Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3917f24d36ecc7216e9eadcfc0ecdaee49dbada66ce0c4f19c90898b55a400
+oid sha256:f1e97bd296e883539018dac2ffe46aed430c2ce0fe546710541cfb36d7621cee
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d38b6b5e92584c139f54a6f1b82207501f0742015843f45e4b67752adbb7d8
+oid sha256:06904eaa66bcdf5fb5698e14b602a4fa7ed63d748a149fa8ce1b94bef7b4096e
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911058565dc868849673710656c32933e9a5c0c739dc26b6d67dce13bb3e41c3
+oid sha256:9cad2658200f2482b7574bdc57c18294b67c90589354a1df1f50b18ca492e76c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018642803877703208,
+  "epoch": 0.02796420581655481,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 0.4413,
       "step": 50
+    },
+    {
+      "epoch": 0.01901565995525727,
+      "grad_norm": 2.404618263244629,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.4902,
+      "step": 51
+    },
+    {
+      "epoch": 0.019388516032811335,
+      "grad_norm": 2.2248353958129883,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.426,
+      "step": 52
+    },
+    {
+      "epoch": 0.0197613721103654,
+      "grad_norm": 1.5294620990753174,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.3083,
+      "step": 53
+    },
+    {
+      "epoch": 0.020134228187919462,
+      "grad_norm": 2.840945243835449,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.5174,
+      "step": 54
+    },
+    {
+      "epoch": 0.020134228187919462,
+      "eval_loss": 0.256969153881073,
+      "eval_runtime": 352.9528,
+      "eval_samples_per_second": 6.4,
+      "eval_steps_per_second": 0.802,
+      "step": 54
+    },
+    {
+      "epoch": 0.020507084265473527,
+      "grad_norm": 2.9101431369781494,
+      "learning_rate": 5e-05,
+      "loss": 0.5569,
+      "step": 55
+    },
+    {
+      "epoch": 0.020879940343027592,
+      "grad_norm": 2.4050216674804688,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.6652,
+      "step": 56
+    },
+    {
+      "epoch": 0.021252796420581657,
+      "grad_norm": 2.165149211883545,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.4262,
+      "step": 57
+    },
+    {
+      "epoch": 0.02162565249813572,
+      "grad_norm": 2.01960825920105,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.6341,
+      "step": 58
+    },
+    {
+      "epoch": 0.021998508575689784,
+      "grad_norm": 1.9947001934051514,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.5419,
+      "step": 59
+    },
+    {
+      "epoch": 0.02237136465324385,
+      "grad_norm": 2.3822672367095947,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.5953,
+      "step": 60
+    },
+    {
+      "epoch": 0.02274422073079791,
+      "grad_norm": 2.9558725357055664,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.6823,
+      "step": 61
+    },
+    {
+      "epoch": 0.023117076808351976,
+      "grad_norm": 2.5282161235809326,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.5637,
+      "step": 62
+    },
+    {
+      "epoch": 0.02348993288590604,
+      "grad_norm": 2.7243053913116455,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.486,
+      "step": 63
+    },
+    {
+      "epoch": 0.02348993288590604,
+      "eval_loss": 0.25008442997932434,
+      "eval_runtime": 353.0164,
+      "eval_samples_per_second": 6.399,
+      "eval_steps_per_second": 0.802,
+      "step": 63
+    },
+    {
+      "epoch": 0.023862788963460103,
+      "grad_norm": 2.5961456298828125,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.709,
+      "step": 64
+    },
+    {
+      "epoch": 0.024235645041014168,
+      "grad_norm": 1.7899454832077026,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.3097,
+      "step": 65
+    },
+    {
+      "epoch": 0.024608501118568233,
+      "grad_norm": 2.0271105766296387,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.5219,
+      "step": 66
+    },
+    {
+      "epoch": 0.024981357196122298,
+      "grad_norm": 2.0244550704956055,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.449,
+      "step": 67
+    },
+    {
+      "epoch": 0.02535421327367636,
+      "grad_norm": 2.342764377593994,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.5528,
+      "step": 68
+    },
+    {
+      "epoch": 0.025727069351230425,
+      "grad_norm": 2.4467732906341553,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.5,
+      "step": 69
+    },
+    {
+      "epoch": 0.02609992542878449,
+      "grad_norm": 1.8645575046539307,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3163,
+      "step": 70
+    },
+    {
+      "epoch": 0.02647278150633855,
+      "grad_norm": 2.5564777851104736,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.5877,
+      "step": 71
+    },
+    {
+      "epoch": 0.026845637583892617,
+      "grad_norm": 2.0534887313842773,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.5893,
+      "step": 72
+    },
+    {
+      "epoch": 0.026845637583892617,
+      "eval_loss": 0.24400091171264648,
+      "eval_runtime": 352.9932,
+      "eval_samples_per_second": 6.4,
+      "eval_steps_per_second": 0.802,
+      "step": 72
+    },
+    {
+      "epoch": 0.027218493661446682,
+      "grad_norm": 2.7727997303009033,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.5884,
+      "step": 73
+    },
+    {
+      "epoch": 0.027591349739000747,
+      "grad_norm": 1.9303561449050903,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.6323,
+      "step": 74
+    },
+    {
+      "epoch": 0.02796420581655481,
+      "grad_norm": 2.5347917079925537,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.4399,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 9.521684545536e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null