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:ea64ed130d0ef8f289148ea621136002897a5fb55f7f129430c910aa5feae12a
+oid sha256:cd3917f24d36ecc7216e9eadcfc0ecdaee49dbada66ce0c4f19c90898b55a400
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355696199e252227eb16466b175b3181f8c86b445112db1425685c39e0d17883
+oid sha256:c4d38b6b5e92584c139f54a6f1b82207501f0742015843f45e4b67752adbb7d8
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399f4300e86eac772c2e46dc0bc520439cb85ab9dbbd73bd0ad5009da807761b
+oid sha256:911058565dc868849673710656c32933e9a5c0c739dc26b6d67dce13bb3e41c3
 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": 0.009321401938851604,
+  "epoch": 0.018642803877703208,
   "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": 0.7409,
       "step": 25
+    },
+    {
+      "epoch": 0.009694258016405667,
+      "grad_norm": 3.393937110900879,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.768,
+      "step": 26
+    },
+    {
+      "epoch": 0.010067114093959731,
+      "grad_norm": 2.6685173511505127,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.6532,
+      "step": 27
+    },
+    {
+      "epoch": 0.010067114093959731,
+      "eval_loss": 0.3525005280971527,
+      "eval_runtime": 353.0466,
+      "eval_samples_per_second": 6.399,
+      "eval_steps_per_second": 0.802,
+      "step": 27
+    },
+    {
+      "epoch": 0.010439970171513796,
+      "grad_norm": 2.637833595275879,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.6783,
+      "step": 28
+    },
+    {
+      "epoch": 0.01081282624906786,
+      "grad_norm": 2.6375908851623535,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.8731,
+      "step": 29
+    },
+    {
+      "epoch": 0.011185682326621925,
+      "grad_norm": 3.6596407890319824,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.8254,
+      "step": 30
+    },
+    {
+      "epoch": 0.011558538404175988,
+      "grad_norm": 2.597501754760742,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.6116,
+      "step": 31
+    },
+    {
+      "epoch": 0.011931394481730051,
+      "grad_norm": 2.175229787826538,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.5833,
+      "step": 32
+    },
+    {
+      "epoch": 0.012304250559284116,
+      "grad_norm": 2.7441792488098145,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.8438,
+      "step": 33
+    },
+    {
+      "epoch": 0.01267710663683818,
+      "grad_norm": 2.9346845149993896,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.8046,
+      "step": 34
+    },
+    {
+      "epoch": 0.013049962714392245,
+      "grad_norm": 2.7344934940338135,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.6102,
+      "step": 35
+    },
+    {
+      "epoch": 0.013422818791946308,
+      "grad_norm": 2.4309346675872803,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.5593,
+      "step": 36
+    },
+    {
+      "epoch": 0.013422818791946308,
+      "eval_loss": 0.30376312136650085,
+      "eval_runtime": 353.0002,
+      "eval_samples_per_second": 6.399,
+      "eval_steps_per_second": 0.802,
+      "step": 36
+    },
+    {
+      "epoch": 0.013795674869500374,
+      "grad_norm": 2.6589467525482178,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.5914,
+      "step": 37
+    },
+    {
+      "epoch": 0.014168530947054437,
+      "grad_norm": 3.2474007606506348,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.6242,
+      "step": 38
+    },
+    {
+      "epoch": 0.0145413870246085,
+      "grad_norm": 2.08449125289917,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.523,
+      "step": 39
+    },
+    {
+      "epoch": 0.014914243102162566,
+      "grad_norm": 1.5239322185516357,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4422,
+      "step": 40
+    },
+    {
+      "epoch": 0.015287099179716629,
+      "grad_norm": 2.0777080059051514,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.5522,
+      "step": 41
+    },
+    {
+      "epoch": 0.015659955257270694,
+      "grad_norm": 2.9804673194885254,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.8012,
+      "step": 42
+    },
+    {
+      "epoch": 0.01603281133482476,
+      "grad_norm": 1.4776819944381714,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.3703,
+      "step": 43
+    },
+    {
+      "epoch": 0.01640566741237882,
+      "grad_norm": 1.9899928569793701,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.4545,
+      "step": 44
+    },
+    {
+      "epoch": 0.016778523489932886,
+      "grad_norm": 2.4433422088623047,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.5579,
+      "step": 45
+    },
+    {
+      "epoch": 0.016778523489932886,
+      "eval_loss": 0.27536752820014954,
+      "eval_runtime": 352.9507,
+      "eval_samples_per_second": 6.4,
+      "eval_steps_per_second": 0.802,
+      "step": 45
+    },
+    {
+      "epoch": 0.01715137956748695,
+      "grad_norm": 3.4268898963928223,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5382,
+      "step": 46
+    },
+    {
+      "epoch": 0.017524235645041013,
+      "grad_norm": 2.0205821990966797,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.4476,
+      "step": 47
+    },
+    {
+      "epoch": 0.017897091722595078,
+      "grad_norm": 3.0076658725738525,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.5125,
+      "step": 48
+    },
+    {
+      "epoch": 0.018269947800149143,
+      "grad_norm": 3.84687876701355,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.5999,
+      "step": 49
+    },
+    {
+      "epoch": 0.018642803877703208,
+      "grad_norm": 1.8309787511825562,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.4413,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.173894848512e+16,
+  "total_flos": 6.347789697024e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null