Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e17fa18be372baf32000af11faeb5c3d0dceed24b5fc9e65d07b42195264cc
+oid sha256:9ca2c7324f68b30544a7f153c3ee7d440ed9e719d3766920ad8b056f7d199d27
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0150c2116bea9bba32eccc6f00e21ae94dbf568c50e3a4fbc590c5709660d57
+oid sha256:dda61902e742b50b338d72ccf1aeb1fc32ab070ea2e0721ce534a0aa1765b30a
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c7abc92a27b0b273f741dae9c7618464e891c61e90ac22845483a90f2b6a69
+oid sha256:026030288cd601691b26a9dd3addc963d8372e0cdb3ae5ae397bb1e558a3e4d2
 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": 0.07225433526011561,
+  "epoch": 0.14450867052023122,
   "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": 2.9553,
       "step": 25
+    },
+    {
+      "epoch": 0.07514450867052024,
+      "grad_norm": 2.6830172538757324,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.9984,
+      "step": 26
+    },
+    {
+      "epoch": 0.07803468208092486,
+      "grad_norm": 2.6048848628997803,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 3.146,
+      "step": 27
+    },
+    {
+      "epoch": 0.07803468208092486,
+      "eval_loss": 2.980114221572876,
+      "eval_runtime": 8.8703,
+      "eval_samples_per_second": 32.919,
+      "eval_steps_per_second": 4.171,
+      "step": 27
+    },
+    {
+      "epoch": 0.08092485549132948,
+      "grad_norm": 2.5352957248687744,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.8203,
+      "step": 28
+    },
+    {
+      "epoch": 0.0838150289017341,
+      "grad_norm": 2.465588331222534,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.8266,
+      "step": 29
+    },
+    {
+      "epoch": 0.08670520231213873,
+      "grad_norm": 2.6173558235168457,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 3.0962,
+      "step": 30
+    },
+    {
+      "epoch": 0.08959537572254335,
+      "grad_norm": 2.6473875045776367,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.8749,
+      "step": 31
+    },
+    {
+      "epoch": 0.09248554913294797,
+      "grad_norm": 2.5935564041137695,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 2.7621,
+      "step": 32
+    },
+    {
+      "epoch": 0.0953757225433526,
+      "grad_norm": 2.4422733783721924,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.7569,
+      "step": 33
+    },
+    {
+      "epoch": 0.09826589595375723,
+      "grad_norm": 2.623366355895996,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.8016,
+      "step": 34
+    },
+    {
+      "epoch": 0.10115606936416185,
+      "grad_norm": 2.533163547515869,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.9004,
+      "step": 35
+    },
+    {
+      "epoch": 0.10404624277456648,
+      "grad_norm": 2.4128429889678955,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.7106,
+      "step": 36
+    },
+    {
+      "epoch": 0.10404624277456648,
+      "eval_loss": 2.8798065185546875,
+      "eval_runtime": 8.8724,
+      "eval_samples_per_second": 32.911,
+      "eval_steps_per_second": 4.17,
+      "step": 36
+    },
+    {
+      "epoch": 0.1069364161849711,
+      "grad_norm": 2.8826918601989746,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.6589,
+      "step": 37
+    },
+    {
+      "epoch": 0.10982658959537572,
+      "grad_norm": 2.6255695819854736,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.9028,
+      "step": 38
+    },
+    {
+      "epoch": 0.11271676300578035,
+      "grad_norm": 2.598806619644165,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.9346,
+      "step": 39
+    },
+    {
+      "epoch": 0.11560693641618497,
+      "grad_norm": 2.8739166259765625,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 3.2118,
+      "step": 40
+    },
+    {
+      "epoch": 0.11849710982658959,
+      "grad_norm": 2.8248085975646973,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 3.0775,
+      "step": 41
+    },
+    {
+      "epoch": 0.12138728323699421,
+      "grad_norm": 2.626497745513916,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.6998,
+      "step": 42
+    },
+    {
+      "epoch": 0.12427745664739884,
+      "grad_norm": 2.717621088027954,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.9985,
+      "step": 43
+    },
+    {
+      "epoch": 0.12716763005780346,
+      "grad_norm": 2.500718355178833,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.545,
+      "step": 44
+    },
+    {
+      "epoch": 0.13005780346820808,
+      "grad_norm": 2.7403721809387207,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.8951,
+      "step": 45
+    },
+    {
+      "epoch": 0.13005780346820808,
+      "eval_loss": 2.8127658367156982,
+      "eval_runtime": 8.8782,
+      "eval_samples_per_second": 32.89,
+      "eval_steps_per_second": 4.168,
+      "step": 45
+    },
+    {
+      "epoch": 0.1329479768786127,
+      "grad_norm": 2.7176103591918945,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.5859,
+      "step": 46
+    },
+    {
+      "epoch": 0.13583815028901733,
+      "grad_norm": 2.871258020401001,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.7279,
+      "step": 47
+    },
+    {
+      "epoch": 0.13872832369942195,
+      "grad_norm": 2.6269922256469727,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.7583,
+      "step": 48
+    },
+    {
+      "epoch": 0.1416184971098266,
+      "grad_norm": 2.6989223957061768,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.7658,
+      "step": 49
+    },
+    {
+      "epoch": 0.14450867052023122,
+      "grad_norm": 3.0512256622314453,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.8892,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2419306423910400.0,
+  "total_flos": 4838612847820800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null