243,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.1018,
+      "step": 38
+    },
+    {
+      "epoch": 0.006585612968591692,
+      "grad_norm": 0.6583210825920105,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0182,
+      "step": 39
+    },
+    {
+      "epoch": 0.006754474839581222,
+      "grad_norm": 2.233595371246338,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0855,
+      "step": 40
+    },
+    {
+      "epoch": 0.006923336710570753,
+      "grad_norm": 4.077779769897461,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.2739,
+      "step": 41
+    },
+    {
+      "epoch": 0.0070921985815602835,
+      "grad_norm": 0.9433442950248718,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0213,
+      "step": 42
+    },
+    {
+      "epoch": 0.007261060452549814,
+      "grad_norm": 1.9460291862487793,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0612,
+      "step": 43
+    },
+    {
+      "epoch": 0.007429922323539345,
+      "grad_norm": 1.7257614135742188,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0572,
+      "step": 44
+    },
+    {
+      "epoch": 0.007598784194528876,
+      "grad_norm": 2.224824905395508,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0212,
+      "step": 45
+    },
+    {
+      "epoch": 0.007598784194528876,
+      "eval_loss": 0.11776414513587952,
+      "eval_runtime": 549.1937,
+      "eval_samples_per_second": 9.081,
+      "eval_steps_per_second": 1.136,
+      "step": 45
+    },
+    {
+      "epoch": 0.007767646065518406,
+      "grad_norm": 2.233121395111084,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0473,
+      "step": 46
+    },
+    {
+      "epoch": 0.007936507936507936,
+      "grad_norm": 5.550644874572754,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.3432,
+      "step": 47
+    },
+    {
+      "epoch": 0.008105369807497468,
+      "grad_norm": 1.9874426126480103,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0844,
+      "step": 48
+    },
+    {
+      "epoch": 0.008274231678486997,
+      "grad_norm": 0.4189305901527405,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0099,
+      "step": 49
+    },
+    {
+      "epoch": 0.008443093549476529,
+      "grad_norm": 4.122661590576172,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0626,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.85471820890112e+16,
+  "total_flos": 3.70943641780224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null